From d56b74b9e1b8d747171dc6ff60315c00c41562ce Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 18 Jun 2020 16:46:32 -0700 Subject: tools/bpf: Add verifier tests for 32bit pointer/scalar arithmetic Added two test_verifier subtests for 32bit pointer/scalar arithmetic with BPF_SUB operator. They are passing verifier now. Signed-off-by: Yonghong Song Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20200618234632.3321367-1-yhs@fb.com --- .../selftests/bpf/verifier/value_ptr_arith.c | 38 ++++++++++++++++++++++ 1 file changed, 38 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c index 97ee658e1242..ed4e76b24649 100644 --- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c +++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c @@ -836,3 +836,41 @@ .errstr = "R0 invalid mem access 'inv'", .errstr_unpriv = "R0 pointer -= pointer prohibited", }, +{ + "32bit pkt_ptr -= scalar", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_7), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 40), + BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_8, 2), + BPF_ALU32_REG(BPF_MOV, BPF_REG_4, BPF_REG_7), + BPF_ALU32_REG(BPF_SUB, BPF_REG_6, BPF_REG_4), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "32bit scalar -= pkt_ptr", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_7), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 40), + BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_8, 2), + BPF_ALU32_REG(BPF_MOV, BPF_REG_4, BPF_REG_6), + BPF_ALU32_REG(BPF_SUB, BPF_REG_4, BPF_REG_7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, -- cgit v1.2.3 From 8735e6eaa43899d20a1a54b40e79bfa6b324b107 Mon Sep 17 00:00:00 2001 From: Andrea Mayer Date: Sat, 20 Jun 2020 00:54:47 +0200 Subject: selftests: add selftest for the VRF strict mode The new strict mode functionality is tested in different configurations and on different network namespaces. Signed-off-by: Andrea Mayer Signed-off-by: David S. Miller --- .../testing/selftests/net/vrf_strict_mode_test.sh | 390 +++++++++++++++++++++ 1 file changed, 390 insertions(+) create mode 100755 tools/testing/selftests/net/vrf_strict_mode_test.sh (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/net/vrf_strict_mode_test.sh b/tools/testing/selftests/net/vrf_strict_mode_test.sh new file mode 100755 index 000000000000..5274f4a1fba1 --- /dev/null +++ b/tools/testing/selftests/net/vrf_strict_mode_test.sh @@ -0,0 +1,390 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test is designed for testing the new VRF strict_mode functionality. + +ret=0 + +# identifies the "init" network namespace which is often called root network +# namespace. +INIT_NETNS_NAME="init" + +PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no} + +log_test() +{ + local rc=$1 + local expected=$2 + local msg="$3" + + if [ ${rc} -eq ${expected} ]; then + nsuccess=$((nsuccess+1)) + printf "\n TEST: %-60s [ OK ]\n" "${msg}" + else + ret=1 + nfail=$((nfail+1)) + printf "\n TEST: %-60s [FAIL]\n" "${msg}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi +} + +print_log_test_results() +{ + if [ "$TESTS" != "none" ]; then + printf "\nTests passed: %3d\n" ${nsuccess} + printf "Tests failed: %3d\n" ${nfail} + fi +} + +log_section() +{ + echo + echo "################################################################################" + echo "TEST SECTION: $*" + echo "################################################################################" +} + +ip_expand_args() +{ + local nsname=$1 + local nsarg="" + + if [ "${nsname}" != "${INIT_NETNS_NAME}" ]; then + nsarg="-netns ${nsname}" + fi + + echo "${nsarg}" +} + +vrf_count() +{ + local nsname=$1 + local nsarg="$(ip_expand_args ${nsname})" + + ip ${nsarg} -o link show type vrf | wc -l +} + +count_vrf_by_table_id() +{ + local nsname=$1 + local tableid=$2 + local nsarg="$(ip_expand_args ${nsname})" + + ip ${nsarg} -d -o link show type vrf | grep "table ${tableid}" | wc -l +} + +add_vrf() +{ + local nsname=$1 + local vrfname=$2 + local vrftable=$3 + local nsarg="$(ip_expand_args ${nsname})" + + ip ${nsarg} link add ${vrfname} type vrf table ${vrftable} &>/dev/null +} + +add_vrf_and_check() +{ + local nsname=$1 + local vrfname=$2 + local vrftable=$3 + local cnt + local rc + + add_vrf ${nsname} ${vrfname} ${vrftable}; rc=$? + + cnt=$(count_vrf_by_table_id ${nsname} ${vrftable}) + + log_test ${rc} 0 "${nsname}: add vrf ${vrfname}, ${cnt} vrfs for table ${vrftable}" +} + +add_vrf_and_check_fail() +{ + local nsname=$1 + local vrfname=$2 + local vrftable=$3 + local cnt + local rc + + add_vrf ${nsname} ${vrfname} ${vrftable}; rc=$? + + cnt=$(count_vrf_by_table_id ${nsname} ${vrftable}) + + log_test ${rc} 2 "${nsname}: CANNOT add vrf ${vrfname}, ${cnt} vrfs for table ${vrftable}" +} + +del_vrf_and_check() +{ + local nsname=$1 + local vrfname=$2 + local nsarg="$(ip_expand_args ${nsname})" + + ip ${nsarg} link del ${vrfname} + log_test $? 0 "${nsname}: remove vrf ${vrfname}" +} + +config_vrf_and_check() +{ + local nsname=$1 + local addr=$2 + local vrfname=$3 + local nsarg="$(ip_expand_args ${nsname})" + + ip ${nsarg} link set dev ${vrfname} up && \ + ip ${nsarg} addr add ${addr} dev ${vrfname} + log_test $? 0 "${nsname}: vrf ${vrfname} up, addr ${addr}" +} + +read_strict_mode() +{ + local nsname=$1 + local rval + local rc=0 + local nsexec="" + + if [ "${nsname}" != "${INIT_NETNS_NAME}" ]; then + # a custom network namespace is provided + nsexec="ip netns exec ${nsname}" + fi + + rval="$(${nsexec} bash -c "cat /proc/sys/net/vrf/strict_mode" | \ + grep -E "^[0-1]$")" &> /dev/null + if [ $? -ne 0 ]; then + # set errors + rval=255 + rc=1 + fi + + # on success, rval can be only 0 or 1; on error, rval is equal to 255 + echo ${rval} + return ${rc} +} + +read_strict_mode_compare_and_check() +{ + local nsname=$1 + local expected=$2 + local res + + res="$(read_strict_mode ${nsname})" + log_test ${res} ${expected} "${nsname}: check strict_mode=${res}" +} + +set_strict_mode() +{ + local nsname=$1 + local val=$2 + local nsexec="" + + if [ "${nsname}" != "${INIT_NETNS_NAME}" ]; then + # a custom network namespace is provided + nsexec="ip netns exec ${nsname}" + fi + + ${nsexec} bash -c "echo ${val} >/proc/sys/net/vrf/strict_mode" &>/dev/null +} + +enable_strict_mode() +{ + local nsname=$1 + + set_strict_mode ${nsname} 1 +} + +disable_strict_mode() +{ + local nsname=$1 + + set_strict_mode ${nsname} 0 +} + +disable_strict_mode_and_check() +{ + local nsname=$1 + + disable_strict_mode ${nsname} + log_test $? 0 "${nsname}: disable strict_mode (=0)" +} + +enable_strict_mode_and_check() +{ + local nsname=$1 + + enable_strict_mode ${nsname} + log_test $? 0 "${nsname}: enable strict_mode (=1)" +} + +enable_strict_mode_and_check_fail() +{ + local nsname=$1 + + enable_strict_mode ${nsname} + log_test $? 1 "${nsname}: CANNOT enable strict_mode" +} + +strict_mode_check_default() +{ + local nsname=$1 + local strictmode + local vrfcnt + + vrfcnt=$(vrf_count ${nsname}) + strictmode=$(read_strict_mode ${nsname}) + log_test ${strictmode} 0 "${nsname}: strict_mode=0 by default, ${vrfcnt} vrfs" +} + +setup() +{ + modprobe vrf + + ip netns add testns + ip netns exec testns ip link set lo up +} + +cleanup() +{ + ip netns del testns 2>/dev/null + + ip link del vrf100 2>/dev/null + ip link del vrf101 2>/dev/null + ip link del vrf102 2>/dev/null + + echo 0 >/proc/sys/net/vrf/strict_mode 2>/dev/null +} + +vrf_strict_mode_tests_init() +{ + vrf_strict_mode_check_support init + + strict_mode_check_default init + + add_vrf_and_check init vrf100 100 + config_vrf_and_check init 172.16.100.1/24 vrf100 + + enable_strict_mode_and_check init + + add_vrf_and_check_fail init vrf101 100 + + disable_strict_mode_and_check init + + add_vrf_and_check init vrf101 100 + config_vrf_and_check init 172.16.101.1/24 vrf101 + + enable_strict_mode_and_check_fail init + + del_vrf_and_check init vrf101 + + enable_strict_mode_and_check init + + add_vrf_and_check init vrf102 102 + config_vrf_and_check init 172.16.102.1/24 vrf102 + + # the strict_modle is enabled in the init +} + +vrf_strict_mode_tests_testns() +{ + vrf_strict_mode_check_support testns + + strict_mode_check_default testns + + enable_strict_mode_and_check testns + + add_vrf_and_check testns vrf100 100 + config_vrf_and_check testns 10.0.100.1/24 vrf100 + + add_vrf_and_check_fail testns vrf101 100 + + add_vrf_and_check_fail testns vrf102 100 + + add_vrf_and_check testns vrf200 200 + + disable_strict_mode_and_check testns + + add_vrf_and_check testns vrf101 100 + + add_vrf_and_check testns vrf102 100 + + #the strict_mode is disabled in the testns +} + +vrf_strict_mode_tests_mix() +{ + read_strict_mode_compare_and_check init 1 + + read_strict_mode_compare_and_check testns 0 + + del_vrf_and_check testns vrf101 + + del_vrf_and_check testns vrf102 + + disable_strict_mode_and_check init + + enable_strict_mode_and_check testns + + enable_strict_mode_and_check init + enable_strict_mode_and_check init + + disable_strict_mode_and_check testns + disable_strict_mode_and_check testns + + read_strict_mode_compare_and_check init 1 + + read_strict_mode_compare_and_check testns 0 +} + +vrf_strict_mode_tests() +{ + log_section "VRF strict_mode test on init network namespace" + vrf_strict_mode_tests_init + + log_section "VRF strict_mode test on testns network namespace" + vrf_strict_mode_tests_testns + + log_section "VRF strict_mode test mixing init and testns network namespaces" + vrf_strict_mode_tests_mix +} + +vrf_strict_mode_check_support() +{ + local nsname=$1 + local output + local rc + + output="$(lsmod | grep '^vrf' | awk '{print $1}')" + if [ -z "${output}" ]; then + modinfo vrf || return $? + fi + + # we do not care about the value of the strict_mode; we only check if + # the strict_mode parameter is available or not. + read_strict_mode ${nsname} &>/dev/null; rc=$? + log_test ${rc} 0 "${nsname}: net.vrf.strict_mode is available" + + return ${rc} +} + +if [ "$(id -u)" -ne 0 ];then + echo "SKIP: Need root privileges" + exit 0 +fi + +if [ ! -x "$(command -v ip)" ]; then + echo "SKIP: Could not run test without ip tool" + exit 0 +fi + +cleanup &> /dev/null + +setup +vrf_strict_mode_tests +cleanup + +print_log_test_results + +exit $ret -- cgit v1.2.3 From 41c48f3a98231738c5ce79f6f2aa6e40ba924d18 Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Fri, 19 Jun 2020 14:11:43 -0700 Subject: bpf: Support access to bpf map fields There are multiple use-cases when it's convenient to have access to bpf map fields, both `struct bpf_map` and map type specific struct-s such as `struct bpf_array`, `struct bpf_htab`, etc. For example while working with sock arrays it can be necessary to calculate the key based on map->max_entries (some_hash % max_entries). Currently this is solved by communicating max_entries via "out-of-band" channel, e.g. via additional map with known key to get info about target map. That works, but is not very convenient and error-prone while working with many maps. In other cases necessary data is dynamic (i.e. unknown at loading time) and it's impossible to get it at all. For example while working with a hash table it can be convenient to know how much capacity is already used (bpf_htab.count.counter for BPF_F_NO_PREALLOC case). At the same time kernel knows this info and can provide it to bpf program. Fill this gap by adding support to access bpf map fields from bpf program for both `struct bpf_map` and map type specific fields. Support is implemented via btf_struct_access() so that a user can define their own `struct bpf_map` or map type specific struct in their program with only necessary fields and preserve_access_index attribute, cast a map to this struct and use a field. For example: struct bpf_map { __u32 max_entries; } __attribute__((preserve_access_index)); struct bpf_array { struct bpf_map map; __u32 elem_size; } __attribute__((preserve_access_index)); struct { __uint(type, BPF_MAP_TYPE_ARRAY); __uint(max_entries, 4); __type(key, __u32); __type(value, __u32); } m_array SEC(".maps"); SEC("cgroup_skb/egress") int cg_skb(void *ctx) { struct bpf_array *array = (struct bpf_array *)&m_array; struct bpf_map *map = (struct bpf_map *)&m_array; /* .. use map->max_entries or array->map.max_entries .. */ } Similarly to other btf_struct_access() use-cases (e.g. struct tcp_sock in net/ipv4/bpf_tcp_ca.c) the patch allows access to any fields of corresponding struct. Only reading from map fields is supported. For btf_struct_access() to work there should be a way to know btf id of a struct that corresponds to a map type. To get btf id there should be a way to get a stringified name of map-specific struct, such as "bpf_array", "bpf_htab", etc for a map type. Two new fields are added to `struct bpf_map_ops` to handle it: * .map_btf_name keeps a btf name of a struct returned by map_alloc(); * .map_btf_id is used to cache btf id of that struct. To make btf ids calculation cheaper they're calculated once while preparing btf_vmlinux and cached same way as it's done for btf_id field of `struct bpf_func_proto` While calculating btf ids, struct names are NOT checked for collision. Collisions will be checked as a part of the work to prepare btf ids used in verifier in compile time that should land soon. The only known collision for `struct bpf_htab` (kernel/bpf/hashtab.c vs net/core/sock_map.c) was fixed earlier. Both new fields .map_btf_name and .map_btf_id must be set for a map type for the feature to work. If neither is set for a map type, verifier will return ENOTSUPP on a try to access map_ptr of corresponding type. If just one of them set, it's verifier misconfiguration. Only `struct bpf_array` for BPF_MAP_TYPE_ARRAY and `struct bpf_htab` for BPF_MAP_TYPE_HASH are supported by this patch. Other map types will be supported separately. The feature is available only for CONFIG_DEBUG_INFO_BTF=y and gated by perfmon_capable() so that unpriv programs won't have access to bpf map fields. Signed-off-by: Andrey Ignatov Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/6479686a0cd1e9067993df57b4c3eef0e276fec9.1592600985.git.rdna@fb.com --- include/linux/bpf.h | 9 +++ include/linux/bpf_verifier.h | 1 + kernel/bpf/arraymap.c | 3 + kernel/bpf/btf.c | 40 +++++++++++ kernel/bpf/hashtab.c | 3 + kernel/bpf/verifier.c | 82 +++++++++++++++++++--- .../selftests/bpf/verifier/map_ptr_mixing.c | 2 +- 7 files changed, 131 insertions(+), 9 deletions(-) (limited to 'tools/testing/selftests') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 07052d44bca1..1e1501ee53ce 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -92,6 +92,10 @@ struct bpf_map_ops { int (*map_mmap)(struct bpf_map *map, struct vm_area_struct *vma); __poll_t (*map_poll)(struct bpf_map *map, struct file *filp, struct poll_table_struct *pts); + + /* BTF name and id of struct allocated by map_alloc */ + const char * const map_btf_name; + int *map_btf_id; }; struct bpf_map_memory { @@ -1109,6 +1113,11 @@ static inline bool bpf_allow_ptr_leaks(void) return perfmon_capable(); } +static inline bool bpf_allow_ptr_to_map_access(void) +{ + return perfmon_capable(); +} + static inline bool bpf_bypass_spec_v1(void) { return perfmon_capable(); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index ca08db4ffb5f..53c7bd568c5d 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -379,6 +379,7 @@ struct bpf_verifier_env { u32 used_map_cnt; /* number of used maps */ u32 id_gen; /* used to generate unique reg IDs */ bool allow_ptr_leaks; + bool allow_ptr_to_map_access; bool bpf_capable; bool bypass_spec_v1; bool bypass_spec_v4; diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 11584618e861..e7caa48812fb 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -494,6 +494,7 @@ static int array_map_mmap(struct bpf_map *map, struct vm_area_struct *vma) vma->vm_pgoff + pgoff); } +static int array_map_btf_id; const struct bpf_map_ops array_map_ops = { .map_alloc_check = array_map_alloc_check, .map_alloc = array_map_alloc, @@ -510,6 +511,8 @@ const struct bpf_map_ops array_map_ops = { .map_check_btf = array_map_check_btf, .map_lookup_batch = generic_map_lookup_batch, .map_update_batch = generic_map_update_batch, + .map_btf_name = "bpf_array", + .map_btf_id = &array_map_btf_id, }; const struct bpf_map_ops percpu_array_map_ops = { diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 3eb804618a53..e377d1981730 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3571,6 +3571,41 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, struct btf *btf, return ctx_type; } +static const struct bpf_map_ops * const btf_vmlinux_map_ops[] = { +#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) +#define BPF_LINK_TYPE(_id, _name) +#define BPF_MAP_TYPE(_id, _ops) \ + [_id] = &_ops, +#include +#undef BPF_PROG_TYPE +#undef BPF_LINK_TYPE +#undef BPF_MAP_TYPE +}; + +static int btf_vmlinux_map_ids_init(const struct btf *btf, + struct bpf_verifier_log *log) +{ + const struct bpf_map_ops *ops; + int i, btf_id; + + for (i = 0; i < ARRAY_SIZE(btf_vmlinux_map_ops); ++i) { + ops = btf_vmlinux_map_ops[i]; + if (!ops || (!ops->map_btf_name && !ops->map_btf_id)) + continue; + if (!ops->map_btf_name || !ops->map_btf_id) { + bpf_log(log, "map type %d is misconfigured\n", i); + return -EINVAL; + } + btf_id = btf_find_by_name_kind(btf, ops->map_btf_name, + BTF_KIND_STRUCT); + if (btf_id < 0) + return btf_id; + *ops->map_btf_id = btf_id; + } + + return 0; +} + static int btf_translate_to_vmlinux(struct bpf_verifier_log *log, struct btf *btf, const struct btf_type *t, @@ -3633,6 +3668,11 @@ struct btf *btf_parse_vmlinux(void) /* btf_parse_vmlinux() runs under bpf_verifier_lock */ bpf_ctx_convert.t = btf_type_by_id(btf, btf_id); + /* find bpf map structs for map_ptr access checking */ + err = btf_vmlinux_map_ids_init(btf, log); + if (err < 0) + goto errout; + bpf_struct_ops_init(btf, log); btf_verifier_env_free(env); diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index b4b288a3c3c9..2c5999e02060 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -1614,6 +1614,7 @@ htab_lru_map_lookup_and_delete_batch(struct bpf_map *map, true, false); } +static int htab_map_btf_id; const struct bpf_map_ops htab_map_ops = { .map_alloc_check = htab_map_alloc_check, .map_alloc = htab_map_alloc, @@ -1625,6 +1626,8 @@ const struct bpf_map_ops htab_map_ops = { .map_gen_lookup = htab_map_gen_lookup, .map_seq_show_elem = htab_map_seq_show_elem, BATCH_OPS(htab), + .map_btf_name = "bpf_htab", + .map_btf_id = &htab_map_btf_id, }; const struct bpf_map_ops htab_lru_map_ops = { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index a1857c4ffaaf..7460f967cb75 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1351,6 +1351,19 @@ static void mark_reg_not_init(struct bpf_verifier_env *env, __mark_reg_not_init(env, regs + regno); } +static void mark_btf_ld_reg(struct bpf_verifier_env *env, + struct bpf_reg_state *regs, u32 regno, + enum bpf_reg_type reg_type, u32 btf_id) +{ + if (reg_type == SCALAR_VALUE) { + mark_reg_unknown(env, regs, regno); + return; + } + mark_reg_known_zero(env, regs, regno); + regs[regno].type = PTR_TO_BTF_ID; + regs[regno].btf_id = btf_id; +} + #define DEF_NOT_SUBREG (0) static void init_reg_state(struct bpf_verifier_env *env, struct bpf_func_state *state) @@ -3182,19 +3195,68 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, if (ret < 0) return ret; - if (atype == BPF_READ && value_regno >= 0) { - if (ret == SCALAR_VALUE) { - mark_reg_unknown(env, regs, value_regno); - return 0; - } - mark_reg_known_zero(env, regs, value_regno); - regs[value_regno].type = PTR_TO_BTF_ID; - regs[value_regno].btf_id = btf_id; + if (atype == BPF_READ && value_regno >= 0) + mark_btf_ld_reg(env, regs, value_regno, ret, btf_id); + + return 0; +} + +static int check_ptr_to_map_access(struct bpf_verifier_env *env, + struct bpf_reg_state *regs, + int regno, int off, int size, + enum bpf_access_type atype, + int value_regno) +{ + struct bpf_reg_state *reg = regs + regno; + struct bpf_map *map = reg->map_ptr; + const struct btf_type *t; + const char *tname; + u32 btf_id; + int ret; + + if (!btf_vmlinux) { + verbose(env, "map_ptr access not supported without CONFIG_DEBUG_INFO_BTF\n"); + return -ENOTSUPP; + } + + if (!map->ops->map_btf_id || !*map->ops->map_btf_id) { + verbose(env, "map_ptr access not supported for map type %d\n", + map->map_type); + return -ENOTSUPP; + } + + t = btf_type_by_id(btf_vmlinux, *map->ops->map_btf_id); + tname = btf_name_by_offset(btf_vmlinux, t->name_off); + + if (!env->allow_ptr_to_map_access) { + verbose(env, + "%s access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN\n", + tname); + return -EPERM; } + if (off < 0) { + verbose(env, "R%d is %s invalid negative access: off=%d\n", + regno, tname, off); + return -EACCES; + } + + if (atype != BPF_READ) { + verbose(env, "only read from %s is supported\n", tname); + return -EACCES; + } + + ret = btf_struct_access(&env->log, t, off, size, atype, &btf_id); + if (ret < 0) + return ret; + + if (value_regno >= 0) + mark_btf_ld_reg(env, regs, value_regno, ret, btf_id); + return 0; } + /* check whether memory at (regno + off) is accessible for t = (read | write) * if t==write, value_regno is a register which value is stored into memory * if t==read, value_regno is a register which will receive the value from memory @@ -3363,6 +3425,9 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn } else if (reg->type == PTR_TO_BTF_ID) { err = check_ptr_to_btf_access(env, regs, regno, off, size, t, value_regno); + } else if (reg->type == CONST_PTR_TO_MAP) { + err = check_ptr_to_map_access(env, regs, regno, off, size, t, + value_regno); } else { verbose(env, "R%d invalid mem access '%s'\n", regno, reg_type_str[reg->type]); @@ -10951,6 +11016,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, env->strict_alignment = false; env->allow_ptr_leaks = bpf_allow_ptr_leaks(); + env->allow_ptr_to_map_access = bpf_allow_ptr_to_map_access(); env->bypass_spec_v1 = bpf_bypass_spec_v1(); env->bypass_spec_v4 = bpf_bypass_spec_v4(); env->bpf_capable = bpf_capable(); diff --git a/tools/testing/selftests/bpf/verifier/map_ptr_mixing.c b/tools/testing/selftests/bpf/verifier/map_ptr_mixing.c index cd26ee6b7b1d..1f2b8c4cb26d 100644 --- a/tools/testing/selftests/bpf/verifier/map_ptr_mixing.c +++ b/tools/testing/selftests/bpf/verifier/map_ptr_mixing.c @@ -56,7 +56,7 @@ .fixup_map_in_map = { 16 }, .fixup_map_array_48b = { 13 }, .result = REJECT, - .errstr = "R0 invalid mem access 'map_ptr'", + .errstr = "only read from bpf_array is supported", }, { "cond: two branches returning different map pointers for lookup (tail, tail)", -- cgit v1.2.3 From b1b53d413f16c6b5078edb127e660e67332e4d2f Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Fri, 19 Jun 2020 14:11:45 -0700 Subject: selftests/bpf: Test access to bpf map pointer Add selftests to test access to map pointers from bpf program for all map types except struct_ops (that one would need additional work). verifier test focuses mostly on scenarios that must be rejected. prog_tests test focuses on accessing multiple fields both scalar and a nested struct from bpf program and verifies that those fields have expected values. Signed-off-by: Andrey Ignatov Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/139a6a17f8016491e39347849b951525335c6eb4.1592600985.git.rdna@fb.com --- tools/testing/selftests/bpf/prog_tests/map_ptr.c | 32 ++ tools/testing/selftests/bpf/progs/map_ptr_kern.c | 686 +++++++++++++++++++++++ tools/testing/selftests/bpf/verifier/map_ptr.c | 62 ++ 3 files changed, 780 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/map_ptr.c create mode 100644 tools/testing/selftests/bpf/progs/map_ptr_kern.c create mode 100644 tools/testing/selftests/bpf/verifier/map_ptr.c (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/map_ptr.c b/tools/testing/selftests/bpf/prog_tests/map_ptr.c new file mode 100644 index 000000000000..c230a573c373 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/map_ptr.c @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include +#include + +#include "map_ptr_kern.skel.h" + +void test_map_ptr(void) +{ + struct map_ptr_kern *skel; + __u32 duration = 0, retval; + char buf[128]; + int err; + + skel = map_ptr_kern__open_and_load(); + if (CHECK(!skel, "skel_open_load", "open_load failed\n")) + return; + + err = bpf_prog_test_run(bpf_program__fd(skel->progs.cg_skb), 1, &pkt_v4, + sizeof(pkt_v4), buf, NULL, &retval, NULL); + + if (CHECK(err, "test_run", "err=%d errno=%d\n", err, errno)) + goto cleanup; + + if (CHECK(!retval, "retval", "retval=%d map_type=%u line=%u\n", retval, + skel->bss->g_map_type, skel->bss->g_line)) + goto cleanup; + +cleanup: + map_ptr_kern__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/progs/map_ptr_kern.c b/tools/testing/selftests/bpf/progs/map_ptr_kern.c new file mode 100644 index 000000000000..473665cac67e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/map_ptr_kern.c @@ -0,0 +1,686 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include +#include + +#define LOOP_BOUND 0xf +#define MAX_ENTRIES 8 +#define HALF_ENTRIES (MAX_ENTRIES >> 1) + +_Static_assert(MAX_ENTRIES < LOOP_BOUND, "MAX_ENTRIES must be < LOOP_BOUND"); + +enum bpf_map_type g_map_type = BPF_MAP_TYPE_UNSPEC; +__u32 g_line = 0; + +#define VERIFY_TYPE(type, func) ({ \ + g_map_type = type; \ + if (!func()) \ + return 0; \ +}) + + +#define VERIFY(expr) ({ \ + g_line = __LINE__; \ + if (!(expr)) \ + return 0; \ +}) + +struct bpf_map_memory { + __u32 pages; +} __attribute__((preserve_access_index)); + +struct bpf_map { + enum bpf_map_type map_type; + __u32 key_size; + __u32 value_size; + __u32 max_entries; + __u32 id; + struct bpf_map_memory memory; +} __attribute__((preserve_access_index)); + +static inline int check_bpf_map_fields(struct bpf_map *map, __u32 key_size, + __u32 value_size, __u32 max_entries) +{ + VERIFY(map->map_type == g_map_type); + VERIFY(map->key_size == key_size); + VERIFY(map->value_size == value_size); + VERIFY(map->max_entries == max_entries); + VERIFY(map->id > 0); + VERIFY(map->memory.pages > 0); + + return 1; +} + +static inline int check_bpf_map_ptr(struct bpf_map *indirect, + struct bpf_map *direct) +{ + VERIFY(indirect->map_type == direct->map_type); + VERIFY(indirect->key_size == direct->key_size); + VERIFY(indirect->value_size == direct->value_size); + VERIFY(indirect->max_entries == direct->max_entries); + VERIFY(indirect->id == direct->id); + VERIFY(indirect->memory.pages == direct->memory.pages); + + return 1; +} + +static inline int check(struct bpf_map *indirect, struct bpf_map *direct, + __u32 key_size, __u32 value_size, __u32 max_entries) +{ + VERIFY(check_bpf_map_ptr(indirect, direct)); + VERIFY(check_bpf_map_fields(indirect, key_size, value_size, + max_entries)); + return 1; +} + +static inline int check_default(struct bpf_map *indirect, + struct bpf_map *direct) +{ + VERIFY(check(indirect, direct, sizeof(__u32), sizeof(__u32), + MAX_ENTRIES)); + return 1; +} + +typedef struct { + int counter; +} atomic_t; + +struct bpf_htab { + struct bpf_map map; + atomic_t count; + __u32 n_buckets; + __u32 elem_size; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(map_flags, BPF_F_NO_PREALLOC); /* to test bpf_htab.count */ + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_hash SEC(".maps"); + +static inline int check_hash(void) +{ + struct bpf_htab *hash = (struct bpf_htab *)&m_hash; + struct bpf_map *map = (struct bpf_map *)&m_hash; + int i; + + VERIFY(check_default(&hash->map, map)); + + VERIFY(hash->n_buckets == MAX_ENTRIES); + VERIFY(hash->elem_size == 64); + + VERIFY(hash->count.counter == 0); + for (i = 0; i < HALF_ENTRIES; ++i) { + const __u32 key = i; + const __u32 val = 1; + + if (bpf_map_update_elem(hash, &key, &val, 0)) + return 0; + } + VERIFY(hash->count.counter == HALF_ENTRIES); + + return 1; +} + +struct bpf_array { + struct bpf_map map; + __u32 elem_size; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_array SEC(".maps"); + +static inline int check_array(void) +{ + struct bpf_array *array = (struct bpf_array *)&m_array; + struct bpf_map *map = (struct bpf_map *)&m_array; + int i, n_lookups = 0, n_keys = 0; + + VERIFY(check_default(&array->map, map)); + + VERIFY(array->elem_size == 8); + + for (i = 0; i < array->map.max_entries && i < LOOP_BOUND; ++i) { + const __u32 key = i; + __u32 *val = bpf_map_lookup_elem(array, &key); + + ++n_lookups; + if (val) + ++n_keys; + } + + VERIFY(n_lookups == MAX_ENTRIES); + VERIFY(n_keys == MAX_ENTRIES); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_prog_array SEC(".maps"); + +static inline int check_prog_array(void) +{ + struct bpf_array *prog_array = (struct bpf_array *)&m_prog_array; + struct bpf_map *map = (struct bpf_map *)&m_prog_array; + + VERIFY(check_default(&prog_array->map, map)); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_perf_event_array SEC(".maps"); + +static inline int check_perf_event_array(void) +{ + struct bpf_array *perf_event_array = (struct bpf_array *)&m_perf_event_array; + struct bpf_map *map = (struct bpf_map *)&m_perf_event_array; + + VERIFY(check_default(&perf_event_array->map, map)); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_percpu_hash SEC(".maps"); + +static inline int check_percpu_hash(void) +{ + struct bpf_htab *percpu_hash = (struct bpf_htab *)&m_percpu_hash; + struct bpf_map *map = (struct bpf_map *)&m_percpu_hash; + + VERIFY(check_default(&percpu_hash->map, map)); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_percpu_array SEC(".maps"); + +static inline int check_percpu_array(void) +{ + struct bpf_array *percpu_array = (struct bpf_array *)&m_percpu_array; + struct bpf_map *map = (struct bpf_map *)&m_percpu_array; + + VERIFY(check_default(&percpu_array->map, map)); + + return 1; +} + +struct bpf_stack_map { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_STACK_TRACE); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u64); +} m_stack_trace SEC(".maps"); + +static inline int check_stack_trace(void) +{ + struct bpf_stack_map *stack_trace = + (struct bpf_stack_map *)&m_stack_trace; + struct bpf_map *map = (struct bpf_map *)&m_stack_trace; + + VERIFY(check(&stack_trace->map, map, sizeof(__u32), sizeof(__u64), + MAX_ENTRIES)); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_CGROUP_ARRAY); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_cgroup_array SEC(".maps"); + +static inline int check_cgroup_array(void) +{ + struct bpf_array *cgroup_array = (struct bpf_array *)&m_cgroup_array; + struct bpf_map *map = (struct bpf_map *)&m_cgroup_array; + + VERIFY(check_default(&cgroup_array->map, map)); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_LRU_HASH); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_lru_hash SEC(".maps"); + +static inline int check_lru_hash(void) +{ + struct bpf_htab *lru_hash = (struct bpf_htab *)&m_lru_hash; + struct bpf_map *map = (struct bpf_map *)&m_lru_hash; + + VERIFY(check_default(&lru_hash->map, map)); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_LRU_PERCPU_HASH); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_lru_percpu_hash SEC(".maps"); + +static inline int check_lru_percpu_hash(void) +{ + struct bpf_htab *lru_percpu_hash = (struct bpf_htab *)&m_lru_percpu_hash; + struct bpf_map *map = (struct bpf_map *)&m_lru_percpu_hash; + + VERIFY(check_default(&lru_percpu_hash->map, map)); + + return 1; +} + +struct lpm_trie { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct lpm_key { + struct bpf_lpm_trie_key trie_key; + __u32 data; +}; + +struct { + __uint(type, BPF_MAP_TYPE_LPM_TRIE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __uint(max_entries, MAX_ENTRIES); + __type(key, struct lpm_key); + __type(value, __u32); +} m_lpm_trie SEC(".maps"); + +static inline int check_lpm_trie(void) +{ + struct lpm_trie *lpm_trie = (struct lpm_trie *)&m_lpm_trie; + struct bpf_map *map = (struct bpf_map *)&m_lpm_trie; + + VERIFY(check(&lpm_trie->map, map, sizeof(struct lpm_key), sizeof(__u32), + MAX_ENTRIES)); + + return 1; +} + +struct inner_map { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u32); +} inner_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); + __array(values, struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u32); + }); +} m_array_of_maps SEC(".maps") = { + .values = { (void *)&inner_map, 0, 0, 0, 0, 0, 0, 0, 0 }, +}; + +static inline int check_array_of_maps(void) +{ + struct bpf_array *array_of_maps = (struct bpf_array *)&m_array_of_maps; + struct bpf_map *map = (struct bpf_map *)&m_array_of_maps; + + VERIFY(check_default(&array_of_maps->map, map)); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_HASH_OF_MAPS); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); + __array(values, struct inner_map); +} m_hash_of_maps SEC(".maps") = { + .values = { + [2] = &inner_map, + }, +}; + +static inline int check_hash_of_maps(void) +{ + struct bpf_htab *hash_of_maps = (struct bpf_htab *)&m_hash_of_maps; + struct bpf_map *map = (struct bpf_map *)&m_hash_of_maps; + + VERIFY(check_default(&hash_of_maps->map, map)); + + return 1; +} + +struct bpf_dtab { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_DEVMAP); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_devmap SEC(".maps"); + +static inline int check_devmap(void) +{ + struct bpf_dtab *devmap = (struct bpf_dtab *)&m_devmap; + struct bpf_map *map = (struct bpf_map *)&m_devmap; + + VERIFY(check_default(&devmap->map, map)); + + return 1; +} + +struct bpf_stab { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_sockmap SEC(".maps"); + +static inline int check_sockmap(void) +{ + struct bpf_stab *sockmap = (struct bpf_stab *)&m_sockmap; + struct bpf_map *map = (struct bpf_map *)&m_sockmap; + + VERIFY(check_default(&sockmap->map, map)); + + return 1; +} + +struct bpf_cpu_map { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_CPUMAP); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_cpumap SEC(".maps"); + +static inline int check_cpumap(void) +{ + struct bpf_cpu_map *cpumap = (struct bpf_cpu_map *)&m_cpumap; + struct bpf_map *map = (struct bpf_map *)&m_cpumap; + + VERIFY(check_default(&cpumap->map, map)); + + return 1; +} + +struct xsk_map { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_XSKMAP); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_xskmap SEC(".maps"); + +static inline int check_xskmap(void) +{ + struct xsk_map *xskmap = (struct xsk_map *)&m_xskmap; + struct bpf_map *map = (struct bpf_map *)&m_xskmap; + + VERIFY(check_default(&xskmap->map, map)); + + return 1; +} + +struct bpf_shtab { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKHASH); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_sockhash SEC(".maps"); + +static inline int check_sockhash(void) +{ + struct bpf_shtab *sockhash = (struct bpf_shtab *)&m_sockhash; + struct bpf_map *map = (struct bpf_map *)&m_sockhash; + + VERIFY(check_default(&sockhash->map, map)); + + return 1; +} + +struct bpf_cgroup_storage_map { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_CGROUP_STORAGE); + __type(key, struct bpf_cgroup_storage_key); + __type(value, __u32); +} m_cgroup_storage SEC(".maps"); + +static inline int check_cgroup_storage(void) +{ + struct bpf_cgroup_storage_map *cgroup_storage = + (struct bpf_cgroup_storage_map *)&m_cgroup_storage; + struct bpf_map *map = (struct bpf_map *)&m_cgroup_storage; + + VERIFY(check(&cgroup_storage->map, map, + sizeof(struct bpf_cgroup_storage_key), sizeof(__u32), 0)); + + return 1; +} + +struct reuseport_array { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_reuseport_sockarray SEC(".maps"); + +static inline int check_reuseport_sockarray(void) +{ + struct reuseport_array *reuseport_sockarray = + (struct reuseport_array *)&m_reuseport_sockarray; + struct bpf_map *map = (struct bpf_map *)&m_reuseport_sockarray; + + VERIFY(check_default(&reuseport_sockarray->map, map)); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE); + __type(key, struct bpf_cgroup_storage_key); + __type(value, __u32); +} m_percpu_cgroup_storage SEC(".maps"); + +static inline int check_percpu_cgroup_storage(void) +{ + struct bpf_cgroup_storage_map *percpu_cgroup_storage = + (struct bpf_cgroup_storage_map *)&m_percpu_cgroup_storage; + struct bpf_map *map = (struct bpf_map *)&m_percpu_cgroup_storage; + + VERIFY(check(&percpu_cgroup_storage->map, map, + sizeof(struct bpf_cgroup_storage_key), sizeof(__u32), 0)); + + return 1; +} + +struct bpf_queue_stack { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_QUEUE); + __uint(max_entries, MAX_ENTRIES); + __type(value, __u32); +} m_queue SEC(".maps"); + +static inline int check_queue(void) +{ + struct bpf_queue_stack *queue = (struct bpf_queue_stack *)&m_queue; + struct bpf_map *map = (struct bpf_map *)&m_queue; + + VERIFY(check(&queue->map, map, 0, sizeof(__u32), MAX_ENTRIES)); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_STACK); + __uint(max_entries, MAX_ENTRIES); + __type(value, __u32); +} m_stack SEC(".maps"); + +static inline int check_stack(void) +{ + struct bpf_queue_stack *stack = (struct bpf_queue_stack *)&m_stack; + struct bpf_map *map = (struct bpf_map *)&m_stack; + + VERIFY(check(&stack->map, map, 0, sizeof(__u32), MAX_ENTRIES)); + + return 1; +} + +struct bpf_sk_storage_map { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, __u32); + __type(value, __u32); +} m_sk_storage SEC(".maps"); + +static inline int check_sk_storage(void) +{ + struct bpf_sk_storage_map *sk_storage = + (struct bpf_sk_storage_map *)&m_sk_storage; + struct bpf_map *map = (struct bpf_map *)&m_sk_storage; + + VERIFY(check(&sk_storage->map, map, sizeof(__u32), sizeof(__u32), 0)); + + return 1; +} + +struct { + __uint(type, BPF_MAP_TYPE_DEVMAP_HASH); + __uint(max_entries, MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} m_devmap_hash SEC(".maps"); + +static inline int check_devmap_hash(void) +{ + struct bpf_dtab *devmap_hash = (struct bpf_dtab *)&m_devmap_hash; + struct bpf_map *map = (struct bpf_map *)&m_devmap_hash; + + VERIFY(check_default(&devmap_hash->map, map)); + + return 1; +} + +struct bpf_ringbuf_map { + struct bpf_map map; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_RINGBUF); + __uint(max_entries, 1 << 12); +} m_ringbuf SEC(".maps"); + +static inline int check_ringbuf(void) +{ + struct bpf_ringbuf_map *ringbuf = (struct bpf_ringbuf_map *)&m_ringbuf; + struct bpf_map *map = (struct bpf_map *)&m_ringbuf; + + VERIFY(check(&ringbuf->map, map, 0, 0, 1 << 12)); + + return 1; +} + +SEC("cgroup_skb/egress") +int cg_skb(void *ctx) +{ + VERIFY_TYPE(BPF_MAP_TYPE_HASH, check_hash); + VERIFY_TYPE(BPF_MAP_TYPE_ARRAY, check_array); + VERIFY_TYPE(BPF_MAP_TYPE_PROG_ARRAY, check_prog_array); + VERIFY_TYPE(BPF_MAP_TYPE_PERF_EVENT_ARRAY, check_perf_event_array); + VERIFY_TYPE(BPF_MAP_TYPE_PERCPU_HASH, check_percpu_hash); + VERIFY_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, check_percpu_array); + VERIFY_TYPE(BPF_MAP_TYPE_STACK_TRACE, check_stack_trace); + VERIFY_TYPE(BPF_MAP_TYPE_CGROUP_ARRAY, check_cgroup_array); + VERIFY_TYPE(BPF_MAP_TYPE_LRU_HASH, check_lru_hash); + VERIFY_TYPE(BPF_MAP_TYPE_LRU_PERCPU_HASH, check_lru_percpu_hash); + VERIFY_TYPE(BPF_MAP_TYPE_LPM_TRIE, check_lpm_trie); + VERIFY_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, check_array_of_maps); + VERIFY_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, check_hash_of_maps); + VERIFY_TYPE(BPF_MAP_TYPE_DEVMAP, check_devmap); + VERIFY_TYPE(BPF_MAP_TYPE_SOCKMAP, check_sockmap); + VERIFY_TYPE(BPF_MAP_TYPE_CPUMAP, check_cpumap); + VERIFY_TYPE(BPF_MAP_TYPE_XSKMAP, check_xskmap); + VERIFY_TYPE(BPF_MAP_TYPE_SOCKHASH, check_sockhash); + VERIFY_TYPE(BPF_MAP_TYPE_CGROUP_STORAGE, check_cgroup_storage); + VERIFY_TYPE(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, + check_reuseport_sockarray); + VERIFY_TYPE(BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, + check_percpu_cgroup_storage); + VERIFY_TYPE(BPF_MAP_TYPE_QUEUE, check_queue); + VERIFY_TYPE(BPF_MAP_TYPE_STACK, check_stack); + VERIFY_TYPE(BPF_MAP_TYPE_SK_STORAGE, check_sk_storage); + VERIFY_TYPE(BPF_MAP_TYPE_DEVMAP_HASH, check_devmap_hash); + VERIFY_TYPE(BPF_MAP_TYPE_RINGBUF, check_ringbuf); + + return 1; +} + +__u32 _version SEC("version") = 1; +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/verifier/map_ptr.c b/tools/testing/selftests/bpf/verifier/map_ptr.c new file mode 100644 index 000000000000..b52209db8250 --- /dev/null +++ b/tools/testing/selftests/bpf/verifier/map_ptr.c @@ -0,0 +1,62 @@ +{ + "bpf_map_ptr: read with negative offset rejected", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1 }, + .result_unpriv = REJECT, + .errstr_unpriv = "bpf_array access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN", + .result = REJECT, + .errstr = "R1 is bpf_array invalid negative access: off=-8", +}, +{ + "bpf_map_ptr: write rejected", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 3 }, + .result_unpriv = REJECT, + .errstr_unpriv = "bpf_array access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN", + .result = REJECT, + .errstr = "only read from bpf_array is supported", +}, +{ + "bpf_map_ptr: read non-existent field rejected", + .insns = { + BPF_MOV64_IMM(BPF_REG_6, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, 1), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1 }, + .result_unpriv = REJECT, + .errstr_unpriv = "bpf_array access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN", + .result = REJECT, + .errstr = "cannot access ptr member ops with moff 0 in struct bpf_map with off 1 size 4", +}, +{ + "bpf_map_ptr: read ops field accepted", + .insns = { + BPF_MOV64_IMM(BPF_REG_6, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1 }, + .result_unpriv = REJECT, + .errstr_unpriv = "bpf_array access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN", + .result = ACCEPT, + .retval = 1, +}, -- cgit v1.2.3 From 13bd5d025602bb5374f54e144dec577b74718493 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Sun, 21 Jun 2020 11:34:36 +0300 Subject: selftests: forwarding: Add a test for pedit munge tcp, udp sport, dport Add a test that checks that pedit adjusts port numbers of tcp and udp packets. Signed-off-by: Petr Machata Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- .../selftests/net/forwarding/pedit_l4port.sh | 198 +++++++++++++++++++++ 1 file changed, 198 insertions(+) create mode 100755 tools/testing/selftests/net/forwarding/pedit_l4port.sh (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/net/forwarding/pedit_l4port.sh b/tools/testing/selftests/net/forwarding/pedit_l4port.sh new file mode 100755 index 000000000000..5f20d289ee43 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/pedit_l4port.sh @@ -0,0 +1,198 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test sends traffic from H1 to H2. Either on ingress of $swp1, or on egress of $swp2, the +# traffic is acted upon by a pedit action. An ingress filter installed on $h2 verifies that the +# packet looks like expected. +# +# +----------------------+ +----------------------+ +# | H1 | | H2 | +# | + $h1 | | $h2 + | +# | | 192.0.2.1/28 | | 192.0.2.2/28 | | +# +----|-----------------+ +----------------|-----+ +# | | +# +----|----------------------------------------------------------------|-----+ +# | SW | | | +# | +-|----------------------------------------------------------------|-+ | +# | | + $swp1 BR $swp2 + | | +# | +--------------------------------------------------------------------+ | +# +---------------------------------------------------------------------------+ + +ALL_TESTS=" + ping_ipv4 + test_udp_sport + test_udp_dport + test_tcp_sport + test_tcp_dport +" + +NUM_NETIFS=4 +source lib.sh +source tc_common.sh + +: ${HIT_TIMEOUT:=2000} # ms + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/28 2001:db8:1::1/64 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.2/28 2001:db8:1::2/64 + tc qdisc add dev $h2 clsact +} + +h2_destroy() +{ + tc qdisc del dev $h2 clsact + simple_if_fini $h2 192.0.2.2/28 2001:db8:1::2/64 +} + +switch_create() +{ + ip link add name br1 up type bridge vlan_filtering 1 + ip link set dev $swp1 master br1 + ip link set dev $swp1 up + ip link set dev $swp2 master br1 + ip link set dev $swp2 up + + tc qdisc add dev $swp1 clsact + tc qdisc add dev $swp2 clsact +} + +switch_destroy() +{ + tc qdisc del dev $swp2 clsact + tc qdisc del dev $swp1 clsact + + ip link set dev $swp2 nomaster + ip link set dev $swp1 nomaster + ip link del dev br1 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + h2mac=$(mac_get $h2) + + vrf_prepare + h1_create + h2_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h2_destroy + h1_destroy + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1 192.0.2.2 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:1::2 +} + +do_test_pedit_l4port_one() +{ + local pedit_locus=$1; shift + local pedit_prot=$1; shift + local pedit_action=$1; shift + local match_prot=$1; shift + local match_flower=$1; shift + local mz_flags=$1; shift + local saddr=$1; shift + local daddr=$1; shift + + tc filter add $pedit_locus handle 101 pref 1 \ + flower action pedit ex munge $pedit_action + tc filter add dev $h2 ingress handle 101 pref 1 prot $match_prot \ + flower skip_hw $match_flower action pass + + RET=0 + + $MZ $mz_flags $h1 -c 10 -d 20msec -p 100 \ + -a own -b $h2mac -q -t $pedit_prot sp=54321,dp=12345 + + local pkts + pkts=$(busywait "$TC_HIT_TIMEOUT" until_counter_is ">= 10" \ + tc_rule_handle_stats_get "dev $h2 ingress" 101) + check_err $? "Expected to get 10 packets, but got $pkts." + + pkts=$(tc_rule_handle_stats_get "$pedit_locus" 101) + ((pkts >= 10)) + check_err $? "Expected to get 10 packets on pedit rule, but got $pkts." + + log_test "$pedit_locus pedit $pedit_action" + + tc filter del dev $h2 ingress pref 1 + tc filter del $pedit_locus pref 1 +} + +do_test_pedit_l4port() +{ + local locus=$1; shift + local prot=$1; shift + local pedit_port=$1; shift + local flower_port=$1; shift + local port + + for port in 1 11111 65535; do + do_test_pedit_l4port_one "$locus" "$prot" \ + "$prot $pedit_port set $port" \ + ip "ip_proto $prot $flower_port $port" \ + "-A 192.0.2.1 -B 192.0.2.2" + done +} + +test_udp_sport() +{ + do_test_pedit_l4port "dev $swp1 ingress" udp sport src_port + do_test_pedit_l4port "dev $swp2 egress" udp sport src_port +} + +test_udp_dport() +{ + do_test_pedit_l4port "dev $swp1 ingress" udp dport dst_port + do_test_pedit_l4port "dev $swp2 egress" udp dport dst_port +} + +test_tcp_sport() +{ + do_test_pedit_l4port "dev $swp1 ingress" tcp sport src_port + do_test_pedit_l4port "dev $swp2 egress" tcp sport src_port +} + +test_tcp_dport() +{ + do_test_pedit_l4port "dev $swp1 ingress" tcp dport dst_port + do_test_pedit_l4port "dev $swp2 egress" tcp dport dst_port +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS -- cgit v1.2.3 From b7ddfab20a6af3a0e366000eada63adf6a7683e7 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 19 Jun 2020 16:16:57 -0700 Subject: selftests/bpf: Add __ksym extern selftest Validate libbpf is able to handle weak and strong kernel symbol externs in BPF code correctly. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Reviewed-by: Hao Luo Link: https://lore.kernel.org/bpf/20200619231703.738941-4-andriin@fb.com --- tools/testing/selftests/bpf/prog_tests/ksyms.c | 71 ++++++++++++++++++++++++++ tools/testing/selftests/bpf/progs/test_ksyms.c | 32 ++++++++++++ 2 files changed, 103 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/ksyms.c create mode 100644 tools/testing/selftests/bpf/progs/test_ksyms.c (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/ksyms.c b/tools/testing/selftests/bpf/prog_tests/ksyms.c new file mode 100644 index 000000000000..e3d6777226a8 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/ksyms.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ + +#include +#include "test_ksyms.skel.h" +#include + +static int duration; + +static __u64 kallsyms_find(const char *sym) +{ + char type, name[500]; + __u64 addr, res = 0; + FILE *f; + + f = fopen("/proc/kallsyms", "r"); + if (CHECK(!f, "kallsyms_fopen", "failed to open: %d\n", errno)) + return 0; + + while (fscanf(f, "%llx %c %499s%*[^\n]\n", &addr, &type, name) > 0) { + if (strcmp(name, sym) == 0) { + res = addr; + goto out; + } + } + + CHECK(false, "not_found", "symbol %s not found\n", sym); +out: + fclose(f); + return res; +} + +void test_ksyms(void) +{ + __u64 link_fops_addr = kallsyms_find("bpf_link_fops"); + const char *btf_path = "/sys/kernel/btf/vmlinux"; + struct test_ksyms *skel; + struct test_ksyms__data *data; + struct stat st; + __u64 btf_size; + int err; + + if (CHECK(stat(btf_path, &st), "stat_btf", "err %d\n", errno)) + return; + btf_size = st.st_size; + + skel = test_ksyms__open_and_load(); + if (CHECK(!skel, "skel_open", "failed to open and load skeleton\n")) + return; + + err = test_ksyms__attach(skel); + if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) + goto cleanup; + + /* trigger tracepoint */ + usleep(1); + + data = skel->data; + CHECK(data->out__bpf_link_fops != link_fops_addr, "bpf_link_fops", + "got 0x%llx, exp 0x%llx\n", + data->out__bpf_link_fops, link_fops_addr); + CHECK(data->out__bpf_link_fops1 != 0, "bpf_link_fops1", + "got %llu, exp %llu\n", data->out__bpf_link_fops1, (__u64)0); + CHECK(data->out__btf_size != btf_size, "btf_size", + "got %llu, exp %llu\n", data->out__btf_size, btf_size); + CHECK(data->out__per_cpu_start != 0, "__per_cpu_start", + "got %llu, exp %llu\n", data->out__per_cpu_start, (__u64)0); + +cleanup: + test_ksyms__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/progs/test_ksyms.c b/tools/testing/selftests/bpf/progs/test_ksyms.c new file mode 100644 index 000000000000..6c9cbb5a3bdf --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_ksyms.c @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ + +#include +#include +#include + +__u64 out__bpf_link_fops = -1; +__u64 out__bpf_link_fops1 = -1; +__u64 out__btf_size = -1; +__u64 out__per_cpu_start = -1; + +extern const void bpf_link_fops __ksym; +extern const void __start_BTF __ksym; +extern const void __stop_BTF __ksym; +extern const void __per_cpu_start __ksym; +/* non-existing symbol, weak, default to zero */ +extern const void bpf_link_fops1 __ksym __weak; + +SEC("raw_tp/sys_enter") +int handler(const void *ctx) +{ + out__bpf_link_fops = (__u64)&bpf_link_fops; + out__btf_size = (__u64)(&__stop_BTF - &__start_BTF); + out__per_cpu_start = (__u64)&__per_cpu_start; + + out__bpf_link_fops1 = (__u64)&bpf_link_fops1; + + return 0; +} + +char _license[] SEC("license") = "GPL"; -- cgit v1.2.3 From 5e85c6bb8e74bd9daa4f5815da373d4ac2cb1a35 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 22 Jun 2020 20:22:22 -0700 Subject: selftests/bpf: Add variable-length data concatenation pattern test Add selftest that validates variable-length data reading and concatentation with one big shared data array. This is a common pattern in production use for monitoring and tracing applications, that potentially can read a lot of data, but overall read much less. Such pattern allows to determine precisely what amount of data needs to be sent over perfbuf/ringbuf and maximize efficiency. Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20200623032224.4020118-2-andriin@fb.com --- tools/testing/selftests/bpf/prog_tests/varlen.c | 56 +++++++++++++++ tools/testing/selftests/bpf/progs/test_varlen.c | 96 +++++++++++++++++++++++++ 2 files changed, 152 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/varlen.c create mode 100644 tools/testing/selftests/bpf/progs/test_varlen.c (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/varlen.c b/tools/testing/selftests/bpf/prog_tests/varlen.c new file mode 100644 index 000000000000..7533565e096d --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/varlen.c @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include +#include +#include "test_varlen.skel.h" + +#define CHECK_VAL(got, exp) \ + CHECK((got) != (exp), "check", "got %ld != exp %ld\n", \ + (long)(got), (long)(exp)) + +void test_varlen(void) +{ + int duration = 0, err; + struct test_varlen* skel; + struct test_varlen__bss *bss; + struct test_varlen__data *data; + const char str1[] = "Hello, "; + const char str2[] = "World!"; + const char exp_str[] = "Hello, \0World!\0"; + const int size1 = sizeof(str1); + const int size2 = sizeof(str2); + + skel = test_varlen__open_and_load(); + if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) + return; + bss = skel->bss; + data = skel->data; + + err = test_varlen__attach(skel); + if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) + goto cleanup; + + bss->test_pid = getpid(); + + /* trigger everything */ + memcpy(bss->buf_in1, str1, size1); + memcpy(bss->buf_in2, str2, size2); + bss->capture = true; + usleep(1); + bss->capture = false; + + CHECK_VAL(bss->payload1_len1, size1); + CHECK_VAL(bss->payload1_len2, size2); + CHECK_VAL(bss->total1, size1 + size2); + CHECK(memcmp(bss->payload1, exp_str, size1 + size2), "content_check", + "doesn't match!"); + + CHECK_VAL(data->payload2_len1, size1); + CHECK_VAL(data->payload2_len2, size2); + CHECK_VAL(data->total2, size1 + size2); + CHECK(memcmp(data->payload2, exp_str, size1 + size2), "content_check", + "doesn't match!"); +cleanup: + test_varlen__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/progs/test_varlen.c b/tools/testing/selftests/bpf/progs/test_varlen.c new file mode 100644 index 000000000000..09691852debf --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_varlen.c @@ -0,0 +1,96 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include "vmlinux.h" +#include +#include +#include + +#define MAX_LEN 256 + +char buf_in1[MAX_LEN] = {}; +char buf_in2[MAX_LEN] = {}; + +int test_pid = 0; +bool capture = false; + +/* .bss */ +long payload1_len1 = 0; +long payload1_len2 = 0; +long total1 = 0; +char payload1[MAX_LEN + MAX_LEN] = {}; + +/* .data */ +int payload2_len1 = -1; +int payload2_len2 = -1; +int total2 = -1; +char payload2[MAX_LEN + MAX_LEN] = { 1 }; + +SEC("raw_tp/sys_enter") +int handler64(void *regs) +{ + int pid = bpf_get_current_pid_tgid() >> 32; + void *payload = payload1; + u64 len; + + /* ignore irrelevant invocations */ + if (test_pid != pid || !capture) + return 0; + + len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in1[0]); + if (len <= MAX_LEN) { + payload += len; + payload1_len1 = len; + } + + len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in2[0]); + if (len <= MAX_LEN) { + payload += len; + payload1_len2 = len; + } + + total1 = payload - (void *)payload1; + + return 0; +} + +SEC("tp_btf/sys_enter") +int handler32(void *regs) +{ + int pid = bpf_get_current_pid_tgid() >> 32; + void *payload = payload2; + u32 len; + + /* ignore irrelevant invocations */ + if (test_pid != pid || !capture) + return 0; + + len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in1[0]); + if (len <= MAX_LEN) { + payload += len; + payload2_len1 = len; + } + + len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in2[0]); + if (len <= MAX_LEN) { + payload += len; + payload2_len2 = len; + } + + total2 = payload - (void *)payload2; + + return 0; +} + +SEC("tp_btf/sys_exit") +int handler_exit(void *regs) +{ + long bla; + + if (bpf_probe_read_kernel(&bla, sizeof(bla), 0)) + return 1; + else + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; -- cgit v1.2.3 From 2fde1747c986cac28fa66d0cffd7577db042640b Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 22 Jun 2020 20:22:23 -0700 Subject: selftests/bpf: Add variable-length data concat pattern less than test Extend original variable-length tests with a case to catch a common existing pattern of testing for < 0 for errors. Note because verifier also tracks upper bounds and we know it can not be greater than MAX_LEN here we can skip upper bound check. In ALU64 enabled compilation converting from long->int return types in probe helpers results in extra instruction pattern, <<= 32, s >>= 32. The trade-off is the non-ALU64 case works. If you really care about every extra insn (XDP case?) then you probably should be using original int type. In addition adding a sext insn to bpf might help the verifier in the general case to avoid these types of tricks. Signed-off-by: John Fastabend Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20200623032224.4020118-3-andriin@fb.com --- tools/testing/selftests/bpf/prog_tests/varlen.c | 12 +++++ tools/testing/selftests/bpf/progs/test_varlen.c | 70 +++++++++++++++++++++++-- 2 files changed, 78 insertions(+), 4 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/varlen.c b/tools/testing/selftests/bpf/prog_tests/varlen.c index 7533565e096d..c75525eab02c 100644 --- a/tools/testing/selftests/bpf/prog_tests/varlen.c +++ b/tools/testing/selftests/bpf/prog_tests/varlen.c @@ -51,6 +51,18 @@ void test_varlen(void) CHECK_VAL(data->total2, size1 + size2); CHECK(memcmp(data->payload2, exp_str, size1 + size2), "content_check", "doesn't match!"); + + CHECK_VAL(data->payload3_len1, size1); + CHECK_VAL(data->payload3_len2, size2); + CHECK_VAL(data->total3, size1 + size2); + CHECK(memcmp(data->payload3, exp_str, size1 + size2), "content_check", + "doesn't match!"); + + CHECK_VAL(data->payload4_len1, size1); + CHECK_VAL(data->payload4_len2, size2); + CHECK_VAL(data->total4, size1 + size2); + CHECK(memcmp(data->payload4, exp_str, size1 + size2), "content_check", + "doesn't match!"); cleanup: test_varlen__destroy(skel); } diff --git a/tools/testing/selftests/bpf/progs/test_varlen.c b/tools/testing/selftests/bpf/progs/test_varlen.c index 09691852debf..cd4b72c55dfe 100644 --- a/tools/testing/selftests/bpf/progs/test_varlen.c +++ b/tools/testing/selftests/bpf/progs/test_varlen.c @@ -26,8 +26,18 @@ int payload2_len2 = -1; int total2 = -1; char payload2[MAX_LEN + MAX_LEN] = { 1 }; +int payload3_len1 = -1; +int payload3_len2 = -1; +int total3= -1; +char payload3[MAX_LEN + MAX_LEN] = { 1 }; + +int payload4_len1 = -1; +int payload4_len2 = -1; +int total4= -1; +char payload4[MAX_LEN + MAX_LEN] = { 1 }; + SEC("raw_tp/sys_enter") -int handler64(void *regs) +int handler64_unsigned(void *regs) { int pid = bpf_get_current_pid_tgid() >> 32; void *payload = payload1; @@ -54,8 +64,34 @@ int handler64(void *regs) return 0; } -SEC("tp_btf/sys_enter") -int handler32(void *regs) +SEC("raw_tp/sys_exit") +int handler64_signed(void *regs) +{ + int pid = bpf_get_current_pid_tgid() >> 32; + void *payload = payload3; + long len; + + /* ignore irrelevant invocations */ + if (test_pid != pid || !capture) + return 0; + + len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in1[0]); + if (len >= 0) { + payload += len; + payload3_len1 = len; + } + len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in2[0]); + if (len >= 0) { + payload += len; + payload3_len2 = len; + } + total3 = payload - (void *)payload3; + + return 0; +} + +SEC("tp/raw_syscalls/sys_enter") +int handler32_unsigned(void *regs) { int pid = bpf_get_current_pid_tgid() >> 32; void *payload = payload2; @@ -82,7 +118,33 @@ int handler32(void *regs) return 0; } -SEC("tp_btf/sys_exit") +SEC("tp/raw_syscalls/sys_exit") +int handler32_signed(void *regs) +{ + int pid = bpf_get_current_pid_tgid() >> 32; + void *payload = payload4; + int len; + + /* ignore irrelevant invocations */ + if (test_pid != pid || !capture) + return 0; + + len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in1[0]); + if (len >= 0) { + payload += len; + payload4_len1 = len; + } + len = bpf_probe_read_kernel_str(payload, MAX_LEN, &buf_in2[0]); + if (len >= 0) { + payload += len; + payload4_len2 = len; + } + total4 = payload - (void *)payload4; + + return 0; +} + +SEC("tp/syscalls/sys_exit_getpid") int handler_exit(void *regs) { long bla; -- cgit v1.2.3 From 0558c396040734bc1d361919566a581fd41aa539 Mon Sep 17 00:00:00 2001 From: tannerlove Date: Mon, 22 Jun 2020 13:43:24 -0400 Subject: selftests/net: plug rxtimestamp test into kselftest framework Run rxtimestamp as part of TEST_PROGS. Analogous to other tests, add new rxtimestamp.sh wrapper script, so that the test runs isolated from background traffic in a private network namespace. Also ignore failures of test case #6 by default. This case verifies that a receive timestamp is not reported if timestamp reporting is enabled for a socket, but generation is disabled. Receive timestamp generation has to be enabled globally, as no associated socket is known yet. A background process that enables rx timestamp generation therefore causes a false positive. Ntpd is one example that does. Add a "--strict" option to cause failure in the event that any test case fails, including test #6. This is useful for environments that are known to not have such background processes. Tested: make -C tools/testing/selftests TARGETS="net" run_tests Signed-off-by: Tanner Love Acked-by: Willem de Bruijn Signed-off-by: David S. Miller --- tools/testing/selftests/net/Makefile | 1 + tools/testing/selftests/net/rxtimestamp.c | 11 +++++++++-- tools/testing/selftests/net/rxtimestamp.sh | 4 ++++ 3 files changed, 14 insertions(+), 2 deletions(-) create mode 100755 tools/testing/selftests/net/rxtimestamp.sh (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 895ec992b2f1..bfacb960450f 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -17,6 +17,7 @@ TEST_PROGS += route_localnet.sh TEST_PROGS += reuseaddr_ports_exhausted.sh TEST_PROGS += txtimestamp.sh TEST_PROGS += vrf-xfrm-tests.sh +TEST_PROGS += rxtimestamp.sh TEST_PROGS_EXTENDED := in_netns.sh TEST_GEN_FILES = socket nettest TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any diff --git a/tools/testing/selftests/net/rxtimestamp.c b/tools/testing/selftests/net/rxtimestamp.c index 422e7761254d..d4ea86a13e52 100644 --- a/tools/testing/selftests/net/rxtimestamp.c +++ b/tools/testing/selftests/net/rxtimestamp.c @@ -44,6 +44,7 @@ struct test_case { struct options sockopt; struct tstamps expected; bool enabled; + bool warn_on_fail; }; struct sof_flag { @@ -89,7 +90,7 @@ static struct test_case test_cases[] = { }, { { so_timestamping: SOF_TIMESTAMPING_SOFTWARE }, - {} + warn_on_fail : true }, { { so_timestamping: SOF_TIMESTAMPING_RX_SOFTWARE @@ -115,6 +116,7 @@ static struct option long_options[] = { { "tcp", no_argument, 0, 't' }, { "udp", no_argument, 0, 'u' }, { "ip", no_argument, 0, 'i' }, + { "strict", no_argument, 0, 'S' }, { NULL, 0, NULL, 0 }, }; @@ -327,6 +329,7 @@ int main(int argc, char **argv) { bool all_protocols = true; bool all_tests = true; + bool strict = false; int arg_index = 0; int failures = 0; int s, t; @@ -363,6 +366,9 @@ int main(int argc, char **argv) all_protocols = false; socket_types[0].enabled = true; break; + case 'S': + strict = true; + break; default: error(1, 0, "Failed to parse parameters."); } @@ -379,7 +385,8 @@ int main(int argc, char **argv) printf("Starting testcase %d...\n", t); if (run_test_case(socket_types[s], test_cases[t])) { - failures++; + if (strict || !test_cases[t].warn_on_fail) + failures++; printf("FAILURE in test case "); print_test_case(&test_cases[t]); } diff --git a/tools/testing/selftests/net/rxtimestamp.sh b/tools/testing/selftests/net/rxtimestamp.sh new file mode 100755 index 000000000000..91631e88bf46 --- /dev/null +++ b/tools/testing/selftests/net/rxtimestamp.sh @@ -0,0 +1,4 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +./in_netns.sh ./rxtimestamp $@ -- cgit v1.2.3 From fea549b030152d5336dbd960b357a4d4b841a851 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 24 Jun 2020 11:10:59 -0700 Subject: selftests/bpf: Workaround for get_stack_rawtp test. ./test_progs-no_alu32 -t get_stack_raw_tp fails due to: 52: (85) call bpf_get_stack#67 53: (bf) r8 = r0 54: (bf) r1 = r8 55: (67) r1 <<= 32 56: (c7) r1 s>>= 32 ; if (usize < 0) 57: (c5) if r1 s< 0x0 goto pc+26 R0=inv(id=0,smax_value=800) R1_w=inv(id=0,umax_value=800,var_off=(0x0; 0x3ff)) R6=ctx(id=0,off=0,imm=0) R7=map_value(id=0,off=0,ks=4,vs=1600,imm=0) R8_w=inv(id=0,smax_value=800) R9=inv800 ; ksize = bpf_get_stack(ctx, raw_data + usize, max_len - usize, 0); 58: (1f) r9 -= r8 ; ksize = bpf_get_stack(ctx, raw_data + usize, max_len - usize, 0); 59: (bf) r2 = r7 60: (0f) r2 += r1 regs=1 stack=0 before 52: (85) call bpf_get_stack#67 ; ksize = bpf_get_stack(ctx, raw_data + usize, max_len - usize, 0); 61: (bf) r1 = r6 62: (bf) r3 = r9 63: (b7) r4 = 0 64: (85) call bpf_get_stack#67 R0=inv(id=0,smax_value=800) R1_w=ctx(id=0,off=0,imm=0) R2_w=map_value(id=0,off=0,ks=4,vs=1600,umax_value=800,var_off=(0x0; 0x3ff),s32_max_value=1023,u32_max_value=1023) R3_w=inv(id=0,umax_value=9223372036854776608) R3 unbounded memory access, use 'var &= const' or 'if (var < const)' In the C code: usize = bpf_get_stack(ctx, raw_data, max_len, BPF_F_USER_STACK); if (usize < 0) return 0; ksize = bpf_get_stack(ctx, raw_data + usize, max_len - usize, 0); if (ksize < 0) return 0; We used to have problem with pointer arith in R2. Now it's a problem with two integers in R3. 'if (usize < 0)' is comparing R1 and makes it [0,800], but R8 stays [-inf,800]. Both registers represent the same 'usize' variable. Then R9 -= R8 is doing 800 - [-inf, 800] so the result of "max_len - usize" looks unbounded to the verifier while it's obvious in C code that "max_len - usize" should be [0, 800]. To workaround the problem convert ksize and usize variables from int to long. Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c index 29817a703984..b6a6eb279e54 100644 --- a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c +++ b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c @@ -57,8 +57,9 @@ struct { SEC("raw_tracepoint/sys_enter") int bpf_prog1(void *ctx) { - int max_len, max_buildid_len, usize, ksize, total_size; + int max_len, max_buildid_len, total_size; struct stack_trace_t *data; + long usize, ksize; void *raw_data; __u32 key = 0; -- cgit v1.2.3 From f9bcf96837f158db6ea982d15cd2c8161ca6bc23 Mon Sep 17 00:00:00 2001 From: Dmitry Yakunin Date: Sat, 20 Jun 2020 18:30:52 +0300 Subject: bpf: Add SO_KEEPALIVE and related options to bpf_setsockopt This patch adds support of SO_KEEPALIVE flag and TCP related options to bpf_setsockopt() routine. This is helpful if we want to enable or tune TCP keepalive for applications which don't do it in the userspace code. v3: - update kernel-doc in uapi (Nikita Vetoshkin ) v4: - update kernel-doc in tools too (Alexei Starovoitov) - add test to selftests (Alexei Starovoitov) Signed-off-by: Dmitry Yakunin Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20200620153052.9439-3-zeil@yandex-team.ru --- include/uapi/linux/bpf.h | 7 +++-- net/core/filter.c | 36 ++++++++++++++++++++++- tools/include/uapi/linux/bpf.h | 7 +++-- tools/testing/selftests/bpf/progs/connect4_prog.c | 27 +++++++++++++++++ 4 files changed, 72 insertions(+), 5 deletions(-) (limited to 'tools/testing/selftests') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 9d3923e6b860..d9737d51dd19 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1621,10 +1621,13 @@ union bpf_attr { * * * **SOL_SOCKET**, which supports the following *optname*\ s: * **SO_RCVBUF**, **SO_SNDBUF**, **SO_MAX_PACING_RATE**, - * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**. + * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**, + * **SO_BINDTODEVICE**, **SO_KEEPALIVE**. * * **IPPROTO_TCP**, which supports the following *optname*\ s: * **TCP_CONGESTION**, **TCP_BPF_IW**, - * **TCP_BPF_SNDCWND_CLAMP**. + * **TCP_BPF_SNDCWND_CLAMP**, **TCP_SAVE_SYN**, + * **TCP_KEEPIDLE**, **TCP_KEEPINTVL**, **TCP_KEEPCNT**, + * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**. * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. * Return diff --git a/net/core/filter.c b/net/core/filter.c index 73395384afe2..c713b6b8938f 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4289,10 +4289,10 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, char *optval, int optlen, u32 flags) { char devname[IFNAMSIZ]; + int val, valbool; struct net *net; int ifindex; int ret = 0; - int val; if (!sk_fullsock(sk)) return -EINVAL; @@ -4303,6 +4303,7 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, if (optlen != sizeof(int) && optname != SO_BINDTODEVICE) return -EINVAL; val = *((int *)optval); + valbool = val ? 1 : 0; /* Only some socketops are supported */ switch (optname) { @@ -4361,6 +4362,11 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, } ret = sock_bindtoindex(sk, ifindex, false); break; + case SO_KEEPALIVE: + if (sk->sk_prot->keepalive) + sk->sk_prot->keepalive(sk, valbool); + sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool); + break; default: ret = -EINVAL; } @@ -4421,6 +4427,7 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, ret = tcp_set_congestion_control(sk, name, false, reinit, true); } else { + struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); if (optlen != sizeof(int)) @@ -4449,6 +4456,33 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, else tp->save_syn = val; break; + case TCP_KEEPIDLE: + ret = tcp_sock_set_keepidle_locked(sk, val); + break; + case TCP_KEEPINTVL: + if (val < 1 || val > MAX_TCP_KEEPINTVL) + ret = -EINVAL; + else + tp->keepalive_intvl = val * HZ; + break; + case TCP_KEEPCNT: + if (val < 1 || val > MAX_TCP_KEEPCNT) + ret = -EINVAL; + else + tp->keepalive_probes = val; + break; + case TCP_SYNCNT: + if (val < 1 || val > MAX_TCP_SYNCNT) + ret = -EINVAL; + else + icsk->icsk_syn_retries = val; + break; + case TCP_USER_TIMEOUT: + if (val < 0) + ret = -EINVAL; + else + icsk->icsk_user_timeout = val; + break; default: ret = -EINVAL; } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 9d3923e6b860..d9737d51dd19 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1621,10 +1621,13 @@ union bpf_attr { * * * **SOL_SOCKET**, which supports the following *optname*\ s: * **SO_RCVBUF**, **SO_SNDBUF**, **SO_MAX_PACING_RATE**, - * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**. + * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**, + * **SO_BINDTODEVICE**, **SO_KEEPALIVE**. * * **IPPROTO_TCP**, which supports the following *optname*\ s: * **TCP_CONGESTION**, **TCP_BPF_IW**, - * **TCP_BPF_SNDCWND_CLAMP**. + * **TCP_BPF_SNDCWND_CLAMP**, **TCP_SAVE_SYN**, + * **TCP_KEEPIDLE**, **TCP_KEEPINTVL**, **TCP_KEEPCNT**, + * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**. * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. * Return diff --git a/tools/testing/selftests/bpf/progs/connect4_prog.c b/tools/testing/selftests/bpf/progs/connect4_prog.c index 1ab2c5eba86c..b1b2773c0b9d 100644 --- a/tools/testing/selftests/bpf/progs/connect4_prog.c +++ b/tools/testing/selftests/bpf/progs/connect4_prog.c @@ -104,6 +104,30 @@ static __inline int bind_to_device(struct bpf_sock_addr *ctx) return 0; } +static __inline int set_keepalive(struct bpf_sock_addr *ctx) +{ + int zero = 0, one = 1; + + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_KEEPALIVE, &one, sizeof(one))) + return 1; + if (ctx->type == SOCK_STREAM) { + if (bpf_setsockopt(ctx, SOL_TCP, TCP_KEEPIDLE, &one, sizeof(one))) + return 1; + if (bpf_setsockopt(ctx, SOL_TCP, TCP_KEEPINTVL, &one, sizeof(one))) + return 1; + if (bpf_setsockopt(ctx, SOL_TCP, TCP_KEEPCNT, &one, sizeof(one))) + return 1; + if (bpf_setsockopt(ctx, SOL_TCP, TCP_SYNCNT, &one, sizeof(one))) + return 1; + if (bpf_setsockopt(ctx, SOL_TCP, TCP_USER_TIMEOUT, &one, sizeof(one))) + return 1; + } + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_KEEPALIVE, &zero, sizeof(zero))) + return 1; + + return 0; +} + SEC("cgroup/connect4") int connect_v4_prog(struct bpf_sock_addr *ctx) { @@ -121,6 +145,9 @@ int connect_v4_prog(struct bpf_sock_addr *ctx) if (bind_to_device(ctx)) return 0; + if (set_keepalive(ctx)) + return 0; + if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM) return 0; else if (ctx->type == SOCK_STREAM) -- cgit v1.2.3 From 84544f5637ff3501876ba96bd48ca900317e08fb Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 23 Jun 2020 16:08:16 -0700 Subject: selftests/bpf: Move newer bpf_iter_* type redefining to a new header file Commit b9f4c01f3e0b ("selftest/bpf: Make bpf_iter selftest compilable against old vmlinux.h") and Commit dda18a5c0b75 ("selftests/bpf: Convert bpf_iter_test_kern{3, 4}.c to define own bpf_iter_meta") redefined newly introduced types in bpf programs so the bpf program can still compile properly with old kernels although loading may fail. Since this patch set introduced new types and the same workaround is needed, so let us move the workaround to a separate header file so they do not clutter bpf programs. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20200623230816.3988656-1-yhs@fb.com --- tools/testing/selftests/bpf/progs/bpf_iter.h | 49 ++++++++++++++++++++++ .../testing/selftests/bpf/progs/bpf_iter_bpf_map.c | 18 +------- .../selftests/bpf/progs/bpf_iter_ipv6_route.c | 18 +------- .../testing/selftests/bpf/progs/bpf_iter_netlink.c | 18 +------- tools/testing/selftests/bpf/progs/bpf_iter_task.c | 18 +------- .../selftests/bpf/progs/bpf_iter_task_file.c | 20 +-------- .../selftests/bpf/progs/bpf_iter_test_kern3.c | 17 +------- .../selftests/bpf/progs/bpf_iter_test_kern4.c | 17 +------- .../bpf/progs/bpf_iter_test_kern_common.h | 18 +------- 9 files changed, 57 insertions(+), 136 deletions(-) create mode 100644 tools/testing/selftests/bpf/progs/bpf_iter.h (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/progs/bpf_iter.h b/tools/testing/selftests/bpf/progs/bpf_iter.h new file mode 100644 index 000000000000..3757e88c6406 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2020 Facebook */ +/* "undefine" structs in vmlinux.h, because we "override" them below */ +#define bpf_iter_meta bpf_iter_meta___not_used +#define bpf_iter__bpf_map bpf_iter__bpf_map___not_used +#define bpf_iter__ipv6_route bpf_iter__ipv6_route___not_used +#define bpf_iter__netlink bpf_iter__netlink___not_used +#define bpf_iter__task bpf_iter__task___not_used +#define bpf_iter__task_file bpf_iter__task_file___not_used +#include "vmlinux.h" +#undef bpf_iter_meta +#undef bpf_iter__bpf_map +#undef bpf_iter__ipv6_route +#undef bpf_iter__netlink +#undef bpf_iter__task +#undef bpf_iter__task_file + +struct bpf_iter_meta { + struct seq_file *seq; + __u64 session_id; + __u64 seq_num; +} __attribute__((preserve_access_index)); + +struct bpf_iter__ipv6_route { + struct bpf_iter_meta *meta; + struct fib6_info *rt; +} __attribute__((preserve_access_index)); + +struct bpf_iter__netlink { + struct bpf_iter_meta *meta; + struct netlink_sock *sk; +} __attribute__((preserve_access_index)); + +struct bpf_iter__task { + struct bpf_iter_meta *meta; + struct task_struct *task; +} __attribute__((preserve_access_index)); + +struct bpf_iter__task_file { + struct bpf_iter_meta *meta; + struct task_struct *task; + __u32 fd; + struct file *file; +} __attribute__((preserve_access_index)); + +struct bpf_iter__bpf_map { + struct bpf_iter_meta *meta; + struct bpf_map *map; +} __attribute__((preserve_access_index)); diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c index b57bd6fef208..08651b23edba 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c @@ -1,27 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020 Facebook */ -/* "undefine" structs in vmlinux.h, because we "override" them below */ -#define bpf_iter_meta bpf_iter_meta___not_used -#define bpf_iter__bpf_map bpf_iter__bpf_map___not_used -#include "vmlinux.h" -#undef bpf_iter_meta -#undef bpf_iter__bpf_map +#include "bpf_iter.h" #include #include char _license[] SEC("license") = "GPL"; -struct bpf_iter_meta { - struct seq_file *seq; - __u64 session_id; - __u64 seq_num; -} __attribute__((preserve_access_index)); - -struct bpf_iter__bpf_map { - struct bpf_iter_meta *meta; - struct bpf_map *map; -} __attribute__((preserve_access_index)); - SEC("iter/bpf_map") int dump_bpf_map(struct bpf_iter__bpf_map *ctx) { diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c b/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c index c8e9ca74c87b..93a452d1d136 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c @@ -1,25 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020 Facebook */ -/* "undefine" structs in vmlinux.h, because we "override" them below */ -#define bpf_iter_meta bpf_iter_meta___not_used -#define bpf_iter__ipv6_route bpf_iter__ipv6_route___not_used -#include "vmlinux.h" -#undef bpf_iter_meta -#undef bpf_iter__ipv6_route +#include "bpf_iter.h" #include #include -struct bpf_iter_meta { - struct seq_file *seq; - __u64 session_id; - __u64 seq_num; -} __attribute__((preserve_access_index)); - -struct bpf_iter__ipv6_route { - struct bpf_iter_meta *meta; - struct fib6_info *rt; -} __attribute__((preserve_access_index)); - char _license[] SEC("license") = "GPL"; extern bool CONFIG_IPV6_SUBTREES __kconfig __weak; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c index e7b8753eac0b..fda5036fdf75 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c @@ -1,11 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020 Facebook */ -/* "undefine" structs in vmlinux.h, because we "override" them below */ -#define bpf_iter_meta bpf_iter_meta___not_used -#define bpf_iter__netlink bpf_iter__netlink___not_used -#include "vmlinux.h" -#undef bpf_iter_meta -#undef bpf_iter__netlink +#include "bpf_iter.h" #include #include @@ -14,17 +9,6 @@ char _license[] SEC("license") = "GPL"; #define sk_rmem_alloc sk_backlog.rmem_alloc #define sk_refcnt __sk_common.skc_refcnt -struct bpf_iter_meta { - struct seq_file *seq; - __u64 session_id; - __u64 seq_num; -} __attribute__((preserve_access_index)); - -struct bpf_iter__netlink { - struct bpf_iter_meta *meta; - struct netlink_sock *sk; -} __attribute__((preserve_access_index)); - static inline struct inode *SOCK_INODE(struct socket *socket) { return &container_of(socket, struct socket_alloc, socket)->vfs_inode; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task.c b/tools/testing/selftests/bpf/progs/bpf_iter_task.c index ee754021f98e..4983087852a0 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_task.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_task.c @@ -1,27 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020 Facebook */ -/* "undefine" structs in vmlinux.h, because we "override" them below */ -#define bpf_iter_meta bpf_iter_meta___not_used -#define bpf_iter__task bpf_iter__task___not_used -#include "vmlinux.h" -#undef bpf_iter_meta -#undef bpf_iter__task +#include "bpf_iter.h" #include #include char _license[] SEC("license") = "GPL"; -struct bpf_iter_meta { - struct seq_file *seq; - __u64 session_id; - __u64 seq_num; -} __attribute__((preserve_access_index)); - -struct bpf_iter__task { - struct bpf_iter_meta *meta; - struct task_struct *task; -} __attribute__((preserve_access_index)); - SEC("iter/task") int dump_task(struct bpf_iter__task *ctx) { diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c index 0f0ec3db20ba..8b787baa2654 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c @@ -1,29 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020 Facebook */ -/* "undefine" structs in vmlinux.h, because we "override" them below */ -#define bpf_iter_meta bpf_iter_meta___not_used -#define bpf_iter__task_file bpf_iter__task_file___not_used -#include "vmlinux.h" -#undef bpf_iter_meta -#undef bpf_iter__task_file +#include "bpf_iter.h" #include #include char _license[] SEC("license") = "GPL"; -struct bpf_iter_meta { - struct seq_file *seq; - __u64 session_id; - __u64 seq_num; -} __attribute__((preserve_access_index)); - -struct bpf_iter__task_file { - struct bpf_iter_meta *meta; - struct task_struct *task; - __u32 fd; - struct file *file; -} __attribute__((preserve_access_index)); - SEC("iter/task_file") int dump_task_file(struct bpf_iter__task_file *ctx) { diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern3.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern3.c index 13c2c90c835f..2a4647f20c46 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern3.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern3.c @@ -1,25 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020 Facebook */ -#define bpf_iter_meta bpf_iter_meta___not_used -#define bpf_iter__task bpf_iter__task___not_used -#include "vmlinux.h" -#undef bpf_iter_meta -#undef bpf_iter__task +#include "bpf_iter.h" #include char _license[] SEC("license") = "GPL"; -struct bpf_iter_meta { - struct seq_file *seq; - __u64 session_id; - __u64 seq_num; -} __attribute__((preserve_access_index)); - -struct bpf_iter__task { - struct bpf_iter_meta *meta; - struct task_struct *task; -} __attribute__((preserve_access_index)); - SEC("iter/task") int dump_task(struct bpf_iter__task *ctx) { diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c index 0aa71b333cf3..ee49493dc125 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c @@ -1,25 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020 Facebook */ -#define bpf_iter_meta bpf_iter_meta___not_used -#define bpf_iter__bpf_map bpf_iter__bpf_map___not_used -#include "vmlinux.h" -#undef bpf_iter_meta -#undef bpf_iter__bpf_map +#include "bpf_iter.h" #include char _license[] SEC("license") = "GPL"; -struct bpf_iter_meta { - struct seq_file *seq; - __u64 session_id; - __u64 seq_num; -} __attribute__((preserve_access_index)); - -struct bpf_iter__bpf_map { - struct bpf_iter_meta *meta; - struct bpf_map *map; -} __attribute__((preserve_access_index)); - __u32 map1_id = 0, map2_id = 0; __u32 map1_accessed = 0, map2_accessed = 0; __u64 map1_seqnum = 0, map2_seqnum1 = 0, map2_seqnum2 = 0; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern_common.h b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern_common.h index dee1339e6905..d5e3df66ad9a 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern_common.h +++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern_common.h @@ -1,27 +1,11 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (c) 2020 Facebook */ -/* "undefine" structs in vmlinux.h, because we "override" them below */ -#define bpf_iter_meta bpf_iter_meta___not_used -#define bpf_iter__task bpf_iter__task___not_used -#include "vmlinux.h" -#undef bpf_iter_meta -#undef bpf_iter__task +#include "bpf_iter.h" #include char _license[] SEC("license") = "GPL"; int count = 0; -struct bpf_iter_meta { - struct seq_file *seq; - __u64 session_id; - __u64 seq_num; -} __attribute__((preserve_access_index)); - -struct bpf_iter__task { - struct bpf_iter_meta *meta; - struct task_struct *task; -} __attribute__((preserve_access_index)); - SEC("iter/task") int dump_task(struct bpf_iter__task *ctx) { -- cgit v1.2.3 From 647b502e3d5456f5c240b1587112b163c69732e9 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 23 Jun 2020 16:08:17 -0700 Subject: selftests/bpf: Refactor some net macros to bpf_tracing_net.h Refactor bpf_iter_ipv6_route.c and bpf_iter_netlink.c so net macros, originally from various include/linux header files, are moved to a new header file bpf_tracing_net.h. The goal is to improve reuse so networking tracing programs do not need to copy these macros every time they use them. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20200623230817.3988962-1-yhs@fb.com --- tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c | 7 +------ tools/testing/selftests/bpf/progs/bpf_iter_netlink.c | 4 +--- tools/testing/selftests/bpf/progs/bpf_tracing_net.h | 16 ++++++++++++++++ 3 files changed, 18 insertions(+), 9 deletions(-) create mode 100644 tools/testing/selftests/bpf/progs/bpf_tracing_net.h (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c b/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c index 93a452d1d136..d58d9f1642b5 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020 Facebook */ #include "bpf_iter.h" +#include "bpf_tracing_net.h" #include #include @@ -8,12 +9,6 @@ char _license[] SEC("license") = "GPL"; extern bool CONFIG_IPV6_SUBTREES __kconfig __weak; -#define RTF_GATEWAY 0x0002 -#define IFNAMSIZ 16 -#define fib_nh_gw_family nh_common.nhc_gw_family -#define fib_nh_gw6 nh_common.nhc_gw.ipv6 -#define fib_nh_dev nh_common.nhc_dev - SEC("iter/ipv6_route") int dump_ipv6_route(struct bpf_iter__ipv6_route *ctx) { diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c index fda5036fdf75..cec82a419800 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c @@ -1,14 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020 Facebook */ #include "bpf_iter.h" +#include "bpf_tracing_net.h" #include #include char _license[] SEC("license") = "GPL"; -#define sk_rmem_alloc sk_backlog.rmem_alloc -#define sk_refcnt __sk_common.skc_refcnt - static inline struct inode *SOCK_INODE(struct socket *socket) { return &container_of(socket, struct socket_alloc, socket)->vfs_inode; diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h new file mode 100644 index 000000000000..1f38a1098727 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __BPF_TRACING_NET_H__ +#define __BPF_TRACING_NET_H__ + +#define IFNAMSIZ 16 + +#define RTF_GATEWAY 0x0002 + +#define fib_nh_dev nh_common.nhc_dev +#define fib_nh_gw_family nh_common.nhc_gw_family +#define fib_nh_gw6 nh_common.nhc_gw.ipv6 + +#define sk_rmem_alloc sk_backlog.rmem_alloc +#define sk_refcnt __sk_common.skc_refcnt + +#endif -- cgit v1.2.3 From 3982bfaaef7c80ecf6a065cbf9422165a8e36f75 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 23 Jun 2020 16:08:19 -0700 Subject: selftests/bpf: Add more common macros to bpf_tracing_net.h These newly added macros will be used in subsequent bpf iterator tcp{4,6} and udp{4,6} programs. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20200623230819.3989050-1-yhs@fb.com --- .../testing/selftests/bpf/progs/bpf_tracing_net.h | 35 ++++++++++++++++++++++ 1 file changed, 35 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h index 1f38a1098727..01378911252b 100644 --- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h +++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h @@ -2,15 +2,50 @@ #ifndef __BPF_TRACING_NET_H__ #define __BPF_TRACING_NET_H__ +#define AF_INET 2 +#define AF_INET6 10 + +#define ICSK_TIME_RETRANS 1 +#define ICSK_TIME_PROBE0 3 +#define ICSK_TIME_LOSS_PROBE 5 +#define ICSK_TIME_REO_TIMEOUT 6 + #define IFNAMSIZ 16 #define RTF_GATEWAY 0x0002 +#define TCP_INFINITE_SSTHRESH 0x7fffffff +#define TCP_PINGPONG_THRESH 3 + #define fib_nh_dev nh_common.nhc_dev #define fib_nh_gw_family nh_common.nhc_gw_family #define fib_nh_gw6 nh_common.nhc_gw.ipv6 +#define inet_daddr sk.__sk_common.skc_daddr +#define inet_rcv_saddr sk.__sk_common.skc_rcv_saddr +#define inet_dport sk.__sk_common.skc_dport + +#define ir_loc_addr req.__req_common.skc_rcv_saddr +#define ir_num req.__req_common.skc_num +#define ir_rmt_addr req.__req_common.skc_daddr +#define ir_rmt_port req.__req_common.skc_dport +#define ir_v6_rmt_addr req.__req_common.skc_v6_daddr +#define ir_v6_loc_addr req.__req_common.skc_v6_rcv_saddr + +#define sk_family __sk_common.skc_family #define sk_rmem_alloc sk_backlog.rmem_alloc #define sk_refcnt __sk_common.skc_refcnt +#define sk_state __sk_common.skc_state +#define sk_v6_daddr __sk_common.skc_v6_daddr +#define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr + +#define s6_addr32 in6_u.u6_addr32 + +#define tw_daddr __tw_common.skc_daddr +#define tw_rcv_saddr __tw_common.skc_rcv_saddr +#define tw_dport __tw_common.skc_dport +#define tw_refcnt __tw_common.skc_refcnt +#define tw_v6_daddr __tw_common.skc_v6_daddr +#define tw_v6_rcv_saddr __tw_common.skc_v6_rcv_saddr #endif -- cgit v1.2.3 From 2767c97765cb3d9b54c8e62b468e55cc56854a66 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 23 Jun 2020 16:08:20 -0700 Subject: selftests/bpf: Implement sample tcp/tcp6 bpf_iter programs In my VM, I got identical result compared to /proc/net/{tcp,tcp6}. For tcp6: $ cat /proc/net/tcp6 sl local_address remote_address st tx_queue rx_queue tr tm->when retrnsmt uid timeout inode 0: 00000000000000000000000000000000:0016 00000000000000000000000000000000:0000 0A 00000000:00000000 00:00000001 00000000 0 0 17955 1 000000003eb3102e 100 0 0 10 0 $ cat /sys/fs/bpf/p1 sl local_address remote_address st tx_queue rx_queue tr tm->when retrnsmt uid timeout inode 0: 00000000000000000000000000000000:0016 00000000000000000000000000000000:0000 0A 00000000:00000000 00:00000000 00000000 0 0 17955 1 000000003eb3102e 100 0 0 10 0 For tcp: $ cat /proc/net/tcp sl local_address rem_address st tx_queue rx_queue tr tm->when retrnsmt uid timeout inode 0: 00000000:0016 00000000:0000 0A 00000000:00000000 00:00000000 00000000 0 0 2666 1 000000007152e43f 100 0 0 10 0 $ cat /sys/fs/bpf/p2 sl local_address remote_address st tx_queue rx_queue tr tm->when retrnsmt uid timeout inode 1: 00000000:0016 00000000:0000 0A 00000000:00000000 00:00000000 00000000 0 0 2666 1 000000007152e43f 100 0 0 10 0 Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20200623230820.3989165-1-yhs@fb.com --- tools/testing/selftests/bpf/progs/bpf_iter.h | 15 ++ tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c | 234 ++++++++++++++++++++ tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c | 250 ++++++++++++++++++++++ 3 files changed, 499 insertions(+) create mode 100644 tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c create mode 100644 tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/progs/bpf_iter.h b/tools/testing/selftests/bpf/progs/bpf_iter.h index 3757e88c6406..bde23e16e777 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter.h +++ b/tools/testing/selftests/bpf/progs/bpf_iter.h @@ -7,6 +7,8 @@ #define bpf_iter__netlink bpf_iter__netlink___not_used #define bpf_iter__task bpf_iter__task___not_used #define bpf_iter__task_file bpf_iter__task_file___not_used +#define bpf_iter__tcp bpf_iter__tcp___not_used +#define tcp6_sock tcp6_sock___not_used #include "vmlinux.h" #undef bpf_iter_meta #undef bpf_iter__bpf_map @@ -14,6 +16,8 @@ #undef bpf_iter__netlink #undef bpf_iter__task #undef bpf_iter__task_file +#undef bpf_iter__tcp +#undef tcp6_sock struct bpf_iter_meta { struct seq_file *seq; @@ -47,3 +51,14 @@ struct bpf_iter__bpf_map { struct bpf_iter_meta *meta; struct bpf_map *map; } __attribute__((preserve_access_index)); + +struct bpf_iter__tcp { + struct bpf_iter_meta *meta; + struct sock_common *sk_common; + uid_t uid; +} __attribute__((preserve_access_index)); + +struct tcp6_sock { + struct tcp_sock tcp; + struct ipv6_pinfo inet6; +} __attribute__((preserve_access_index)); diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c b/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c new file mode 100644 index 000000000000..30fd587cb325 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c @@ -0,0 +1,234 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include "bpf_tracing_net.h" +#include +#include +#include + +char _license[] SEC("license") = "GPL"; + +static int hlist_unhashed_lockless(const struct hlist_node *h) +{ + return !(h->pprev); +} + +static int timer_pending(const struct timer_list * timer) +{ + return !hlist_unhashed_lockless(&timer->entry); +} + +extern unsigned CONFIG_HZ __kconfig; + +#define USER_HZ 100 +#define NSEC_PER_SEC 1000000000ULL +static clock_t jiffies_to_clock_t(unsigned long x) +{ + /* The implementation here tailored to a particular + * setting of USER_HZ. + */ + u64 tick_nsec = (NSEC_PER_SEC + CONFIG_HZ/2) / CONFIG_HZ; + u64 user_hz_nsec = NSEC_PER_SEC / USER_HZ; + + if ((tick_nsec % user_hz_nsec) == 0) { + if (CONFIG_HZ < USER_HZ) + return x * (USER_HZ / CONFIG_HZ); + else + return x / (CONFIG_HZ / USER_HZ); + } + return x * tick_nsec/user_hz_nsec; +} + +static clock_t jiffies_delta_to_clock_t(long delta) +{ + if (delta <= 0) + return 0; + + return jiffies_to_clock_t(delta); +} + +static long sock_i_ino(const struct sock *sk) +{ + const struct socket *sk_socket = sk->sk_socket; + const struct inode *inode; + unsigned long ino; + + if (!sk_socket) + return 0; + + inode = &container_of(sk_socket, struct socket_alloc, socket)->vfs_inode; + bpf_probe_read(&ino, sizeof(ino), &inode->i_ino); + return ino; +} + +static bool +inet_csk_in_pingpong_mode(const struct inet_connection_sock *icsk) +{ + return icsk->icsk_ack.pingpong >= TCP_PINGPONG_THRESH; +} + +static bool tcp_in_initial_slowstart(const struct tcp_sock *tcp) +{ + return tcp->snd_ssthresh >= TCP_INFINITE_SSTHRESH; +} + +static int dump_tcp_sock(struct seq_file *seq, struct tcp_sock *tp, + uid_t uid, __u32 seq_num) +{ + const struct inet_connection_sock *icsk; + const struct fastopen_queue *fastopenq; + const struct inet_sock *inet; + unsigned long timer_expires; + const struct sock *sp; + __u16 destp, srcp; + __be32 dest, src; + int timer_active; + int rx_queue; + int state; + + icsk = &tp->inet_conn; + inet = &icsk->icsk_inet; + sp = &inet->sk; + fastopenq = &icsk->icsk_accept_queue.fastopenq; + + dest = inet->inet_daddr; + src = inet->inet_rcv_saddr; + destp = bpf_ntohs(inet->inet_dport); + srcp = bpf_ntohs(inet->inet_sport); + + if (icsk->icsk_pending == ICSK_TIME_RETRANS || + icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT || + icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { + timer_active = 1; + timer_expires = icsk->icsk_timeout; + } else if (icsk->icsk_pending == ICSK_TIME_PROBE0) { + timer_active = 4; + timer_expires = icsk->icsk_timeout; + } else if (timer_pending(&sp->sk_timer)) { + timer_active = 2; + timer_expires = sp->sk_timer.expires; + } else { + timer_active = 0; + timer_expires = bpf_jiffies64(); + } + + state = sp->sk_state; + if (state == TCP_LISTEN) { + rx_queue = sp->sk_ack_backlog; + } else { + rx_queue = tp->rcv_nxt - tp->copied_seq; + if (rx_queue < 0) + rx_queue = 0; + } + + BPF_SEQ_PRINTF(seq, "%4d: %08X:%04X %08X:%04X ", + seq_num, src, srcp, destp, destp); + BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d ", + state, + tp->write_seq - tp->snd_una, rx_queue, + timer_active, + jiffies_delta_to_clock_t(timer_expires - bpf_jiffies64()), + icsk->icsk_retransmits, uid, + icsk->icsk_probes_out, + sock_i_ino(sp), + sp->sk_refcnt.refs.counter); + BPF_SEQ_PRINTF(seq, "%pK %lu %lu %u %u %d\n", + tp, + jiffies_to_clock_t(icsk->icsk_rto), + jiffies_to_clock_t(icsk->icsk_ack.ato), + (icsk->icsk_ack.quick << 1) | inet_csk_in_pingpong_mode(icsk), + tp->snd_cwnd, + state == TCP_LISTEN ? fastopenq->max_qlen + : (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh) + ); + + return 0; +} + +static int dump_tw_sock(struct seq_file *seq, struct tcp_timewait_sock *ttw, + uid_t uid, __u32 seq_num) +{ + struct inet_timewait_sock *tw = &ttw->tw_sk; + __u16 destp, srcp; + __be32 dest, src; + long delta; + + delta = tw->tw_timer.expires - bpf_jiffies64(); + dest = tw->tw_daddr; + src = tw->tw_rcv_saddr; + destp = bpf_ntohs(tw->tw_dport); + srcp = bpf_ntohs(tw->tw_sport); + + BPF_SEQ_PRINTF(seq, "%4d: %08X:%04X %08X:%04X ", + seq_num, src, srcp, dest, destp); + + BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK\n", + tw->tw_substate, 0, 0, + 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0, + tw->tw_refcnt.refs.counter, tw); + + return 0; +} + +static int dump_req_sock(struct seq_file *seq, struct tcp_request_sock *treq, + uid_t uid, __u32 seq_num) +{ + struct inet_request_sock *irsk = &treq->req; + struct request_sock *req = &irsk->req; + long ttd; + + ttd = req->rsk_timer.expires - bpf_jiffies64(); + + if (ttd < 0) + ttd = 0; + + BPF_SEQ_PRINTF(seq, "%4d: %08X:%04X %08X:%04X ", + seq_num, irsk->ir_loc_addr, + irsk->ir_num, irsk->ir_rmt_addr, + bpf_ntohs(irsk->ir_rmt_port)); + BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK\n", + TCP_SYN_RECV, 0, 0, 1, jiffies_to_clock_t(ttd), + req->num_timeout, uid, 0, 0, 0, req); + + return 0; +} + +SEC("iter/tcp") +int dump_tcp4(struct bpf_iter__tcp *ctx) +{ + struct sock_common *sk_common = ctx->sk_common; + struct seq_file *seq = ctx->meta->seq; + struct tcp_timewait_sock *tw; + struct tcp_request_sock *req; + struct tcp_sock *tp; + uid_t uid = ctx->uid; + __u32 seq_num; + + if (sk_common == (void *)0) + return 0; + + seq_num = ctx->meta->seq_num; + if (seq_num == 0) + BPF_SEQ_PRINTF(seq, " sl " + "local_address " + "rem_address " + "st tx_queue rx_queue tr tm->when retrnsmt" + " uid timeout inode\n"); + + if (sk_common->skc_family != AF_INET) + return 0; + + tp = bpf_skc_to_tcp_sock(sk_common); + if (tp) + return dump_tcp_sock(seq, tp, uid, seq_num); + + tw = bpf_skc_to_tcp_timewait_sock(sk_common); + if (tw) + return dump_tw_sock(seq, tw, uid, seq_num); + + req = bpf_skc_to_tcp_request_sock(sk_common); + if (req) + return dump_req_sock(seq, req, uid, seq_num); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c b/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c new file mode 100644 index 000000000000..10dec4392031 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c @@ -0,0 +1,250 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include "bpf_tracing_net.h" +#include +#include +#include + +char _license[] SEC("license") = "GPL"; + +static int hlist_unhashed_lockless(const struct hlist_node *h) +{ + return !(h->pprev); +} + +static int timer_pending(const struct timer_list * timer) +{ + return !hlist_unhashed_lockless(&timer->entry); +} + +extern unsigned CONFIG_HZ __kconfig; + +#define USER_HZ 100 +#define NSEC_PER_SEC 1000000000ULL +static clock_t jiffies_to_clock_t(unsigned long x) +{ + /* The implementation here tailored to a particular + * setting of USER_HZ. + */ + u64 tick_nsec = (NSEC_PER_SEC + CONFIG_HZ/2) / CONFIG_HZ; + u64 user_hz_nsec = NSEC_PER_SEC / USER_HZ; + + if ((tick_nsec % user_hz_nsec) == 0) { + if (CONFIG_HZ < USER_HZ) + return x * (USER_HZ / CONFIG_HZ); + else + return x / (CONFIG_HZ / USER_HZ); + } + return x * tick_nsec/user_hz_nsec; +} + +static clock_t jiffies_delta_to_clock_t(long delta) +{ + if (delta <= 0) + return 0; + + return jiffies_to_clock_t(delta); +} + +static long sock_i_ino(const struct sock *sk) +{ + const struct socket *sk_socket = sk->sk_socket; + const struct inode *inode; + unsigned long ino; + + if (!sk_socket) + return 0; + + inode = &container_of(sk_socket, struct socket_alloc, socket)->vfs_inode; + bpf_probe_read(&ino, sizeof(ino), &inode->i_ino); + return ino; +} + +static bool +inet_csk_in_pingpong_mode(const struct inet_connection_sock *icsk) +{ + return icsk->icsk_ack.pingpong >= TCP_PINGPONG_THRESH; +} + +static bool tcp_in_initial_slowstart(const struct tcp_sock *tcp) +{ + return tcp->snd_ssthresh >= TCP_INFINITE_SSTHRESH; +} + +static int dump_tcp6_sock(struct seq_file *seq, struct tcp6_sock *tp, + uid_t uid, __u32 seq_num) +{ + const struct inet_connection_sock *icsk; + const struct fastopen_queue *fastopenq; + const struct in6_addr *dest, *src; + const struct inet_sock *inet; + unsigned long timer_expires; + const struct sock *sp; + __u16 destp, srcp; + int timer_active; + int rx_queue; + int state; + + icsk = &tp->tcp.inet_conn; + inet = &icsk->icsk_inet; + sp = &inet->sk; + fastopenq = &icsk->icsk_accept_queue.fastopenq; + + dest = &sp->sk_v6_daddr; + src = &sp->sk_v6_rcv_saddr; + destp = bpf_ntohs(inet->inet_dport); + srcp = bpf_ntohs(inet->inet_sport); + + if (icsk->icsk_pending == ICSK_TIME_RETRANS || + icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT || + icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { + timer_active = 1; + timer_expires = icsk->icsk_timeout; + } else if (icsk->icsk_pending == ICSK_TIME_PROBE0) { + timer_active = 4; + timer_expires = icsk->icsk_timeout; + } else if (timer_pending(&sp->sk_timer)) { + timer_active = 2; + timer_expires = sp->sk_timer.expires; + } else { + timer_active = 0; + timer_expires = bpf_jiffies64(); + } + + state = sp->sk_state; + if (state == TCP_LISTEN) { + rx_queue = sp->sk_ack_backlog; + } else { + rx_queue = tp->tcp.rcv_nxt - tp->tcp.copied_seq; + if (rx_queue < 0) + rx_queue = 0; + } + + BPF_SEQ_PRINTF(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X ", + seq_num, + src->s6_addr32[0], src->s6_addr32[1], + src->s6_addr32[2], src->s6_addr32[3], srcp, + dest->s6_addr32[0], dest->s6_addr32[1], + dest->s6_addr32[2], dest->s6_addr32[3], destp); + BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d ", + state, + tp->tcp.write_seq - tp->tcp.snd_una, rx_queue, + timer_active, + jiffies_delta_to_clock_t(timer_expires - bpf_jiffies64()), + icsk->icsk_retransmits, uid, + icsk->icsk_probes_out, + sock_i_ino(sp), + sp->sk_refcnt.refs.counter); + BPF_SEQ_PRINTF(seq, "%pK %lu %lu %u %u %d\n", + tp, + jiffies_to_clock_t(icsk->icsk_rto), + jiffies_to_clock_t(icsk->icsk_ack.ato), + (icsk->icsk_ack.quick << 1) | inet_csk_in_pingpong_mode(icsk), + tp->tcp.snd_cwnd, + state == TCP_LISTEN ? fastopenq->max_qlen + : (tcp_in_initial_slowstart(&tp->tcp) ? -1 + : tp->tcp.snd_ssthresh) + ); + + return 0; +} + +static int dump_tw_sock(struct seq_file *seq, struct tcp_timewait_sock *ttw, + uid_t uid, __u32 seq_num) +{ + struct inet_timewait_sock *tw = &ttw->tw_sk; + const struct in6_addr *dest, *src; + __u16 destp, srcp; + long delta; + + delta = tw->tw_timer.expires - bpf_jiffies64(); + dest = &tw->tw_v6_daddr; + src = &tw->tw_v6_rcv_saddr; + destp = bpf_ntohs(tw->tw_dport); + srcp = bpf_ntohs(tw->tw_sport); + + BPF_SEQ_PRINTF(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X ", + seq_num, + src->s6_addr32[0], src->s6_addr32[1], + src->s6_addr32[2], src->s6_addr32[3], srcp, + dest->s6_addr32[0], dest->s6_addr32[1], + dest->s6_addr32[2], dest->s6_addr32[3], destp); + + BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK\n", + tw->tw_substate, 0, 0, + 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0, + tw->tw_refcnt.refs.counter, tw); + + return 0; +} + +static int dump_req_sock(struct seq_file *seq, struct tcp_request_sock *treq, + uid_t uid, __u32 seq_num) +{ + struct inet_request_sock *irsk = &treq->req; + struct request_sock *req = &irsk->req; + struct in6_addr *src, *dest; + long ttd; + + ttd = req->rsk_timer.expires - bpf_jiffies64(); + src = &irsk->ir_v6_loc_addr; + dest = &irsk->ir_v6_rmt_addr; + + if (ttd < 0) + ttd = 0; + + BPF_SEQ_PRINTF(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X ", + seq_num, + src->s6_addr32[0], src->s6_addr32[1], + src->s6_addr32[2], src->s6_addr32[3], + irsk->ir_num, + dest->s6_addr32[0], dest->s6_addr32[1], + dest->s6_addr32[2], dest->s6_addr32[3], + bpf_ntohs(irsk->ir_rmt_port)); + BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK\n", + TCP_SYN_RECV, 0, 0, 1, jiffies_to_clock_t(ttd), + req->num_timeout, uid, 0, 0, 0, req); + + return 0; +} + +SEC("iter/tcp") +int dump_tcp6(struct bpf_iter__tcp *ctx) +{ + struct sock_common *sk_common = ctx->sk_common; + struct seq_file *seq = ctx->meta->seq; + struct tcp_timewait_sock *tw; + struct tcp_request_sock *req; + struct tcp6_sock *tp; + uid_t uid = ctx->uid; + __u32 seq_num; + + if (sk_common == (void *)0) + return 0; + + seq_num = ctx->meta->seq_num; + if (seq_num == 0) + BPF_SEQ_PRINTF(seq, " sl " + "local_address " + "remote_address " + "st tx_queue rx_queue tr tm->when retrnsmt" + " uid timeout inode\n"); + + if (sk_common->skc_family != AF_INET6) + return 0; + + tp = bpf_skc_to_tcp6_sock(sk_common); + if (tp) + return dump_tcp6_sock(seq, tp, uid, seq_num); + + tw = bpf_skc_to_tcp_timewait_sock(sk_common); + if (tw) + return dump_tw_sock(seq, tw, uid, seq_num); + + req = bpf_skc_to_tcp_request_sock(sk_common); + if (req) + return dump_req_sock(seq, req, uid, seq_num); + + return 0; +} -- cgit v1.2.3 From ace6d6ec9e9e167047b6c8ca462a0830220640c2 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 23 Jun 2020 16:08:22 -0700 Subject: selftests/bpf: Implement sample udp/udp6 bpf_iter programs On my VM, I got identical results between /proc/net/udp[6] and the udp{4,6} bpf iterator. For udp6: $ cat /sys/fs/bpf/p1 sl local_address remote_address st tx_queue rx_queue tr tm->when retrnsmt uid timeout inode ref pointer drops 1405: 000080FE00000000FF7CC4D0D9EFE4FE:0222 00000000000000000000000000000000:0000 07 00000000:00000000 00:00000000 00000000 193 0 19183 2 0000000029eab111 0 $ cat /proc/net/udp6 sl local_address remote_address st tx_queue rx_queue tr tm->when retrnsmt uid timeout inode ref pointer drops 1405: 000080FE00000000FF7CC4D0D9EFE4FE:0222 00000000000000000000000000000000:0000 07 00000000:00000000 00:00000000 00000000 193 0 19183 2 0000000029eab111 0 For udp4: $ cat /sys/fs/bpf/p4 sl local_address rem_address st tx_queue rx_queue tr tm->when retrnsmt uid timeout inode ref pointer drops 2007: 00000000:1F90 00000000:0000 07 00000000:00000000 00:00000000 00000000 0 0 72540 2 000000004ede477a 0 $ cat /proc/net/udp sl local_address rem_address st tx_queue rx_queue tr tm->when retrnsmt uid timeout inode ref pointer drops 2007: 00000000:1F90 00000000:0000 07 00000000:00000000 00:00000000 00000000 0 0 72540 2 000000004ede477a 0 Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20200623230822.3989299-1-yhs@fb.com --- tools/testing/selftests/bpf/progs/bpf_iter.h | 16 +++++ tools/testing/selftests/bpf/progs/bpf_iter_udp4.c | 71 ++++++++++++++++++++ tools/testing/selftests/bpf/progs/bpf_iter_udp6.c | 79 +++++++++++++++++++++++ 3 files changed, 166 insertions(+) create mode 100644 tools/testing/selftests/bpf/progs/bpf_iter_udp4.c create mode 100644 tools/testing/selftests/bpf/progs/bpf_iter_udp6.c (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/progs/bpf_iter.h b/tools/testing/selftests/bpf/progs/bpf_iter.h index bde23e16e777..17db3bac518b 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter.h +++ b/tools/testing/selftests/bpf/progs/bpf_iter.h @@ -9,6 +9,8 @@ #define bpf_iter__task_file bpf_iter__task_file___not_used #define bpf_iter__tcp bpf_iter__tcp___not_used #define tcp6_sock tcp6_sock___not_used +#define bpf_iter__udp bpf_iter__udp___not_used +#define udp6_sock udp6_sock___not_used #include "vmlinux.h" #undef bpf_iter_meta #undef bpf_iter__bpf_map @@ -18,6 +20,8 @@ #undef bpf_iter__task_file #undef bpf_iter__tcp #undef tcp6_sock +#undef bpf_iter__udp +#undef udp6_sock struct bpf_iter_meta { struct seq_file *seq; @@ -62,3 +66,15 @@ struct tcp6_sock { struct tcp_sock tcp; struct ipv6_pinfo inet6; } __attribute__((preserve_access_index)); + +struct bpf_iter__udp { + struct bpf_iter_meta *meta; + struct udp_sock *udp_sk; + uid_t uid __attribute__((aligned(8))); + int bucket __attribute__((aligned(8))); +} __attribute__((preserve_access_index)); + +struct udp6_sock { + struct udp_sock udp; + struct ipv6_pinfo inet6; +} __attribute__((preserve_access_index)); diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c b/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c new file mode 100644 index 000000000000..7053784575e4 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include "bpf_tracing_net.h" +#include +#include +#include + +char _license[] SEC("license") = "GPL"; + +static long sock_i_ino(const struct sock *sk) +{ + const struct socket *sk_socket = sk->sk_socket; + const struct inode *inode; + unsigned long ino; + + if (!sk_socket) + return 0; + + inode = &container_of(sk_socket, struct socket_alloc, socket)->vfs_inode; + bpf_probe_read(&ino, sizeof(ino), &inode->i_ino); + return ino; +} + +SEC("iter/udp") +int dump_udp4(struct bpf_iter__udp *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct udp_sock *udp_sk = ctx->udp_sk; + struct inet_sock *inet; + __u16 srcp, destp; + __be32 dest, src; + __u32 seq_num; + int rqueue; + + if (udp_sk == (void *)0) + return 0; + + seq_num = ctx->meta->seq_num; + if (seq_num == 0) + BPF_SEQ_PRINTF(seq, + " sl local_address rem_address st tx_queue " + "rx_queue tr tm->when retrnsmt uid timeout " + "inode ref pointer drops\n"); + + /* filter out udp6 sockets */ + inet = &udp_sk->inet; + if (inet->sk.sk_family == AF_INET6) + return 0; + + inet = &udp_sk->inet; + dest = inet->inet_daddr; + src = inet->inet_rcv_saddr; + srcp = bpf_ntohs(inet->inet_sport); + destp = bpf_ntohs(inet->inet_dport); + rqueue = inet->sk.sk_rmem_alloc.counter - udp_sk->forward_deficit; + + BPF_SEQ_PRINTF(seq, "%5d: %08X:%04X %08X:%04X ", + ctx->bucket, src, srcp, dest, destp); + + BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %u\n", + inet->sk.sk_state, + inet->sk.sk_wmem_alloc.refs.counter - 1, + rqueue, + 0, 0L, 0, ctx->uid, 0, + sock_i_ino(&inet->sk), + inet->sk.sk_refcnt.refs.counter, udp_sk, + inet->sk.sk_drops.counter); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c b/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c new file mode 100644 index 000000000000..c1175a6ecf43 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c @@ -0,0 +1,79 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include "bpf_tracing_net.h" +#include +#include +#include + +char _license[] SEC("license") = "GPL"; + +#define IPV6_SEQ_DGRAM_HEADER \ + " sl " \ + "local_address " \ + "remote_address " \ + "st tx_queue rx_queue tr tm->when retrnsmt" \ + " uid timeout inode ref pointer drops\n" + +static long sock_i_ino(const struct sock *sk) +{ + const struct socket *sk_socket = sk->sk_socket; + const struct inode *inode; + unsigned long ino; + + if (!sk_socket) + return 0; + + inode = &container_of(sk_socket, struct socket_alloc, socket)->vfs_inode; + bpf_probe_read(&ino, sizeof(ino), &inode->i_ino); + return ino; +} + +SEC("iter/udp") +int dump_udp6(struct bpf_iter__udp *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct udp_sock *udp_sk = ctx->udp_sk; + const struct in6_addr *dest, *src; + struct udp6_sock *udp6_sk; + struct inet_sock *inet; + __u16 srcp, destp; + __u32 seq_num; + int rqueue; + + if (udp_sk == (void *)0) + return 0; + + seq_num = ctx->meta->seq_num; + if (seq_num == 0) + BPF_SEQ_PRINTF(seq, IPV6_SEQ_DGRAM_HEADER); + + udp6_sk = bpf_skc_to_udp6_sock(udp_sk); + if (udp6_sk == (void *)0) + return 0; + + inet = &udp_sk->inet; + srcp = bpf_ntohs(inet->inet_sport); + destp = bpf_ntohs(inet->inet_dport); + rqueue = inet->sk.sk_rmem_alloc.counter - udp_sk->forward_deficit; + dest = &inet->sk.sk_v6_daddr; + src = &inet->sk.sk_v6_rcv_saddr; + + BPF_SEQ_PRINTF(seq, "%5d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X ", + ctx->bucket, + src->s6_addr32[0], src->s6_addr32[1], + src->s6_addr32[2], src->s6_addr32[3], srcp, + dest->s6_addr32[0], dest->s6_addr32[1], + dest->s6_addr32[2], dest->s6_addr32[3], destp); + + BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %u\n", + inet->sk.sk_state, + inet->sk.sk_wmem_alloc.refs.counter - 1, + rqueue, + 0, 0L, 0, ctx->uid, 0, + sock_i_ino(&inet->sk), + inet->sk.sk_refcnt.refs.counter, udp_sk, + inet->sk.sk_drops.counter); + + return 0; +} -- cgit v1.2.3 From cfcd75f9bf12301dfdcfe9ff6dfb240997e7745f Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 23 Jun 2020 16:08:23 -0700 Subject: selftests/bpf: Add tcp/udp iterator programs to selftests Added tcp{4,6} and udp{4,6} bpf programs into test_progs selftest so that they at least can load successfully. $ ./test_progs -n 3 ... #3/7 tcp4:OK #3/8 tcp6:OK #3/9 udp4:OK #3/10 udp6:OK ... #3 bpf_iter:OK Summary: 1/16 PASSED, 0 SKIPPED, 0 FAILED Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20200623230823.3989372-1-yhs@fb.com --- tools/testing/selftests/bpf/prog_tests/bpf_iter.c | 68 +++++++++++++++++++++++ 1 file changed, 68 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index 87c29dde1cf9..1e2e0fced6e8 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -6,6 +6,10 @@ #include "bpf_iter_bpf_map.skel.h" #include "bpf_iter_task.skel.h" #include "bpf_iter_task_file.skel.h" +#include "bpf_iter_tcp4.skel.h" +#include "bpf_iter_tcp6.skel.h" +#include "bpf_iter_udp4.skel.h" +#include "bpf_iter_udp6.skel.h" #include "bpf_iter_test_kern1.skel.h" #include "bpf_iter_test_kern2.skel.h" #include "bpf_iter_test_kern3.skel.h" @@ -120,6 +124,62 @@ static void test_task_file(void) bpf_iter_task_file__destroy(skel); } +static void test_tcp4(void) +{ + struct bpf_iter_tcp4 *skel; + + skel = bpf_iter_tcp4__open_and_load(); + if (CHECK(!skel, "bpf_iter_tcp4__open_and_load", + "skeleton open_and_load failed\n")) + return; + + do_dummy_read(skel->progs.dump_tcp4); + + bpf_iter_tcp4__destroy(skel); +} + +static void test_tcp6(void) +{ + struct bpf_iter_tcp6 *skel; + + skel = bpf_iter_tcp6__open_and_load(); + if (CHECK(!skel, "bpf_iter_tcp6__open_and_load", + "skeleton open_and_load failed\n")) + return; + + do_dummy_read(skel->progs.dump_tcp6); + + bpf_iter_tcp6__destroy(skel); +} + +static void test_udp4(void) +{ + struct bpf_iter_udp4 *skel; + + skel = bpf_iter_udp4__open_and_load(); + if (CHECK(!skel, "bpf_iter_udp4__open_and_load", + "skeleton open_and_load failed\n")) + return; + + do_dummy_read(skel->progs.dump_udp4); + + bpf_iter_udp4__destroy(skel); +} + +static void test_udp6(void) +{ + struct bpf_iter_udp6 *skel; + + skel = bpf_iter_udp6__open_and_load(); + if (CHECK(!skel, "bpf_iter_udp6__open_and_load", + "skeleton open_and_load failed\n")) + return; + + do_dummy_read(skel->progs.dump_udp6); + + bpf_iter_udp6__destroy(skel); +} + /* The expected string is less than 16 bytes */ static int do_read_with_fd(int iter_fd, const char *expected, bool read_one_char) @@ -394,6 +454,14 @@ void test_bpf_iter(void) test_task(); if (test__start_subtest("task_file")) test_task_file(); + if (test__start_subtest("tcp4")) + test_tcp4(); + if (test__start_subtest("tcp6")) + test_tcp6(); + if (test__start_subtest("udp4")) + test_udp4(); + if (test__start_subtest("udp6")) + test_udp6(); if (test__start_subtest("anon")) test_anon_iter(false); if (test__start_subtest("anon-read-one-char")) -- cgit v1.2.3 From 5712174c5c9e3d684ad05d4aaed1e14acda4bb74 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 25 Jun 2020 16:26:29 -0700 Subject: selftests/bpf: Test auto-load disabling logic for BPF programs Validate that BPF object with broken (in multiple ways) BPF program can still be successfully loaded, if that broken BPF program is disabled. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200625232629.3444003-3-andriin@fb.com --- tools/testing/selftests/bpf/prog_tests/autoload.c | 41 +++++++++++++++++++++++ tools/testing/selftests/bpf/progs/test_autoload.c | 40 ++++++++++++++++++++++ 2 files changed, 81 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/autoload.c create mode 100644 tools/testing/selftests/bpf/progs/test_autoload.c (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/autoload.c b/tools/testing/selftests/bpf/prog_tests/autoload.c new file mode 100644 index 000000000000..3693f7d133eb --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/autoload.c @@ -0,0 +1,41 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include +#include +#include "test_autoload.skel.h" + +void test_autoload(void) +{ + int duration = 0, err; + struct test_autoload* skel; + + skel = test_autoload__open_and_load(); + /* prog3 should be broken */ + if (CHECK(skel, "skel_open_and_load", "unexpected success\n")) + goto cleanup; + + skel = test_autoload__open(); + if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) + goto cleanup; + + /* don't load prog3 */ + bpf_program__set_autoload(skel->progs.prog3, false); + + err = test_autoload__load(skel); + if (CHECK(err, "skel_load", "failed to load skeleton: %d\n", err)) + goto cleanup; + + err = test_autoload__attach(skel); + if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) + goto cleanup; + + usleep(1); + + CHECK(!skel->bss->prog1_called, "prog1", "not called\n"); + CHECK(!skel->bss->prog2_called, "prog2", "not called\n"); + CHECK(skel->bss->prog3_called, "prog3", "called?!\n"); + +cleanup: + test_autoload__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/progs/test_autoload.c b/tools/testing/selftests/bpf/progs/test_autoload.c new file mode 100644 index 000000000000..62c8cdec6d5d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_autoload.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include "vmlinux.h" +#include +#include +#include + +bool prog1_called = false; +bool prog2_called = false; +bool prog3_called = false; + +SEC("raw_tp/sys_enter") +int prog1(const void *ctx) +{ + prog1_called = true; + return 0; +} + +SEC("raw_tp/sys_exit") +int prog2(const void *ctx) +{ + prog2_called = true; + return 0; +} + +struct fake_kernel_struct { + int whatever; +} __attribute__((preserve_access_index)); + +SEC("fentry/unexisting-kprobe-will-fail-if-loaded") +int prog3(const void *ctx) +{ + struct fake_kernel_struct *fake = (void *)ctx; + fake->whatever = 123; + prog3_called = true; + return 0; +} + +char _license[] SEC("license") = "GPL"; -- cgit v1.2.3 From 6cf0291f95172db68d8a283854389a1966e43c65 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Sat, 27 Jun 2020 01:45:29 +0300 Subject: selftests: forwarding: Add a RED test for SW datapath This test is inspired by the mlxsw RED selftest. It is much simpler to set up (also because there is no point in testing PRIO / RED encapsulation). It tests bare RED, ECN and ECN+nodrop modes of operation. On top of that it tests RED early_drop and mark qevents. Signed-off-by: Petr Machata Signed-off-by: David S. Miller --- tools/testing/selftests/net/forwarding/sch_red.sh | 492 ++++++++++++++++++++++ 1 file changed, 492 insertions(+) create mode 100755 tools/testing/selftests/net/forwarding/sch_red.sh (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/net/forwarding/sch_red.sh b/tools/testing/selftests/net/forwarding/sch_red.sh new file mode 100755 index 000000000000..e714bae473fb --- /dev/null +++ b/tools/testing/selftests/net/forwarding/sch_red.sh @@ -0,0 +1,492 @@ +# SPDX-License-Identifier: GPL-2.0 + +# This test sends one stream of traffic from H1 through a TBF shaper, to a RED +# within TBF shaper on $swp3. The two shapers have the same configuration, and +# thus the resulting stream should fill all available bandwidth on the latter +# shaper. A second stream is sent from H2 also via $swp3, and used to inject +# additional traffic. Since all available bandwidth is taken, this traffic has +# to go to backlog. +# +# +--------------------------+ +--------------------------+ +# | H1 | | H2 | +# | + $h1 | | + $h2 | +# | | 192.0.2.1/28 | | | 192.0.2.2/28 | +# | | TBF 10Mbps | | | | +# +-----|--------------------+ +-----|--------------------+ +# | | +# +-----|------------------------------------------------|--------------------+ +# | SW | | | +# | +--|------------------------------------------------|----------------+ | +# | | + $swp1 + $swp2 | | +# | | BR | | +# | | | | +# | | + $swp3 | | +# | | | TBF 10Mbps / RED | | +# | +--------------------------------|-----------------------------------+ | +# | | | +# +-----------------------------------|---------------------------------------+ +# | +# +-----|--------------------+ +# | H3 | | +# | + $h1 | +# | 192.0.2.3/28 | +# | | +# +--------------------------+ + +ALL_TESTS=" + ping_ipv4 + ecn_test + ecn_nodrop_test + red_test + red_qevent_test + ecn_qevent_test +" + +NUM_NETIFS=6 +CHECK_TC="yes" +source lib.sh + +BACKLOG=30000 +PKTSZ=1400 + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 + mtu_set $h1 10000 + tc qdisc replace dev $h1 root handle 1: tbf \ + rate 10Mbit burst 10K limit 1M +} + +h1_destroy() +{ + tc qdisc del dev $h1 root + mtu_restore $h1 + simple_if_fini $h1 192.0.2.1/28 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.2/28 + mtu_set $h2 10000 +} + +h2_destroy() +{ + mtu_restore $h2 + simple_if_fini $h2 192.0.2.2/28 +} + +h3_create() +{ + simple_if_init $h3 192.0.2.3/28 + mtu_set $h3 10000 +} + +h3_destroy() +{ + mtu_restore $h3 + simple_if_fini $h3 192.0.2.3/28 +} + +switch_create() +{ + ip link add dev br up type bridge + ip link set dev $swp1 up master br + ip link set dev $swp2 up master br + ip link set dev $swp3 up master br + + mtu_set $swp1 10000 + mtu_set $swp2 10000 + mtu_set $swp3 10000 + + tc qdisc replace dev $swp3 root handle 1: tbf \ + rate 10Mbit burst 10K limit 1M + ip link add name _drop_test up type dummy +} + +switch_destroy() +{ + ip link del dev _drop_test + tc qdisc del dev $swp3 root + + mtu_restore $h3 + mtu_restore $h2 + mtu_restore $h1 + + ip link set dev $swp3 down nomaster + ip link set dev $swp2 down nomaster + ip link set dev $swp1 down nomaster + ip link del dev br +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + h2=${NETIFS[p3]} + swp2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + h3_mac=$(mac_get $h3) + + vrf_prepare + + h1_create + h2_create + h3_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h3_destroy + h2_destroy + h1_destroy + + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1 192.0.2.3 " from host 1" + ping_test $h2 192.0.2.3 " from host 2" +} + +get_qdisc_backlog() +{ + qdisc_stats_get $swp3 11: .backlog +} + +get_nmarked() +{ + qdisc_stats_get $swp3 11: .marked +} + +get_qdisc_npackets() +{ + qdisc_stats_get $swp3 11: .packets +} + +get_nmirrored() +{ + link_stats_get _drop_test tx packets +} + +send_packets() +{ + local proto=$1; shift + local pkts=$1; shift + + $MZ $h2 -p $PKTSZ -a own -b $h3_mac -A 192.0.2.2 -B 192.0.2.3 -t $proto -q -c $pkts "$@" +} + +# This sends traffic in an attempt to build a backlog of $size. Returns 0 on +# success. After 10 failed attempts it bails out and returns 1. It dumps the +# backlog size to stdout. +build_backlog() +{ + local size=$1; shift + local proto=$1; shift + + local i=0 + + while :; do + local cur=$(get_qdisc_backlog) + local diff=$((size - cur)) + local pkts=$(((diff + PKTSZ - 1) / PKTSZ)) + + if ((cur >= size)); then + echo $cur + return 0 + elif ((i++ > 10)); then + echo $cur + return 1 + fi + + send_packets $proto $pkts "$@" + sleep 1 + done +} + +check_marking() +{ + local cond=$1; shift + + local npackets_0=$(get_qdisc_npackets) + local nmarked_0=$(get_nmarked) + sleep 5 + local npackets_1=$(get_qdisc_npackets) + local nmarked_1=$(get_nmarked) + + local nmarked_d=$((nmarked_1 - nmarked_0)) + local npackets_d=$((npackets_1 - npackets_0)) + local pct=$((100 * nmarked_d / npackets_d)) + + echo $pct + ((pct $cond)) +} + +check_mirroring() +{ + local cond=$1; shift + + local npackets_0=$(get_qdisc_npackets) + local nmirrored_0=$(get_nmirrored) + sleep 5 + local npackets_1=$(get_qdisc_npackets) + local nmirrored_1=$(get_nmirrored) + + local nmirrored_d=$((nmirrored_1 - nmirrored_0)) + local npackets_d=$((npackets_1 - npackets_0)) + local pct=$((100 * nmirrored_d / npackets_d)) + + echo $pct + ((pct $cond)) +} + +ecn_test_common() +{ + local name=$1; shift + local limit=$1; shift + local backlog + local pct + + # Build the below-the-limit backlog using UDP. We could use TCP just + # fine, but this way we get a proof that UDP is accepted when queue + # length is below the limit. The main stream is using TCP, and if the + # limit is misconfigured, we would see this traffic being ECN marked. + RET=0 + backlog=$(build_backlog $((2 * limit / 3)) udp) + check_err $? "Could not build the requested backlog" + pct=$(check_marking "== 0") + check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0." + log_test "$name backlog < limit" + + # Now push TCP, because non-TCP traffic would be early-dropped after the + # backlog crosses the limit, and we want to make sure that the backlog + # is above the limit. + RET=0 + backlog=$(build_backlog $((3 * limit / 2)) tcp tos=0x01) + check_err $? "Could not build the requested backlog" + pct=$(check_marking ">= 95") + check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected >= 95." + log_test "$name backlog > limit" +} + +do_ecn_test() +{ + local limit=$1; shift + local name=ECN + + $MZ $h1 -p $PKTSZ -A 192.0.2.1 -B 192.0.2.3 -c 0 \ + -a own -b $h3_mac -t tcp -q tos=0x01 & + sleep 1 + + ecn_test_common "$name" $limit + + # Up there we saw that UDP gets accepted when backlog is below the + # limit. Now that it is above, it should all get dropped, and backlog + # building should fail. + RET=0 + build_backlog $((2 * limit)) udp >/dev/null + check_fail $? "UDP traffic went into backlog instead of being early-dropped" + log_test "$name backlog > limit: UDP early-dropped" + + stop_traffic + sleep 1 +} + +do_ecn_nodrop_test() +{ + local limit=$1; shift + local name="ECN nodrop" + + $MZ $h1 -p $PKTSZ -A 192.0.2.1 -B 192.0.2.3 -c 0 \ + -a own -b $h3_mac -t tcp -q tos=0x01 & + sleep 1 + + ecn_test_common "$name" $limit + + # Up there we saw that UDP gets accepted when backlog is below the + # limit. Now that it is above, in nodrop mode, make sure it goes to + # backlog as well. + RET=0 + build_backlog $((2 * limit)) udp >/dev/null + check_err $? "UDP traffic was early-dropped instead of getting into backlog" + log_test "$name backlog > limit: UDP not dropped" + + stop_traffic + sleep 1 +} + +do_red_test() +{ + local limit=$1; shift + local backlog + local pct + + # Use ECN-capable TCP to verify there's no marking even though the queue + # is above limit. + $MZ $h1 -p $PKTSZ -A 192.0.2.1 -B 192.0.2.3 -c 0 \ + -a own -b $h3_mac -t tcp -q tos=0x01 & + + # Pushing below the queue limit should work. + RET=0 + backlog=$(build_backlog $((2 * limit / 3)) tcp tos=0x01) + check_err $? "Could not build the requested backlog" + pct=$(check_marking "== 0") + check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0." + log_test "RED backlog < limit" + + # Pushing above should not. + RET=0 + backlog=$(build_backlog $((3 * limit / 2)) tcp tos=0x01) + check_fail $? "Traffic went into backlog instead of being early-dropped" + pct=$(check_marking "== 0") + check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0." + log_test "RED backlog > limit" + + stop_traffic + sleep 1 +} + +do_red_qevent_test() +{ + local limit=$1; shift + local backlog + local base + local now + local pct + + RET=0 + + $MZ $h1 -p $PKTSZ -A 192.0.2.1 -B 192.0.2.3 -c 0 \ + -a own -b $h3_mac -t udp -q & + sleep 1 + + tc filter add block 10 pref 1234 handle 102 matchall skip_hw \ + action mirred egress mirror dev _drop_test + + # Push to the queue until it's at the limit. The configured limit is + # rounded by the qdisc, so this is the best we can do to get to the real + # limit. + build_backlog $((3 * limit / 2)) udp >/dev/null + + base=$(get_nmirrored) + send_packets udp 100 + sleep 1 + now=$(get_nmirrored) + ((now >= base + 100)) + check_err $? "Dropped packets not observed: 100 expected, $((now - base)) seen" + + tc filter del block 10 pref 1234 handle 102 matchall + + base=$(get_nmirrored) + send_packets udp 100 + sleep 1 + now=$(get_nmirrored) + ((now == base)) + check_err $? "Dropped packets still observed: 0 expected, $((now - base)) seen" + + log_test "RED early_dropped packets mirrored" + + stop_traffic + sleep 1 +} + +do_ecn_qevent_test() +{ + local limit=$1; shift + local name=ECN + + RET=0 + + $MZ $h1 -p $PKTSZ -A 192.0.2.1 -B 192.0.2.3 -c 0 \ + -a own -b $h3_mac -t tcp -q tos=0x01 & + sleep 1 + + tc filter add block 10 pref 1234 handle 102 matchall skip_hw \ + action mirred egress mirror dev _drop_test + + backlog=$(build_backlog $((2 * limit / 3)) tcp tos=0x01) + check_err $? "Could not build the requested backlog" + pct=$(check_mirroring "== 0") + check_err $? "backlog $backlog / $limit Got $pct% mirrored packets, expected == 0." + + backlog=$(build_backlog $((3 * limit / 2)) tcp tos=0x01) + check_err $? "Could not build the requested backlog" + pct=$(check_mirroring ">= 95") + check_err $? "backlog $backlog / $limit Got $pct% mirrored packets, expected >= 95." + + tc filter del block 10 pref 1234 handle 102 matchall + + log_test "ECN marked packets mirrored" + + stop_traffic + sleep 1 +} + +install_qdisc() +{ + local -a args=("$@") + + tc qdisc replace dev $swp3 parent 1:1 handle 11: red \ + limit 1M avpkt $PKTSZ probability 1 \ + min $BACKLOG max $((BACKLOG + 1)) burst 38 "${args[@]}" + sleep 1 +} + +uninstall_qdisc() +{ + tc qdisc del dev $swp3 parent 1:1 +} + +ecn_test() +{ + install_qdisc ecn + do_ecn_test $BACKLOG + uninstall_qdisc +} + +ecn_nodrop_test() +{ + install_qdisc ecn nodrop + do_ecn_nodrop_test $BACKLOG + uninstall_qdisc +} + +red_test() +{ + install_qdisc + do_red_test $BACKLOG + uninstall_qdisc +} + +red_qevent_test() +{ + install_qdisc qevent early_drop block 10 + do_red_qevent_test $BACKLOG + uninstall_qdisc +} + +ecn_qevent_test() +{ + install_qdisc ecn qevent mark block 10 + do_ecn_qevent_test $BACKLOG + uninstall_qdisc +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS -- cgit v1.2.3 From dd9e67ff8086adeaf257a17eee9ee73dcb2c1c13 Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Mon, 29 Jun 2020 23:46:19 +0300 Subject: selftests: forwarding: ethtool: Move different_speeds_get() to ethtool_lib Currently different_speeds_get() is used only by ethtool.sh tests. The function can be useful for another tests that check ethtool configurations. Move the function to ethtool_lib in order to allow other tests to use it. Signed-off-by: Amit Cohen Reviewed-by: Petr Machata Reviewed-by: Florian Fainelli Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- tools/testing/selftests/net/forwarding/ethtool.sh | 17 ----------------- tools/testing/selftests/net/forwarding/ethtool_lib.sh | 17 +++++++++++++++++ 2 files changed, 17 insertions(+), 17 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/net/forwarding/ethtool.sh b/tools/testing/selftests/net/forwarding/ethtool.sh index eb8e2a23bbb4..ea7a11a9f788 100755 --- a/tools/testing/selftests/net/forwarding/ethtool.sh +++ b/tools/testing/selftests/net/forwarding/ethtool.sh @@ -50,23 +50,6 @@ cleanup() h1_destroy } -different_speeds_get() -{ - local dev1=$1; shift - local dev2=$1; shift - local with_mode=$1; shift - local adver=$1; shift - - local -a speeds_arr - - speeds_arr=($(common_speeds_get $dev1 $dev2 $with_mode $adver)) - if [[ ${#speeds_arr[@]} < 2 ]]; then - check_err 1 "cannot check different speeds. There are not enough speeds" - fi - - echo ${speeds_arr[0]} ${speeds_arr[1]} -} - same_speeds_autoneg_off() { # Check that when each of the reported speeds is forced, the links come diff --git a/tools/testing/selftests/net/forwarding/ethtool_lib.sh b/tools/testing/selftests/net/forwarding/ethtool_lib.sh index 925d229a59d8..9188e624dec0 100644 --- a/tools/testing/selftests/net/forwarding/ethtool_lib.sh +++ b/tools/testing/selftests/net/forwarding/ethtool_lib.sh @@ -67,3 +67,20 @@ common_speeds_get() <(printf '%s\n' "${dev1_speeds[@]}" | sort -u) \ <(printf '%s\n' "${dev2_speeds[@]}" | sort -u) } + +different_speeds_get() +{ + local dev1=$1; shift + local dev2=$1; shift + local with_mode=$1; shift + local adver=$1; shift + + local -a speeds_arr + + speeds_arr=($(common_speeds_get $dev1 $dev2 $with_mode $adver)) + if [[ ${#speeds_arr[@]} < 2 ]]; then + check_err 1 "cannot check different speeds. There are not enough speeds" + fi + + echo ${speeds_arr[0]} ${speeds_arr[1]} +} -- cgit v1.2.3 From 0433045c27bf9ae71e1c0300c278582407dd0e0b Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Mon, 29 Jun 2020 23:46:20 +0300 Subject: selftests: forwarding: forwarding.config.sample: Add port with no cable connected Add NETIF_NO_CABLE port to tests topology. The port can also be declared as an environment variable and tests can be run like that: NETIF_NO_CABLE=eth9 ./test.sh eth{1..8} The NETIF_NO_CABLE port will be used by ethtool_extended_state test. Signed-off-by: Amit Cohen Reviewed-by: Petr Machata Reviewed-by: Florian Fainelli Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- tools/testing/selftests/net/forwarding/forwarding.config.sample | 3 +++ 1 file changed, 3 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/net/forwarding/forwarding.config.sample b/tools/testing/selftests/net/forwarding/forwarding.config.sample index e2adb533c8fc..b802c14d2950 100644 --- a/tools/testing/selftests/net/forwarding/forwarding.config.sample +++ b/tools/testing/selftests/net/forwarding/forwarding.config.sample @@ -14,6 +14,9 @@ NETIFS[p6]=veth5 NETIFS[p7]=veth6 NETIFS[p8]=veth7 +# Port that does not have a cable connected. +NETIF_NO_CABLE=eth8 + ############################################################################## # Defines -- cgit v1.2.3 From 7d10bcce98cd44ea7c040380397114e0ac94422f Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Mon, 29 Jun 2020 23:46:21 +0300 Subject: selftests: forwarding: Add tests for ethtool extended state Add tests to check ethtool report about extended state. The tests configure several states and verify that the correct extended state is reported by ethtool. Check extended state with substate (Autoneg) and extended state without substate (No cable). Signed-off-by: Amit Cohen Reviewed-by: Petr Machata Reviewed-by: Florian Fainelli Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- .../net/forwarding/ethtool_extended_state.sh | 102 +++++++++++++++++++++ 1 file changed, 102 insertions(+) create mode 100755 tools/testing/selftests/net/forwarding/ethtool_extended_state.sh (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh b/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh new file mode 100755 index 000000000000..4b42dfd4efd1 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh @@ -0,0 +1,102 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ALL_TESTS=" + autoneg + autoneg_force_mode + no_cable +" + +NUM_NETIFS=2 +source lib.sh +source ethtool_lib.sh + +setup_prepare() +{ + swp1=${NETIFS[p1]} + swp2=${NETIFS[p2]} + swp3=$NETIF_NO_CABLE +} + +ethtool_extended_state_check() +{ + local dev=$1; shift + local expected_ext_state=$1; shift + local expected_ext_substate=${1:-""}; shift + + local ext_state=$(ethtool $dev | grep "Link detected" \ + | cut -d "(" -f2 | cut -d ")" -f1) + local ext_substate=$(echo $ext_state | cut -sd "," -f2 \ + | sed -e 's/^[[:space:]]*//') + ext_state=$(echo $ext_state | cut -d "," -f1) + + [[ $ext_state == $expected_ext_state ]] + check_err $? "Expected \"$expected_ext_state\", got \"$ext_state\"" + + [[ $ext_substate == $expected_ext_substate ]] + check_err $? "Expected \"$expected_ext_substate\", got \"$ext_substate\"" +} + +autoneg() +{ + RET=0 + + ip link set dev $swp1 up + + sleep 4 + ethtool_extended_state_check $swp1 "Autoneg" "No partner detected" + + log_test "Autoneg, No partner detected" + + ip link set dev $swp1 down +} + +autoneg_force_mode() +{ + RET=0 + + ip link set dev $swp1 up + ip link set dev $swp2 up + + local -a speeds_arr=($(different_speeds_get $swp1 $swp2 0 0)) + local speed1=${speeds_arr[0]} + local speed2=${speeds_arr[1]} + + ethtool_set $swp1 speed $speed1 autoneg off + ethtool_set $swp2 speed $speed2 autoneg off + + sleep 4 + ethtool_extended_state_check $swp1 "Autoneg" \ + "No partner detected during force mode" + + ethtool_extended_state_check $swp2 "Autoneg" \ + "No partner detected during force mode" + + log_test "Autoneg, No partner detected during force mode" + + ethtool -s $swp2 autoneg on + ethtool -s $swp1 autoneg on + + ip link set dev $swp2 down + ip link set dev $swp1 down +} + +no_cable() +{ + RET=0 + + ip link set dev $swp3 up + + sleep 1 + ethtool_extended_state_check $swp3 "No cable" + + log_test "No cable" + + ip link set dev $swp3 down +} + +setup_prepare + +tests_run + +exit $EXIT_STATUS -- cgit v1.2.3 From ca4db6389d611eee2eb7c1dfe710b62d8ea06772 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 29 Jun 2020 17:47:59 -0700 Subject: selftests/bpf: Allow substituting custom vmlinux.h for selftests build Similarly to bpftool Makefile, allow to specify custom location of vmlinux.h to be used during the build. This allows simpler testing setups with checked-in pre-generated vmlinux.h. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20200630004759.521530-2-andriin@fb.com --- tools/testing/selftests/bpf/Makefile | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 22aaec74ea0a..1f9c696b3edf 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -134,12 +134,12 @@ $(OUTPUT)/test_stub.o: test_stub.c $(BPFOBJ) $(call msg,CC,,$@) $(CC) -c $(CFLAGS) -o $@ $< -VMLINUX_BTF_PATHS := $(if $(O),$(O)/vmlinux) \ +VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \ $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \ ../../../../vmlinux \ /sys/kernel/btf/vmlinux \ /boot/vmlinux-$(shell uname -r) -VMLINUX_BTF := $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS)))) +VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS)))) $(OUTPUT)/runqslower: $(BPFOBJ) $(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/runqslower \ @@ -182,8 +182,13 @@ $(BUILD_DIR)/libbpf $(BUILD_DIR)/bpftool $(INCLUDE_DIR): mkdir -p $@ $(INCLUDE_DIR)/vmlinux.h: $(VMLINUX_BTF) | $(BPFTOOL) $(INCLUDE_DIR) +ifeq ($(VMLINUX_H),) $(call msg,GEN,,$@) $(BPFTOOL) btf dump file $(VMLINUX_BTF) format c > $@ +else + $(call msg,CP,,$@) + cp "$(VMLINUX_H)" $@ +endif # Get Clang's default includes on this system, as opposed to those seen by # '-target bpf'. This fixes "missing" files on some architectures/distros, -- cgit v1.2.3 From 8c18311067d0f0d5f332b9e1f3859eb15e23332d Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 30 Jun 2020 08:21:25 -0700 Subject: selftests/bpf: Add byte swapping selftest Add simple selftest validating byte swap built-ins and compile-time macros. Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20200630152125.3631920-3-andriin@fb.com --- tools/testing/selftests/bpf/prog_tests/endian.c | 53 +++++++++++++++++++++++++ tools/testing/selftests/bpf/progs/test_endian.c | 37 +++++++++++++++++ 2 files changed, 90 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/endian.c create mode 100644 tools/testing/selftests/bpf/progs/test_endian.c (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/endian.c b/tools/testing/selftests/bpf/prog_tests/endian.c new file mode 100644 index 000000000000..1a11612ace6c --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/endian.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include +#include "test_endian.skel.h" + +static int duration; + +#define IN16 0x1234 +#define IN32 0x12345678U +#define IN64 0x123456789abcdef0ULL + +#define OUT16 0x3412 +#define OUT32 0x78563412U +#define OUT64 0xf0debc9a78563412ULL + +void test_endian(void) +{ + struct test_endian* skel; + struct test_endian__bss *bss; + int err; + + skel = test_endian__open_and_load(); + if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) + return; + bss = skel->bss; + + bss->in16 = IN16; + bss->in32 = IN32; + bss->in64 = IN64; + + err = test_endian__attach(skel); + if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) + goto cleanup; + + usleep(1); + + CHECK(bss->out16 != OUT16, "out16", "got 0x%llx != exp 0x%llx\n", + (__u64)bss->out16, (__u64)OUT16); + CHECK(bss->out32 != OUT32, "out32", "got 0x%llx != exp 0x%llx\n", + (__u64)bss->out32, (__u64)OUT32); + CHECK(bss->out64 != OUT64, "out16", "got 0x%llx != exp 0x%llx\n", + (__u64)bss->out64, (__u64)OUT64); + + CHECK(bss->const16 != OUT16, "const16", "got 0x%llx != exp 0x%llx\n", + (__u64)bss->const16, (__u64)OUT16); + CHECK(bss->const32 != OUT32, "const32", "got 0x%llx != exp 0x%llx\n", + (__u64)bss->const32, (__u64)OUT32); + CHECK(bss->const64 != OUT64, "const64", "got 0x%llx != exp 0x%llx\n", + (__u64)bss->const64, (__u64)OUT64); +cleanup: + test_endian__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/progs/test_endian.c b/tools/testing/selftests/bpf/progs/test_endian.c new file mode 100644 index 000000000000..ddb687c5d125 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_endian.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include "vmlinux.h" +#include +#include + +#define IN16 0x1234 +#define IN32 0x12345678U +#define IN64 0x123456789abcdef0ULL + +__u16 in16 = 0; +__u32 in32 = 0; +__u64 in64 = 0; + +__u16 out16 = 0; +__u32 out32 = 0; +__u64 out64 = 0; + +__u16 const16 = 0; +__u32 const32 = 0; +__u64 const64 = 0; + +SEC("raw_tp/sys_enter") +int sys_enter(const void *ctx) +{ + out16 = __builtin_bswap16(in16); + out32 = __builtin_bswap32(in32); + out64 = __builtin_bswap64(in64); + const16 = ___bpf_swab16(IN16); + const32 = ___bpf_swab32(IN32); + const64 = ___bpf_swab64(IN64); + + return 0; +} + +char _license[] SEC("license") = "GPL"; -- cgit v1.2.3 From c7568114bc56cf3ec0bd9eb117bbe7cad3d30e11 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 29 Jun 2020 23:28:46 -0700 Subject: selftests/bpf: Add bpf_iter test with bpf_get_task_stack() The new test is similar to other bpf_iter tests. It dumps all /proc//stack to a seq_file. Here is some example output: pid: 2873 num_entries: 3 [<0>] worker_thread+0xc6/0x380 [<0>] kthread+0x135/0x150 [<0>] ret_from_fork+0x22/0x30 pid: 2874 num_entries: 9 [<0>] __bpf_get_stack+0x15e/0x250 [<0>] bpf_prog_22a400774977bb30_dump_task_stack+0x4a/0xb3c [<0>] bpf_iter_run_prog+0x81/0x170 [<0>] __task_seq_show+0x58/0x80 [<0>] bpf_seq_read+0x1c3/0x3b0 [<0>] vfs_read+0x9e/0x170 [<0>] ksys_read+0xa7/0xe0 [<0>] do_syscall_64+0x4c/0xa0 [<0>] entry_SYSCALL_64_after_hwframe+0x44/0xa9 Note: bpf_iter test as-is doesn't print the contents of the seq_file. To see the example above, it is necessary to add printf() to do_dummy_read. Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20200630062846.664389-5-songliubraving@fb.com --- tools/testing/selftests/bpf/prog_tests/bpf_iter.c | 17 ++++++++++ .../selftests/bpf/progs/bpf_iter_task_stack.c | 37 ++++++++++++++++++++++ 2 files changed, 54 insertions(+) create mode 100644 tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index 1e2e0fced6e8..fed42755416d 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -5,6 +5,7 @@ #include "bpf_iter_netlink.skel.h" #include "bpf_iter_bpf_map.skel.h" #include "bpf_iter_task.skel.h" +#include "bpf_iter_task_stack.skel.h" #include "bpf_iter_task_file.skel.h" #include "bpf_iter_tcp4.skel.h" #include "bpf_iter_tcp6.skel.h" @@ -110,6 +111,20 @@ static void test_task(void) bpf_iter_task__destroy(skel); } +static void test_task_stack(void) +{ + struct bpf_iter_task_stack *skel; + + skel = bpf_iter_task_stack__open_and_load(); + if (CHECK(!skel, "bpf_iter_task_stack__open_and_load", + "skeleton open_and_load failed\n")) + return; + + do_dummy_read(skel->progs.dump_task_stack); + + bpf_iter_task_stack__destroy(skel); +} + static void test_task_file(void) { struct bpf_iter_task_file *skel; @@ -452,6 +467,8 @@ void test_bpf_iter(void) test_bpf_map(); if (test__start_subtest("task")) test_task(); + if (test__start_subtest("task_stack")) + test_task_stack(); if (test__start_subtest("task_file")) test_task_file(); if (test__start_subtest("tcp4")) diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c new file mode 100644 index 000000000000..e40d32a2ed93 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include +#include + +char _license[] SEC("license") = "GPL"; + +#define MAX_STACK_TRACE_DEPTH 64 +unsigned long entries[MAX_STACK_TRACE_DEPTH]; +#define SIZE_OF_ULONG (sizeof(unsigned long)) + +SEC("iter/task") +int dump_task_stack(struct bpf_iter__task *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct task_struct *task = ctx->task; + long i, retlen; + + if (task == (void *)0) + return 0; + + retlen = bpf_get_task_stack(task, entries, + MAX_STACK_TRACE_DEPTH * SIZE_OF_ULONG, 0); + if (retlen < 0) + return 0; + + BPF_SEQ_PRINTF(seq, "pid: %8u num_entries: %8u\n", task->pid, + retlen / SIZE_OF_ULONG); + for (i = 0; i < MAX_STACK_TRACE_DEPTH; i++) { + if (retlen > i * SIZE_OF_ULONG) + BPF_SEQ_PRINTF(seq, "[<0>] %pB\n", (void *)entries[i]); + } + BPF_SEQ_PRINTF(seq, "\n"); + + return 0; +} -- cgit v1.2.3 From 8d821b5db70723d27ee749b4870de90760606918 Mon Sep 17 00:00:00 2001 From: Hao Luo Date: Wed, 1 Jul 2020 10:53:15 -0700 Subject: selftests/bpf: Switch test_vmlinux to use hrtimer_range_start_ns. The test_vmlinux test uses hrtimer_nanosleep as hook to test tracing programs. But in a kernel built by clang, which performs more aggresive inlining, that function gets inlined into its caller SyS_nanosleep. Therefore, even though fentry and kprobe do hook on the function, they aren't triggered by the call to nanosleep in the test. A possible fix is switching to use a function that is less likely to be inlined, such as hrtimer_range_start_ns. The EXPORT_SYMBOL functions shouldn't be inlined based on the description of [1], therefore safe to use for this test. Also the arguments of this function include the duration of sleep, therefore suitable for test verification. [1] af3b56289be1 time: don't inline EXPORT_SYMBOL functions Tested: In a clang build kernel, before this change, the test fails: test_vmlinux:PASS:skel_open 0 nsec test_vmlinux:PASS:skel_attach 0 nsec test_vmlinux:PASS:tp 0 nsec test_vmlinux:PASS:raw_tp 0 nsec test_vmlinux:PASS:tp_btf 0 nsec test_vmlinux:FAIL:kprobe not called test_vmlinux:FAIL:fentry not called After switching to hrtimer_range_start_ns, the test passes: test_vmlinux:PASS:skel_open 0 nsec test_vmlinux:PASS:skel_attach 0 nsec test_vmlinux:PASS:tp 0 nsec test_vmlinux:PASS:raw_tp 0 nsec test_vmlinux:PASS:tp_btf 0 nsec test_vmlinux:PASS:kprobe 0 nsec test_vmlinux:PASS:fentry 0 nsec Signed-off-by: Hao Luo Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20200701175315.1161242-1-haoluo@google.com --- tools/testing/selftests/bpf/progs/test_vmlinux.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/progs/test_vmlinux.c b/tools/testing/selftests/bpf/progs/test_vmlinux.c index 5611b564d3b1..29fa09d6a6c6 100644 --- a/tools/testing/selftests/bpf/progs/test_vmlinux.c +++ b/tools/testing/selftests/bpf/progs/test_vmlinux.c @@ -63,20 +63,20 @@ int BPF_PROG(handle__tp_btf, struct pt_regs *regs, long id) return 0; } -SEC("kprobe/hrtimer_nanosleep") -int BPF_KPROBE(handle__kprobe, - ktime_t rqtp, enum hrtimer_mode mode, clockid_t clockid) +SEC("kprobe/hrtimer_start_range_ns") +int BPF_KPROBE(handle__kprobe, struct hrtimer *timer, ktime_t tim, u64 delta_ns, + const enum hrtimer_mode mode) { - if (rqtp == MY_TV_NSEC) + if (tim == MY_TV_NSEC) kprobe_called = true; return 0; } -SEC("fentry/hrtimer_nanosleep") -int BPF_PROG(handle__fentry, - ktime_t rqtp, enum hrtimer_mode mode, clockid_t clockid) +SEC("fentry/hrtimer_start_range_ns") +int BPF_PROG(handle__fentry, struct hrtimer *timer, ktime_t tim, u64 delta_ns, + const enum hrtimer_mode mode) { - if (rqtp == MY_TV_NSEC) + if (tim == MY_TV_NSEC) fentry_called = true; return 0; } -- cgit v1.2.3 From 6c92bd5cd4650c39dd929565ee172984c680fead Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Wed, 1 Jul 2020 23:44:07 +0200 Subject: selftests/bpf: Test_progs indicate to shell on non-actions When a user selects a non-existing test the summary is printed with indication 0 for all info types, and shell "success" (EXIT_SUCCESS) is indicated. This can be understood by a human end-user, but for shell scripting is it useful to indicate a shell failure (EXIT_FAILURE). Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/159363984736.930467.17956007131403952343.stgit@firesoul --- tools/testing/selftests/bpf/test_progs.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index 54fa5fa688ce..da70a4f72f54 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -687,5 +687,8 @@ int main(int argc, char **argv) free_str_set(&env.subtest_selector.whitelist); free(env.subtest_selector.num_set); + if (env.succ_cnt + env.fail_cnt + env.skip_cnt == 0) + return EXIT_FAILURE; + return env.fail_cnt ? EXIT_FAILURE : EXIT_SUCCESS; } -- cgit v1.2.3 From 643e7233aa948901dce81d4573c91ed99fdd272e Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Wed, 1 Jul 2020 23:44:12 +0200 Subject: selftests/bpf: Test_progs option for getting number of tests It can be practial to get the number of tests that test_progs contain. This could for example be used to create a shell for-loop construct that runs the individual tests. Like: for N in $(seq 1 $(./test_progs -c)); do ./test_progs -n $N 2>&1 > result_test_${N}.log & done ; wait V2: Add the ability to return the count for the selected tests. This is useful for getting a count e.g. after excluding some tests with option -b. The current beakers test script like to report the max test count upfront. Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/159363985244.930467.12617117873058936829.stgit@firesoul --- tools/testing/selftests/bpf/test_progs.c | 18 ++++++++++++++++++ tools/testing/selftests/bpf/test_progs.h | 1 + 2 files changed, 19 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index da70a4f72f54..a5dba14b2025 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -366,6 +366,7 @@ enum ARG_KEYS { ARG_TEST_NAME_BLACKLIST = 'b', ARG_VERIFIER_STATS = 's', ARG_VERBOSE = 'v', + ARG_GET_TEST_CNT = 'c', }; static const struct argp_option opts[] = { @@ -379,6 +380,8 @@ static const struct argp_option opts[] = { "Output verifier statistics", }, { "verbose", ARG_VERBOSE, "LEVEL", OPTION_ARG_OPTIONAL, "Verbose output (use -vv or -vvv for progressively verbose output)" }, + { "count", ARG_GET_TEST_CNT, NULL, 0, + "Get number of selected top-level tests " }, {}, }; @@ -511,6 +514,9 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state) } } break; + case ARG_GET_TEST_CNT: + env->get_test_cnt = true; + break; case ARGP_KEY_ARG: argp_usage(state); break; @@ -654,6 +660,11 @@ int main(int argc, char **argv) test->test_num, test->test_name)) continue; + if (env.get_test_cnt) { + env.succ_cnt++; + continue; + } + test->run_test(); /* ensure last sub-test is finalized properly */ if (test->subtest_name) @@ -677,9 +688,16 @@ int main(int argc, char **argv) cleanup_cgroup_environment(); } stdio_restore(); + + if (env.get_test_cnt) { + printf("%d\n", env.succ_cnt); + goto out; + } + fprintf(stdout, "Summary: %d/%d PASSED, %d SKIPPED, %d FAILED\n", env.succ_cnt, env.sub_succ_cnt, env.skip_cnt, env.fail_cnt); +out: free_str_set(&env.test_selector.blacklist); free_str_set(&env.test_selector.whitelist); free(env.test_selector.num_set); diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index f4503c926aca..0030584619c3 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -66,6 +66,7 @@ struct test_env { enum verbosity verbosity; bool jit_enabled; + bool get_test_cnt; struct prog_test_def *test; FILE *stdout; -- cgit v1.2.3 From c1f1f3656eee3a59a40e1805699041ec1c14ab83 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Wed, 1 Jul 2020 23:44:17 +0200 Subject: selftests/bpf: Test_progs option for listing test names The program test_progs have some very useful ability to specify a list of test name substrings for selecting which tests to run. This patch add the ability to list the selected test names without running them. This is practical for seeing which tests gets selected with given select arguments (which can also contain a exclude list via --name-blacklist). This output can also be used by shell-scripts in a for-loop: for N in $(./test_progs --list -t xdp); do \ ./test_progs -t $N 2>&1 > result_test_${N}.log & \ done ; wait This features can also be used for looking up a test number and returning a testname. If the selection was empty then a shell EXIT_FAILURE is returned. This is useful for scripting. e.g. like this: n=1; while [ $(./test_progs --list -n $n) ] ; do \ ./test_progs -n $n ; n=$(( n+1 )); \ done Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/159363985751.930467.9610992940793316982.stgit@firesoul --- tools/testing/selftests/bpf/test_progs.c | 15 +++++++++++++++ tools/testing/selftests/bpf/test_progs.h | 1 + 2 files changed, 16 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index a5dba14b2025..ef05d2f0e7bb 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -367,6 +367,7 @@ enum ARG_KEYS { ARG_VERIFIER_STATS = 's', ARG_VERBOSE = 'v', ARG_GET_TEST_CNT = 'c', + ARG_LIST_TEST_NAMES = 'l', }; static const struct argp_option opts[] = { @@ -382,6 +383,8 @@ static const struct argp_option opts[] = { "Verbose output (use -vv or -vvv for progressively verbose output)" }, { "count", ARG_GET_TEST_CNT, NULL, 0, "Get number of selected top-level tests " }, + { "list", ARG_LIST_TEST_NAMES, NULL, 0, + "List test names that would run (without running them) " }, {}, }; @@ -517,6 +520,9 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state) case ARG_GET_TEST_CNT: env->get_test_cnt = true; break; + case ARG_LIST_TEST_NAMES: + env->list_test_names = true; + break; case ARGP_KEY_ARG: argp_usage(state); break; @@ -665,6 +671,12 @@ int main(int argc, char **argv) continue; } + if (env.list_test_names) { + fprintf(env.stdout, "%s\n", test->test_name); + env.succ_cnt++; + continue; + } + test->run_test(); /* ensure last sub-test is finalized properly */ if (test->subtest_name) @@ -694,6 +706,9 @@ int main(int argc, char **argv) goto out; } + if (env.list_test_names) + goto out; + fprintf(stdout, "Summary: %d/%d PASSED, %d SKIPPED, %d FAILED\n", env.succ_cnt, env.sub_succ_cnt, env.skip_cnt, env.fail_cnt); diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index 0030584619c3..ec31f382e7fd 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -67,6 +67,7 @@ struct test_env { bool jit_enabled; bool get_test_cnt; + bool list_test_names; struct prog_test_def *test; FILE *stdout; -- cgit v1.2.3 From 767659f65000e6a19fee3b9bf6cda2839968329a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 30 Jun 2020 21:24:44 +0200 Subject: selftests: mptcp: add option to specify size of file to transfer The script generates two random files that are then sent via tcp and mptcp connections. In order to compare throughput over consecutive runs add an option to provide the file size on the command line: "-f 128000". Also add an option, -t, to enable tcp tests. This is useful to compare throughput of mptcp connections and tcp connections. Example: run tests with a 4mb file size, 300ms delay 0.01% loss, default gso/tso/gro settings and with large write/blocking io: mptcp_connect.sh -t -f $((4 * 1024 * 1024)) -d 300 -l 0.01% -r 0 -e "" -m mmap Signed-off-by: Florian Westphal Reviewed-by: Matthieu Baerts Signed-off-by: David S. Miller --- tools/testing/selftests/net/mptcp/mptcp_connect.sh | 52 ++++++++++++++++------ 1 file changed, 39 insertions(+), 13 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index acf02e156d20..8f7145c413b9 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -3,7 +3,7 @@ time_start=$(date +%s) -optstring="S:R:d:e:l:r:h4cm:" +optstring="S:R:d:e:l:r:h4cm:f:t" ret=0 sin="" sout="" @@ -21,6 +21,8 @@ testmode="" sndbuf=0 rcvbuf=0 options_log=true +do_tcp=0 +filesize=0 if [ $tc_loss -eq 100 ];then tc_loss=1% @@ -40,9 +42,11 @@ usage() { echo -e "\t-e: ethtool features to disable, e.g.: \"-e tso -e gso\" (default: randomly disable any of tso/gso/gro)" echo -e "\t-4: IPv4 only: disable IPv6 tests (default: test both IPv4 and IPv6)" echo -e "\t-c: capture packets for each test using tcpdump (default: no capture)" + echo -e "\t-f: size of file to transfer in bytes (default random)" echo -e "\t-S: set sndbuf value (default: use kernel default)" echo -e "\t-R: set rcvbuf value (default: use kernel default)" echo -e "\t-m: test mode (poll, sendfile; default: poll)" + echo -e "\t-t: also run tests with TCP (use twice to non-fallback tcp)" } while getopts "$optstring" option;do @@ -94,6 +98,12 @@ while getopts "$optstring" option;do "m") testmode="$OPTARG" ;; + "f") + filesize="$OPTARG" + ;; + "t") + do_tcp=$((do_tcp+1)) + ;; "?") usage $0 exit 1 @@ -449,20 +459,25 @@ make_file() { local name=$1 local who=$2 + local SIZE=$filesize + local ksize + local rem - local SIZE TSIZE - SIZE=$((RANDOM % (1024 * 8))) - TSIZE=$((SIZE * 1024)) + if [ $SIZE -eq 0 ]; then + local MAXSIZE=$((1024 * 1024 * 8)) + local MINSIZE=$((1024 * 256)) - dd if=/dev/urandom of="$name" bs=1024 count=$SIZE 2> /dev/null + SIZE=$(((RANDOM * RANDOM + MINSIZE) % MAXSIZE)) + fi - SIZE=$((RANDOM % 1024)) - SIZE=$((SIZE + 128)) - TSIZE=$((TSIZE + SIZE)) - dd if=/dev/urandom conv=notrunc of="$name" bs=1 count=$SIZE 2> /dev/null + ksize=$((SIZE / 1024)) + rem=$((SIZE - (ksize * 1024))) + + dd if=/dev/urandom of="$name" bs=1024 count=$ksize 2> /dev/null + dd if=/dev/urandom conv=notrunc of="$name" bs=1 count=$rem 2> /dev/null echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name" - echo "Created $name (size $TSIZE) containing data sent by $who" + echo "Created $name (size $(du -b "$name")) containing data sent by $who" } run_tests_lo() @@ -497,9 +512,11 @@ run_tests_lo() return 1 fi - # don't bother testing fallback tcp except for loopback case. - if [ ${listener_ns} != ${connector_ns} ]; then - return 0 + if [ $do_tcp -eq 0 ]; then + # don't bother testing fallback tcp except for loopback case. + if [ ${listener_ns} != ${connector_ns} ]; then + return 0 + fi fi do_transfer ${listener_ns} ${connector_ns} MPTCP TCP ${connect_addr} ${local_addr} @@ -516,6 +533,15 @@ run_tests_lo() return 1 fi + if [ $do_tcp -gt 1 ] ;then + do_transfer ${listener_ns} ${connector_ns} TCP TCP ${connect_addr} ${local_addr} + lret=$? + if [ $lret -ne 0 ]; then + ret=$lret + return 1 + fi + fi + return 0 } -- cgit v1.2.3 From 99126abec5e5778583b959cb164f1888374917d3 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 1 Jul 2020 17:48:52 -0700 Subject: bpf: selftests: A few improvements to network_helpers.c This patch makes a few changes to the network_helpers.c 1) Enforce SO_RCVTIMEO and SO_SNDTIMEO This patch enforces timeout to the network fds through setsockopt SO_RCVTIMEO and SO_SNDTIMEO. It will remove the need for SOCK_NONBLOCK that requires a more demanding timeout logic with epoll/select, e.g. epoll_create, epoll_ctrl, and then epoll_wait for timeout. That removes the need for connect_wait() from the cgroup_skb_sk_lookup.c. The needed change is made in cgroup_skb_sk_lookup.c. 2) start_server(): Add optional addr_str and port to start_server(). That removes the need of the start_server_with_port(). The caller can pass addr_str==NULL and/or port==0. I have a future tcp-hdr-opt test that will pass a non-NULL addr_str and it is in general useful for other future tests. "int timeout_ms" is also added to control the timeout on the "accept(listen_fd)". 3) connect_to_fd(): Fully use the server_fd. The server sock address has already been obtained from getsockname(server_fd). The sockaddr includes the family, so the "int family" arg is redundant. Since the server address is obtained from server_fd, there is little reason not to get the server's socket type from the server_fd also. getsockopt(server_fd) can be used to do that, so "int type" arg is also removed. "int timeout_ms" is added. 4) connect_fd_to_fd(): "int timeout_ms" is added. Some code is also refactored to connect_fd_to_addr() which is shared with connect_to_fd(). 5) Preserve errno: Some callers need to check errno, e.g. cgroup_skb_sk_lookup.c. Make changes to do it more consistently in save_errno_close() and log_err(). Signed-off-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20200702004852.2103003-1-kafai@fb.com --- tools/testing/selftests/bpf/network_helpers.c | 157 ++++++++++++--------- tools/testing/selftests/bpf/network_helpers.h | 9 +- .../bpf/prog_tests/cgroup_skb_sk_lookup.c | 12 +- .../selftests/bpf/prog_tests/connect_force_port.c | 10 +- .../selftests/bpf/prog_tests/load_bytes_relative.c | 4 +- tools/testing/selftests/bpf/prog_tests/tcp_rtt.c | 4 +- 6 files changed, 110 insertions(+), 86 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index e36dd1a1780d..acd08715be2e 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -7,8 +7,6 @@ #include -#include - #include #include #include @@ -17,8 +15,13 @@ #include "network_helpers.h" #define clean_errno() (errno == 0 ? "None" : strerror(errno)) -#define log_err(MSG, ...) fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", \ - __FILE__, __LINE__, clean_errno(), ##__VA_ARGS__) +#define log_err(MSG, ...) ({ \ + int __save = errno; \ + fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", \ + __FILE__, __LINE__, clean_errno(), \ + ##__VA_ARGS__); \ + errno = __save; \ +}) struct ipv4_packet pkt_v4 = { .eth.h_proto = __bpf_constant_htons(ETH_P_IP), @@ -37,7 +40,34 @@ struct ipv6_packet pkt_v6 = { .tcp.doff = 5, }; -int start_server_with_port(int family, int type, __u16 port) +static int settimeo(int fd, int timeout_ms) +{ + struct timeval timeout = { .tv_sec = 3 }; + + if (timeout_ms > 0) { + timeout.tv_sec = timeout_ms / 1000; + timeout.tv_usec = (timeout_ms % 1000) * 1000; + } + + if (setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &timeout, + sizeof(timeout))) { + log_err("Failed to set SO_RCVTIMEO"); + return -1; + } + + if (setsockopt(fd, SOL_SOCKET, SO_SNDTIMEO, &timeout, + sizeof(timeout))) { + log_err("Failed to set SO_SNDTIMEO"); + return -1; + } + + return 0; +} + +#define save_errno_close(fd) ({ int __save = errno; close(fd); errno = __save; }) + +int start_server(int family, int type, const char *addr_str, __u16 port, + int timeout_ms) { struct sockaddr_storage addr = {}; socklen_t len; @@ -48,120 +78,119 @@ int start_server_with_port(int family, int type, __u16 port) sin->sin_family = AF_INET; sin->sin_port = htons(port); + if (addr_str && + inet_pton(AF_INET, addr_str, &sin->sin_addr) != 1) { + log_err("inet_pton(AF_INET, %s)", addr_str); + return -1; + } len = sizeof(*sin); } else { struct sockaddr_in6 *sin6 = (void *)&addr; sin6->sin6_family = AF_INET6; sin6->sin6_port = htons(port); + if (addr_str && + inet_pton(AF_INET6, addr_str, &sin6->sin6_addr) != 1) { + log_err("inet_pton(AF_INET6, %s)", addr_str); + return -1; + } len = sizeof(*sin6); } - fd = socket(family, type | SOCK_NONBLOCK, 0); + fd = socket(family, type, 0); if (fd < 0) { log_err("Failed to create server socket"); return -1; } + if (settimeo(fd, timeout_ms)) + goto error_close; + if (bind(fd, (const struct sockaddr *)&addr, len) < 0) { log_err("Failed to bind socket"); - close(fd); - return -1; + goto error_close; } if (type == SOCK_STREAM) { if (listen(fd, 1) < 0) { log_err("Failed to listed on socket"); - close(fd); - return -1; + goto error_close; } } return fd; -} -int start_server(int family, int type) -{ - return start_server_with_port(family, type, 0); +error_close: + save_errno_close(fd); + return -1; } -static const struct timeval timeo_sec = { .tv_sec = 3 }; -static const size_t timeo_optlen = sizeof(timeo_sec); - -int connect_to_fd(int family, int type, int server_fd) +static int connect_fd_to_addr(int fd, + const struct sockaddr_storage *addr, + socklen_t addrlen) { - int fd, save_errno; - - fd = socket(family, type, 0); - if (fd < 0) { - log_err("Failed to create client socket"); + if (connect(fd, (const struct sockaddr *)addr, addrlen)) { + log_err("Failed to connect to server"); return -1; } - if (connect_fd_to_fd(fd, server_fd) < 0 && errno != EINPROGRESS) { - save_errno = errno; - close(fd); - errno = save_errno; - return -1; - } - - return fd; + return 0; } -int connect_fd_to_fd(int client_fd, int server_fd) +int connect_to_fd(int server_fd, int timeout_ms) { struct sockaddr_storage addr; - socklen_t len = sizeof(addr); - int save_errno; + struct sockaddr_in *addr_in; + socklen_t addrlen, optlen; + int fd, type; - if (setsockopt(client_fd, SOL_SOCKET, SO_RCVTIMEO, &timeo_sec, - timeo_optlen)) { - log_err("Failed to set SO_RCVTIMEO"); + optlen = sizeof(type); + if (getsockopt(server_fd, SOL_SOCKET, SO_TYPE, &type, &optlen)) { + log_err("getsockopt(SOL_TYPE)"); return -1; } - if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) { + addrlen = sizeof(addr); + if (getsockname(server_fd, (struct sockaddr *)&addr, &addrlen)) { log_err("Failed to get server addr"); return -1; } - if (connect(client_fd, (const struct sockaddr *)&addr, len) < 0) { - if (errno != EINPROGRESS) { - save_errno = errno; - log_err("Failed to connect to server"); - errno = save_errno; - } + addr_in = (struct sockaddr_in *)&addr; + fd = socket(addr_in->sin_family, type, 0); + if (fd < 0) { + log_err("Failed to create client socket"); return -1; } - return 0; + if (settimeo(fd, timeout_ms)) + goto error_close; + + if (connect_fd_to_addr(fd, &addr, addrlen)) + goto error_close; + + return fd; + +error_close: + save_errno_close(fd); + return -1; } -int connect_wait(int fd) +int connect_fd_to_fd(int client_fd, int server_fd, int timeout_ms) { - struct epoll_event ev = {}, events[2]; - int timeout_ms = 1000; - int efd, nfd; + struct sockaddr_storage addr; + socklen_t len = sizeof(addr); - efd = epoll_create1(EPOLL_CLOEXEC); - if (efd < 0) { - log_err("Failed to open epoll fd"); + if (settimeo(client_fd, timeout_ms)) return -1; - } - - ev.events = EPOLLRDHUP | EPOLLOUT; - ev.data.fd = fd; - if (epoll_ctl(efd, EPOLL_CTL_ADD, fd, &ev) < 0) { - log_err("Failed to register fd=%d on epoll fd=%d", fd, efd); - close(efd); + if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) { + log_err("Failed to get server addr"); return -1; } - nfd = epoll_wait(efd, events, ARRAY_SIZE(events), timeout_ms); - if (nfd < 0) - log_err("Failed to wait for I/O event on epoll fd=%d", efd); + if (connect_fd_to_addr(client_fd, &addr, len)) + return -1; - close(efd); - return nfd; + return 0; } diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h index 6a8009605670..f580e82fda58 100644 --- a/tools/testing/selftests/bpf/network_helpers.h +++ b/tools/testing/selftests/bpf/network_helpers.h @@ -33,10 +33,9 @@ struct ipv6_packet { } __packed; extern struct ipv6_packet pkt_v6; -int start_server(int family, int type); -int start_server_with_port(int family, int type, __u16 port); -int connect_to_fd(int family, int type, int server_fd); -int connect_fd_to_fd(int client_fd, int server_fd); -int connect_wait(int client_fd); +int start_server(int family, int type, const char *addr, __u16 port, + int timeout_ms); +int connect_to_fd(int server_fd, int timeout_ms); +int connect_fd_to_fd(int client_fd, int server_fd, int timeout_ms); #endif diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_skb_sk_lookup.c b/tools/testing/selftests/bpf/prog_tests/cgroup_skb_sk_lookup.c index 059047af7df3..464edc1c1708 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_skb_sk_lookup.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_skb_sk_lookup.c @@ -13,7 +13,7 @@ static void run_lookup_test(__u16 *g_serv_port, int out_sk) socklen_t addr_len = sizeof(addr); __u32 duration = 0; - serv_sk = start_server(AF_INET6, SOCK_STREAM); + serv_sk = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0); if (CHECK(serv_sk < 0, "start_server", "failed to start server\n")) return; @@ -24,17 +24,13 @@ static void run_lookup_test(__u16 *g_serv_port, int out_sk) *g_serv_port = addr.sin6_port; /* Client outside of test cgroup should fail to connect by timeout. */ - err = connect_fd_to_fd(out_sk, serv_sk); + err = connect_fd_to_fd(out_sk, serv_sk, 1000); if (CHECK(!err || errno != EINPROGRESS, "connect_fd_to_fd", "unexpected result err %d errno %d\n", err, errno)) goto cleanup; - err = connect_wait(out_sk); - if (CHECK(err, "connect_wait", "unexpected result %d\n", err)) - goto cleanup; - /* Client inside test cgroup should connect just fine. */ - in_sk = connect_to_fd(AF_INET6, SOCK_STREAM, serv_sk); + in_sk = connect_to_fd(serv_sk, 0); if (CHECK(in_sk < 0, "connect_to_fd", "errno %d\n", errno)) goto cleanup; @@ -85,7 +81,7 @@ void test_cgroup_skb_sk_lookup(void) * differs from that of testing cgroup. Moving selftests process to * testing cgroup won't change cgroup id of an already created socket. */ - out_sk = socket(AF_INET6, SOCK_STREAM | SOCK_NONBLOCK, 0); + out_sk = socket(AF_INET6, SOCK_STREAM, 0); if (CHECK_FAIL(out_sk < 0)) return; diff --git a/tools/testing/selftests/bpf/prog_tests/connect_force_port.c b/tools/testing/selftests/bpf/prog_tests/connect_force_port.c index 17bbf76812ca..9229db2f5ca5 100644 --- a/tools/testing/selftests/bpf/prog_tests/connect_force_port.c +++ b/tools/testing/selftests/bpf/prog_tests/connect_force_port.c @@ -114,7 +114,7 @@ static int run_test(int cgroup_fd, int server_fd, int family, int type) goto close_bpf_object; } - fd = connect_to_fd(family, type, server_fd); + fd = connect_to_fd(server_fd, 0); if (fd < 0) { err = -1; goto close_bpf_object; @@ -137,25 +137,25 @@ void test_connect_force_port(void) if (CHECK_FAIL(cgroup_fd < 0)) return; - server_fd = start_server_with_port(AF_INET, SOCK_STREAM, 60123); + server_fd = start_server(AF_INET, SOCK_STREAM, NULL, 60123, 0); if (CHECK_FAIL(server_fd < 0)) goto close_cgroup_fd; CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET, SOCK_STREAM)); close(server_fd); - server_fd = start_server_with_port(AF_INET6, SOCK_STREAM, 60124); + server_fd = start_server(AF_INET6, SOCK_STREAM, NULL, 60124, 0); if (CHECK_FAIL(server_fd < 0)) goto close_cgroup_fd; CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET6, SOCK_STREAM)); close(server_fd); - server_fd = start_server_with_port(AF_INET, SOCK_DGRAM, 60123); + server_fd = start_server(AF_INET, SOCK_DGRAM, NULL, 60123, 0); if (CHECK_FAIL(server_fd < 0)) goto close_cgroup_fd; CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET, SOCK_DGRAM)); close(server_fd); - server_fd = start_server_with_port(AF_INET6, SOCK_DGRAM, 60124); + server_fd = start_server(AF_INET6, SOCK_DGRAM, NULL, 60124, 0); if (CHECK_FAIL(server_fd < 0)) goto close_cgroup_fd; CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET6, SOCK_DGRAM)); diff --git a/tools/testing/selftests/bpf/prog_tests/load_bytes_relative.c b/tools/testing/selftests/bpf/prog_tests/load_bytes_relative.c index c1168e4a9036..5a2a689dbb68 100644 --- a/tools/testing/selftests/bpf/prog_tests/load_bytes_relative.c +++ b/tools/testing/selftests/bpf/prog_tests/load_bytes_relative.c @@ -23,7 +23,7 @@ void test_load_bytes_relative(void) if (CHECK_FAIL(cgroup_fd < 0)) return; - server_fd = start_server(AF_INET, SOCK_STREAM); + server_fd = start_server(AF_INET, SOCK_STREAM, NULL, 0, 0); if (CHECK_FAIL(server_fd < 0)) goto close_cgroup_fd; @@ -49,7 +49,7 @@ void test_load_bytes_relative(void) if (CHECK_FAIL(err)) goto close_bpf_object; - client_fd = connect_to_fd(AF_INET, SOCK_STREAM, server_fd); + client_fd = connect_to_fd(server_fd, 0); if (CHECK_FAIL(client_fd < 0)) goto close_bpf_object; close(client_fd); diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c index 9013a0c01eed..d207e968e6b1 100644 --- a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c +++ b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c @@ -118,7 +118,7 @@ static int run_test(int cgroup_fd, int server_fd) goto close_bpf_object; } - client_fd = connect_to_fd(AF_INET, SOCK_STREAM, server_fd); + client_fd = connect_to_fd(server_fd, 0); if (client_fd < 0) { err = -1; goto close_bpf_object; @@ -161,7 +161,7 @@ void test_tcp_rtt(void) if (CHECK_FAIL(cgroup_fd < 0)) return; - server_fd = start_server(AF_INET, SOCK_STREAM); + server_fd = start_server(AF_INET, SOCK_STREAM, NULL, 0, 0); if (CHECK_FAIL(server_fd < 0)) goto close_cgroup_fd; -- cgit v1.2.3 From 811d7e375d08312dba23f3b6bf7e58ec14aa5dcb Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 1 Jul 2020 17:48:58 -0700 Subject: bpf: selftests: Restore netns after each test It is common for networking tests creating its netns and making its own setting under this new netns (e.g. changing tcp sysctl). If the test forgot to restore to the original netns, it would affect the result of other tests. This patch saves the original netns at the beginning and then restores it after every test. Since the restore "setns()" is not expensive, it does it on all tests without tracking if a test has created a new netns or not. The new restore_netns() could also be done in test__end_subtest() such that each subtest will get an automatic netns reset. However, the individual test would lose flexibility to have total control on netns for its own subtests. In some cases, forcing a test to do unnecessary netns re-configure for each subtest is time consuming. e.g. In my vm, forcing netns re-configure on each subtest in sk_assign.c increased the runtime from 1s to 8s. On top of that, test_progs.c is also doing per-test (instead of per-subtest) cleanup for cgroup. Thus, this patch also does per-test restore_netns(). The only existing per-subtest cleanup is reset_affinity() and no test is depending on this. Thus, it is removed from test__end_subtest() to give a consistent expectation to the individual tests. test_progs.c only ensures any affinity/netns/cgroup change made by an earlier test does not affect the following tests. Signed-off-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200702004858.2103728-1-kafai@fb.com --- tools/testing/selftests/bpf/test_progs.c | 23 +++++++++++++++++++++-- tools/testing/selftests/bpf/test_progs.h | 2 ++ 2 files changed, 23 insertions(+), 2 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index ef05d2f0e7bb..104e833d0087 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -121,6 +121,24 @@ static void reset_affinity() { } } +static void save_netns(void) +{ + env.saved_netns_fd = open("/proc/self/ns/net", O_RDONLY); + if (env.saved_netns_fd == -1) { + perror("open(/proc/self/ns/net)"); + exit(-1); + } +} + +static void restore_netns(void) +{ + if (setns(env.saved_netns_fd, CLONE_NEWNET) == -1) { + stdio_restore(); + perror("setns(CLONE_NEWNS)"); + exit(-1); + } +} + void test__end_subtest() { struct prog_test_def *test = env.test; @@ -138,8 +156,6 @@ void test__end_subtest() test->test_num, test->subtest_num, test->subtest_name, sub_error_cnt ? "FAIL" : "OK"); - reset_affinity(); - free(test->subtest_name); test->subtest_name = NULL; } @@ -655,6 +671,7 @@ int main(int argc, char **argv) return -1; } + save_netns(); stdio_hijack(); for (i = 0; i < prog_test_cnt; i++) { struct prog_test_def *test = &prog_test_defs[i]; @@ -696,6 +713,7 @@ int main(int argc, char **argv) test->error_cnt ? "FAIL" : "OK"); reset_affinity(); + restore_netns(); if (test->need_cgroup_cleanup) cleanup_cgroup_environment(); } @@ -719,6 +737,7 @@ out: free_str_set(&env.subtest_selector.blacklist); free_str_set(&env.subtest_selector.whitelist); free(env.subtest_selector.num_set); + close(env.saved_netns_fd); if (env.succ_cnt + env.fail_cnt + env.skip_cnt == 0) return EXIT_FAILURE; diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index ec31f382e7fd..6e09bf738473 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -80,6 +80,8 @@ struct test_env { int sub_succ_cnt; /* successful sub-tests */ int fail_cnt; /* total failed tests + sub-tests */ int skip_cnt; /* skipped tests */ + + int saved_netns_fd; }; extern struct test_env env; -- cgit v1.2.3 From 9ff79af3331277c69ac61cc75b2392eb3284e305 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Fri, 3 Jul 2020 11:17:19 -0700 Subject: selftests/bpf: Fix compilation error of bpf_iter_task_stack.c BPF selftests show a compilation error as follows: libbpf: invalid relo for 'entries' in special section 0xfff2; forgot to initialize global var?.. Fix it by initializing 'entries' to zeros. Fixes: c7568114bc56 ("selftests/bpf: Add bpf_iter test with bpf_get_task_stack()") Reported-by: Jesper Dangaard Brouer Signed-off-by: Song Liu Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20200703181719.3747072-1-songliubraving@fb.com --- tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c index e40d32a2ed93..50e59a2e142e 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c @@ -7,7 +7,7 @@ char _license[] SEC("license") = "GPL"; #define MAX_STACK_TRACE_DEPTH 64 -unsigned long entries[MAX_STACK_TRACE_DEPTH]; +unsigned long entries[MAX_STACK_TRACE_DEPTH] = {}; #define SIZE_OF_ULONG (sizeof(unsigned long)) SEC("iter/task") -- cgit v1.2.3 From b0d754ef35041f921a1a03319b570fdfac9a027e Mon Sep 17 00:00:00 2001 From: tannerlove Date: Fri, 3 Jul 2020 14:53:06 -0400 Subject: selftests/net: add ipv6 test coverage in rxtimestamp test Add the options --ipv4, --ipv6 to specify running over ipv4 and/or ipv6. If neither is specified, then run both. Signed-off-by: Tanner Love Acked-by: Willem de Bruijn Signed-off-by: David S. Miller --- tools/testing/selftests/net/rxtimestamp.c | 85 +++++++++++++++++++++---------- 1 file changed, 59 insertions(+), 26 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/net/rxtimestamp.c b/tools/testing/selftests/net/rxtimestamp.c index d4ea86a13e52..c599d371cbbe 100644 --- a/tools/testing/selftests/net/rxtimestamp.c +++ b/tools/testing/selftests/net/rxtimestamp.c @@ -117,6 +117,8 @@ static struct option long_options[] = { { "udp", no_argument, 0, 'u' }, { "ip", no_argument, 0, 'i' }, { "strict", no_argument, 0, 'S' }, + { "ipv4", no_argument, 0, '4' }, + { "ipv6", no_argument, 0, '6' }, { NULL, 0, NULL, 0 }, }; @@ -272,37 +274,55 @@ void config_so_flags(int rcv, struct options o) error(1, errno, "Failed to set SO_TIMESTAMPING"); } -bool run_test_case(struct socket_type s, struct test_case t) +bool run_test_case(struct socket_type *s, int test_num, char ip_version, + bool strict) { - int port = (s.type == SOCK_RAW) ? 0 : next_port++; + union { + struct sockaddr_in6 addr6; + struct sockaddr_in addr4; + struct sockaddr addr_un; + } addr; int read_size = op_size; - struct sockaddr_in addr; + int src, dst, rcv, port; + socklen_t addr_size; bool failed = false; - int src, dst, rcv; - src = socket(AF_INET, s.type, s.protocol); + port = (s->type == SOCK_RAW) ? 0 : next_port++; + memset(&addr, 0, sizeof(addr)); + if (ip_version == '4') { + addr.addr4.sin_family = AF_INET; + addr.addr4.sin_addr.s_addr = htonl(INADDR_LOOPBACK); + addr.addr4.sin_port = htons(port); + addr_size = sizeof(addr.addr4); + if (s->type == SOCK_RAW) + read_size += 20; /* for IPv4 header */ + } else { + addr.addr6.sin6_family = AF_INET6; + addr.addr6.sin6_addr = in6addr_loopback; + addr.addr6.sin6_port = htons(port); + addr_size = sizeof(addr.addr6); + } + printf("Starting testcase %d over ipv%c...\n", test_num, ip_version); + src = socket(addr.addr_un.sa_family, s->type, + s->protocol); if (src < 0) error(1, errno, "Failed to open src socket"); - dst = socket(AF_INET, s.type, s.protocol); + dst = socket(addr.addr_un.sa_family, s->type, + s->protocol); if (dst < 0) error(1, errno, "Failed to open dst socket"); - memset(&addr, 0, sizeof(addr)); - addr.sin_family = AF_INET; - addr.sin_addr.s_addr = htonl(INADDR_LOOPBACK); - addr.sin_port = htons(port); - - if (bind(dst, (struct sockaddr *)&addr, sizeof(addr)) < 0) + if (bind(dst, &addr.addr_un, addr_size) < 0) error(1, errno, "Failed to bind to port %d", port); - if (s.type == SOCK_STREAM && (listen(dst, 1) < 0)) + if (s->type == SOCK_STREAM && (listen(dst, 1) < 0)) error(1, errno, "Failed to listen"); - if (connect(src, (struct sockaddr *)&addr, sizeof(addr)) < 0) + if (connect(src, &addr.addr_un, addr_size) < 0) error(1, errno, "Failed to connect"); - if (s.type == SOCK_STREAM) { + if (s->type == SOCK_STREAM) { rcv = accept(dst, NULL, NULL); if (rcv < 0) error(1, errno, "Failed to accept"); @@ -311,17 +331,22 @@ bool run_test_case(struct socket_type s, struct test_case t) rcv = dst; } - config_so_flags(rcv, t.sockopt); + config_so_flags(rcv, test_cases[test_num].sockopt); usleep(20000); /* setsockopt for SO_TIMESTAMPING is asynchronous */ do_send(src); - if (s.type == SOCK_RAW) - read_size += 20; /* for IP header */ - failed = do_recv(rcv, read_size, t.expected); + failed = do_recv(rcv, read_size, test_cases[test_num].expected); close(rcv); close(src); + if (failed) { + printf("FAILURE in testcase %d over ipv%c ", test_num, + ip_version); + print_test_case(&test_cases[test_num]); + if (!strict && test_cases[test_num].warn_on_fail) + failed = false; + } return failed; } @@ -329,6 +354,8 @@ int main(int argc, char **argv) { bool all_protocols = true; bool all_tests = true; + bool cfg_ipv4 = false; + bool cfg_ipv6 = false; bool strict = false; int arg_index = 0; int failures = 0; @@ -369,6 +396,12 @@ int main(int argc, char **argv) case 'S': strict = true; break; + case '4': + cfg_ipv4 = true; + break; + case '6': + cfg_ipv6 = true; + break; default: error(1, 0, "Failed to parse parameters."); } @@ -382,14 +415,14 @@ int main(int argc, char **argv) for (t = 0; t < ARRAY_SIZE(test_cases); t++) { if (!all_tests && !test_cases[t].enabled) continue; - - printf("Starting testcase %d...\n", t); - if (run_test_case(socket_types[s], test_cases[t])) { - if (strict || !test_cases[t].warn_on_fail) + if (cfg_ipv4 || !cfg_ipv6) + if (run_test_case(&socket_types[s], t, '4', + strict)) + failures++; + if (cfg_ipv6 || !cfg_ipv4) + if (run_test_case(&socket_types[s], t, '6', + strict)) failures++; - printf("FAILURE in test case "); - print_test_case(&test_cases[t]); - } } } if (!failures) -- cgit v1.2.3 From f551e2fdaf81b7b561bb5dc590da13f21c4c1295 Mon Sep 17 00:00:00 2001 From: Tanner Love Date: Sat, 4 Jul 2020 16:45:14 -0400 Subject: selftests/net: update initializer syntax to use c99 designators Before, clang version 9 threw errors such as: error: use of GNU old-style field designator extension [-Werror,-Wgnu-designator] { tstamp: true, swtstamp: true } ^~~~~~~ .tstamp = Fix these warnings in tools/testing/selftests/net in the same manner as commit 121e357ac728 ("selftests/harness: Update named initializer syntax"). N.B. rxtimestamp.c is the only affected file in the directory. Signed-off-by: Tanner Love Acked-by: Willem de Bruijn Signed-off-by: David S. Miller --- tools/testing/selftests/net/rxtimestamp.c | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/net/rxtimestamp.c b/tools/testing/selftests/net/rxtimestamp.c index c599d371cbbe..221fdece47d4 100644 --- a/tools/testing/selftests/net/rxtimestamp.c +++ b/tools/testing/selftests/net/rxtimestamp.c @@ -68,44 +68,44 @@ static struct socket_type socket_types[] = { static struct test_case test_cases[] = { { {}, {} }, { - { so_timestamp: 1 }, - { tstamp: true } + { .so_timestamp = 1 }, + { .tstamp = true } }, { - { so_timestampns: 1 }, - { tstampns: true } + { .so_timestampns = 1 }, + { .tstampns = true } }, { - { so_timestamp: 1, so_timestampns: 1 }, - { tstampns: true } + { .so_timestamp = 1, .so_timestampns = 1 }, + { .tstampns = true } }, { - { so_timestamping: SOF_TIMESTAMPING_RX_SOFTWARE }, + { .so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE }, {} }, { /* Loopback device does not support hw timestamps. */ - { so_timestamping: SOF_TIMESTAMPING_RX_HARDWARE }, + { .so_timestamping = SOF_TIMESTAMPING_RX_HARDWARE }, {} }, { - { so_timestamping: SOF_TIMESTAMPING_SOFTWARE }, - warn_on_fail : true + { .so_timestamping = SOF_TIMESTAMPING_SOFTWARE }, + .warn_on_fail = true }, { - { so_timestamping: SOF_TIMESTAMPING_RX_SOFTWARE + { .so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE | SOF_TIMESTAMPING_RX_HARDWARE }, {} }, { - { so_timestamping: SOF_TIMESTAMPING_SOFTWARE + { .so_timestamping = SOF_TIMESTAMPING_SOFTWARE | SOF_TIMESTAMPING_RX_SOFTWARE }, - { swtstamp: true } + { .swtstamp = true } }, { - { so_timestamp: 1, so_timestamping: SOF_TIMESTAMPING_SOFTWARE + { .so_timestamp = 1, .so_timestamping = SOF_TIMESTAMPING_SOFTWARE | SOF_TIMESTAMPING_RX_SOFTWARE }, - { tstamp: true, swtstamp: true } + { .tstamp = true, .swtstamp = true } }, }; -- cgit v1.2.3 From 0b8241fe3c4e172332f9fa690db6689e78e8e27f Mon Sep 17 00:00:00 2001 From: Matthieu Baerts Date: Mon, 6 Jul 2020 14:44:08 +0200 Subject: selftests: mptcp: capture pcap on both sides When investigating performance issues that involve latency / loss / reordering it is useful to have the pcap from the sender-side as it allows to easier infer the state of the sender's congestion-control, loss-recovery, etc. Allow the selftests to capture a pcap on both sender and receiver so that this information is not lost when reproducing. This patch also improves the file names. Instead of: ns4-5ee79a56-X4O6gS-ns3-5ee79a56-X4O6gS-MPTCP-MPTCP-10.0.3.1.pcap We now have something like for the same test: 5ee79a56-X4O6gS-ns3-ns4-MPTCP-MPTCP-10.0.3.1-10030-connector.pcap 5ee79a56-X4O6gS-ns3-ns4-MPTCP-MPTCP-10.0.3.1-10030-listener.pcap It was a connection from ns3 to ns4, better to start with ns3 then. The port is also added, easier to find the trace we want. Co-developed-by: Christoph Paasch Signed-off-by: Christoph Paasch Signed-off-by: Matthieu Baerts Signed-off-by: David S. Miller --- tools/testing/selftests/net/mptcp/mptcp_connect.sh | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index 8f7145c413b9..c0589e071f20 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -395,10 +395,14 @@ do_transfer() capuser="-Z $SUDO_USER" fi - local capfile="${listener_ns}-${connector_ns}-${cl_proto}-${srv_proto}-${connect_addr}.pcap" + local capfile="${rndh}-${connector_ns:0:3}-${listener_ns:0:3}-${cl_proto}-${srv_proto}-${connect_addr}-${port}" + local capopt="-i any -s 65535 -B 32768 ${capuser}" - ip netns exec ${listener_ns} tcpdump -i any -s 65535 -B 32768 $capuser -w $capfile > "$capout" 2>&1 & - local cappid=$! + ip netns exec ${listener_ns} tcpdump ${capopt} -w "${capfile}-listener.pcap" >> "${capout}" 2>&1 & + local cappid_listener=$! + + ip netns exec ${connector_ns} tcpdump ${capopt} -w "${capfile}-connector.pcap" >> "${capout}" 2>&1 & + local cappid_connector=$! sleep 1 fi @@ -423,7 +427,8 @@ do_transfer() if $capture; then sleep 1 - kill $cappid + kill ${cappid_listener} + kill ${cappid_connector} fi local duration -- cgit v1.2.3 From 65ffd797861a44ff97081de1db01e4aef716ed46 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 6 Jul 2020 16:01:28 -0700 Subject: selftests/bpf: Test BPF_CGROUP_INET_SOCK_RELEASE Simple test that enforces a single SOCK_DGRAM socket per cgroup. Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200706230128.4073544-5-sdf@google.com --- tools/testing/selftests/bpf/prog_tests/udp_limit.c | 75 ++++++++++++++++++++++ tools/testing/selftests/bpf/progs/udp_limit.c | 42 ++++++++++++ 2 files changed, 117 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/udp_limit.c create mode 100644 tools/testing/selftests/bpf/progs/udp_limit.c (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/udp_limit.c b/tools/testing/selftests/bpf/prog_tests/udp_limit.c new file mode 100644 index 000000000000..2aba09d4d01b --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/udp_limit.c @@ -0,0 +1,75 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include "udp_limit.skel.h" + +#include +#include + +static int duration; + +void test_udp_limit(void) +{ + struct udp_limit *skel; + int fd1 = -1, fd2 = -1; + int cgroup_fd; + + cgroup_fd = test__join_cgroup("/udp_limit"); + if (CHECK(cgroup_fd < 0, "cg-join", "errno %d", errno)) + return; + + skel = udp_limit__open_and_load(); + if (CHECK(!skel, "skel-load", "errno %d", errno)) + goto close_cgroup_fd; + + skel->links.sock = bpf_program__attach_cgroup(skel->progs.sock, cgroup_fd); + skel->links.sock_release = bpf_program__attach_cgroup(skel->progs.sock_release, cgroup_fd); + if (CHECK(IS_ERR(skel->links.sock) || IS_ERR(skel->links.sock_release), + "cg-attach", "sock %ld sock_release %ld", + PTR_ERR(skel->links.sock), + PTR_ERR(skel->links.sock_release))) + goto close_skeleton; + + /* BPF program enforces a single UDP socket per cgroup, + * verify that. + */ + fd1 = socket(AF_INET, SOCK_DGRAM, 0); + if (CHECK(fd1 < 0, "fd1", "errno %d", errno)) + goto close_skeleton; + + fd2 = socket(AF_INET, SOCK_DGRAM, 0); + if (CHECK(fd2 >= 0, "fd2", "errno %d", errno)) + goto close_skeleton; + + /* We can reopen again after close. */ + close(fd1); + fd1 = -1; + + fd1 = socket(AF_INET, SOCK_DGRAM, 0); + if (CHECK(fd1 < 0, "fd1-again", "errno %d", errno)) + goto close_skeleton; + + /* Make sure the program was invoked the expected + * number of times: + * - open fd1 - BPF_CGROUP_INET_SOCK_CREATE + * - attempt to openfd2 - BPF_CGROUP_INET_SOCK_CREATE + * - close fd1 - BPF_CGROUP_INET_SOCK_RELEASE + * - open fd1 again - BPF_CGROUP_INET_SOCK_CREATE + */ + if (CHECK(skel->bss->invocations != 4, "bss-invocations", + "invocations=%d", skel->bss->invocations)) + goto close_skeleton; + + /* We should still have a single socket in use */ + if (CHECK(skel->bss->in_use != 1, "bss-in_use", + "in_use=%d", skel->bss->in_use)) + goto close_skeleton; + +close_skeleton: + if (fd1 >= 0) + close(fd1); + if (fd2 >= 0) + close(fd2); + udp_limit__destroy(skel); +close_cgroup_fd: + close(cgroup_fd); +} diff --git a/tools/testing/selftests/bpf/progs/udp_limit.c b/tools/testing/selftests/bpf/progs/udp_limit.c new file mode 100644 index 000000000000..8429b22525a7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/udp_limit.c @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include +#include + +int invocations = 0, in_use = 0; + +SEC("cgroup/sock_create") +int sock(struct bpf_sock *ctx) +{ + __u32 key; + + if (ctx->type != SOCK_DGRAM) + return 1; + + __sync_fetch_and_add(&invocations, 1); + + if (in_use > 0) { + /* BPF_CGROUP_INET_SOCK_RELEASE is _not_ called + * when we return an error from the BPF + * program! + */ + return 0; + } + + __sync_fetch_and_add(&in_use, 1); + return 1; +} + +SEC("cgroup/sock_release") +int sock_release(struct bpf_sock *ctx) +{ + __u32 key; + + if (ctx->type != SOCK_DGRAM) + return 1; + + __sync_fetch_and_add(&invocations, 1); + __sync_fetch_and_add(&in_use, -1); + return 1; +} -- cgit v1.2.3 From 5cfd607b49db2b7c05fccc2915a528d97bc8f17d Mon Sep 17 00:00:00 2001 From: "Daniel T. Lee" Date: Wed, 8 Jul 2020 03:48:55 +0900 Subject: selftests: bpf: Remove unused bpf_map_def_legacy struct samples/bpf no longer use bpf_map_def_legacy and instead use the libbpf's bpf_map_def or new BTF-defined MAP format. This commit removes unused bpf_map_def_legacy struct from selftests/bpf/bpf_legacy.h. Signed-off-by: Daniel T. Lee Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200707184855.30968-5-danieltimlee@gmail.com --- tools/testing/selftests/bpf/bpf_legacy.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/bpf_legacy.h b/tools/testing/selftests/bpf/bpf_legacy.h index 6f8988738bc1..719ab56cdb5d 100644 --- a/tools/testing/selftests/bpf/bpf_legacy.h +++ b/tools/testing/selftests/bpf/bpf_legacy.h @@ -2,20 +2,6 @@ #ifndef __BPF_LEGACY__ #define __BPF_LEGACY__ -/* - * legacy bpf_map_def with extra fields supported only by bpf_load(), do not - * use outside of samples/bpf - */ -struct bpf_map_def_legacy { - unsigned int type; - unsigned int key_size; - unsigned int value_size; - unsigned int max_entries; - unsigned int map_flags; - unsigned int inner_map_idx; - unsigned int numa_node; -}; - #define BPF_ANNOTATE_KV_PAIR(name, type_key, type_val) \ struct ____btf_map_##name { \ type_key key; \ -- cgit v1.2.3 From 3220fb667842a9725cbb71656f406eadb03c094b Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 7 Jul 2020 09:12:19 +0200 Subject: selftests/bpf: test_progs use another shell exit on non-actions This is a follow up adjustment to commit 6c92bd5cd465 ("selftests/bpf: Test_progs indicate to shell on non-actions"), that returns shell exit indication EXIT_FAILURE (value 1) when user selects a non-existing test. The problem with using EXIT_FAILURE is that a shell script cannot tell the difference between a non-existing test and the test failing. This patch uses value 2 as shell exit indication. (Aside note unrecognized option parameters use value 64). Fixes: 6c92bd5cd465 ("selftests/bpf: Test_progs indicate to shell on non-actions") Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/159410593992.1093222.90072558386094370.stgit@firesoul --- tools/testing/selftests/bpf/test_progs.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index 104e833d0087..65d3f8686e29 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -12,6 +12,8 @@ #include #include /* backtrace */ +#define EXIT_NO_TEST 2 + /* defined in test_progs.h */ struct test_env env = {}; @@ -740,7 +742,7 @@ out: close(env.saved_netns_fd); if (env.succ_cnt + env.fail_cnt + env.skip_cnt == 0) - return EXIT_FAILURE; + return EXIT_NO_TEST; return env.fail_cnt ? EXIT_FAILURE : EXIT_SUCCESS; } -- cgit v1.2.3 From b8c50df0cb3eb9008f8372e4ff0317eee993b8d1 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 7 Jul 2020 09:12:25 +0200 Subject: selftests/bpf: test_progs avoid minus shell exit codes There are a number of places in test_progs that use minus-1 as the argument to exit(). This is confusing as a process exit status is masked to be a number between 0 and 255 as defined in man exit(3). Thus, users will see status 255 instead of minus-1. This patch use positive exit code 3 instead of minus-1. These cases are put in the same group of infrastructure setup errors. Fixes: fd27b1835e70 ("selftests/bpf: Reset process and thread affinity after each test/sub-test") Fixes: 811d7e375d08 ("bpf: selftests: Restore netns after each test") Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/159410594499.1093222.11080787853132708654.stgit@firesoul --- tools/testing/selftests/bpf/test_progs.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index 65d3f8686e29..b1e4dadacd9b 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -13,6 +13,7 @@ #include /* backtrace */ #define EXIT_NO_TEST 2 +#define EXIT_ERR_SETUP_INFRA 3 /* defined in test_progs.h */ struct test_env env = {}; @@ -113,13 +114,13 @@ static void reset_affinity() { if (err < 0) { stdio_restore(); fprintf(stderr, "Failed to reset process affinity: %d!\n", err); - exit(-1); + exit(EXIT_ERR_SETUP_INFRA); } err = pthread_setaffinity_np(pthread_self(), sizeof(cpuset), &cpuset); if (err < 0) { stdio_restore(); fprintf(stderr, "Failed to reset thread affinity: %d!\n", err); - exit(-1); + exit(EXIT_ERR_SETUP_INFRA); } } @@ -128,7 +129,7 @@ static void save_netns(void) env.saved_netns_fd = open("/proc/self/ns/net", O_RDONLY); if (env.saved_netns_fd == -1) { perror("open(/proc/self/ns/net)"); - exit(-1); + exit(EXIT_ERR_SETUP_INFRA); } } @@ -137,7 +138,7 @@ static void restore_netns(void) if (setns(env.saved_netns_fd, CLONE_NEWNET) == -1) { stdio_restore(); perror("setns(CLONE_NEWNS)"); - exit(-1); + exit(EXIT_ERR_SETUP_INFRA); } } -- cgit v1.2.3 From fcda189a5133b6fe50eb63d1062a15be4df9e3de Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 7 Jul 2020 18:53:16 -0700 Subject: selftests/bpf: Add test relying only on CO-RE and no recent kernel features Add a test that relies on CO-RE, but doesn't expect any of the recent features, not available on old kernels. This is useful for Travis CI tests running against very old kernels (e.g., libbpf has 4.9 kernel testing now), to verify that CO-RE still works, even if kernel itself doesn't support BTF yet, as long as there is .BTF embedded into vmlinux image by pahole. Given most of CO-RE doesn't require any kernel awareness of BTF, it is a useful test to validate that libbpf's BTF sanitization is working well even with ancient kernels. Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20200708015318.3827358-5-andriin@fb.com --- .../testing/selftests/bpf/prog_tests/core_retro.c | 33 ++++++++++++++++++++++ .../testing/selftests/bpf/progs/test_core_retro.c | 30 ++++++++++++++++++++ 2 files changed, 63 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/core_retro.c create mode 100644 tools/testing/selftests/bpf/progs/test_core_retro.c (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/core_retro.c b/tools/testing/selftests/bpf/prog_tests/core_retro.c new file mode 100644 index 000000000000..78e30d3a23d5 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/core_retro.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook +#define _GNU_SOURCE +#include +#include "test_core_retro.skel.h" + +void test_core_retro(void) +{ + int err, zero = 0, res, duration = 0; + struct test_core_retro *skel; + + /* load program */ + skel = test_core_retro__open_and_load(); + if (CHECK(!skel, "skel_load", "skeleton open/load failed\n")) + goto out_close; + + /* attach probe */ + err = test_core_retro__attach(skel); + if (CHECK(err, "attach_kprobe", "err %d\n", err)) + goto out_close; + + /* trigger */ + usleep(1); + + err = bpf_map_lookup_elem(bpf_map__fd(skel->maps.results), &zero, &res); + if (CHECK(err, "map_lookup", "failed to lookup result: %d\n", errno)) + goto out_close; + + CHECK(res != getpid(), "pid_check", "got %d != exp %d\n", res, getpid()); + +out_close: + test_core_retro__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/progs/test_core_retro.c b/tools/testing/selftests/bpf/progs/test_core_retro.c new file mode 100644 index 000000000000..75c60c3c29cf --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_retro.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook +#include +#include +#include + +struct task_struct { + int tgid; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} results SEC(".maps"); + +SEC("tp/raw_syscalls/sys_enter") +int handle_sys_enter(void *ctx) +{ + struct task_struct *task = (void *)bpf_get_current_task(); + int tgid = BPF_CORE_READ(task, tgid); + int zero = 0; + + bpf_map_update_elem(&results, &zero, &tgid, 0); + + return 0; +} + +char _license[] SEC("license") = "GPL"; -- cgit v1.2.3 From 6984cbc6dfa280687367b9660d8c830518239851 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 7 Jul 2020 18:53:18 -0700 Subject: selftests/bpf: Switch perf_buffer test to tracepoint and skeleton Switch perf_buffer test to use skeleton to avoid use of bpf_prog_load() and make test a bit more succinct. Also switch BPF program to use tracepoint instead of kprobe, as that allows to support older kernels, which had tracepoint support before kprobe support in the form that libbpf expects (i.e., libbpf expects /sys/bus/event_source/devices/kprobe/type, which doesn't always exist on old kernels). Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20200708015318.3827358-7-andriin@fb.com --- .../testing/selftests/bpf/prog_tests/perf_buffer.c | 42 +++++++--------------- .../testing/selftests/bpf/progs/test_perf_buffer.c | 4 +-- 2 files changed, 14 insertions(+), 32 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c index a122ce3b360e..c33ec180b3f2 100644 --- a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c +++ b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c @@ -4,6 +4,7 @@ #include #include #include +#include "test_perf_buffer.skel.h" #include "bpf/libbpf_internal.h" /* AddressSanitizer sometimes crashes due to data dereference below, due to @@ -25,16 +26,11 @@ static void on_sample(void *ctx, int cpu, void *data, __u32 size) void test_perf_buffer(void) { - int err, prog_fd, on_len, nr_on_cpus = 0, nr_cpus, i, duration = 0; - const char *prog_name = "kprobe/sys_nanosleep"; - const char *file = "./test_perf_buffer.o"; + int err, on_len, nr_on_cpus = 0, nr_cpus, i, duration = 0; struct perf_buffer_opts pb_opts = {}; - struct bpf_map *perf_buf_map; + struct test_perf_buffer *skel; cpu_set_t cpu_set, cpu_seen; - struct bpf_program *prog; - struct bpf_object *obj; struct perf_buffer *pb; - struct bpf_link *link; bool *online; nr_cpus = libbpf_num_possible_cpus(); @@ -51,33 +47,21 @@ void test_perf_buffer(void) nr_on_cpus++; /* load program */ - err = bpf_prog_load(file, BPF_PROG_TYPE_KPROBE, &obj, &prog_fd); - if (CHECK(err, "obj_load", "err %d errno %d\n", err, errno)) { - obj = NULL; - goto out_close; - } - - prog = bpf_object__find_program_by_title(obj, prog_name); - if (CHECK(!prog, "find_probe", "prog '%s' not found\n", prog_name)) + skel = test_perf_buffer__open_and_load(); + if (CHECK(!skel, "skel_load", "skeleton open/load failed\n")) goto out_close; - /* load map */ - perf_buf_map = bpf_object__find_map_by_name(obj, "perf_buf_map"); - if (CHECK(!perf_buf_map, "find_perf_buf_map", "not found\n")) - goto out_close; - - /* attach kprobe */ - link = bpf_program__attach_kprobe(prog, false /* retprobe */, - SYS_NANOSLEEP_KPROBE_NAME); - if (CHECK(IS_ERR(link), "attach_kprobe", "err %ld\n", PTR_ERR(link))) + /* attach probe */ + err = test_perf_buffer__attach(skel); + if (CHECK(err, "attach_kprobe", "err %d\n", err)) goto out_close; /* set up perf buffer */ pb_opts.sample_cb = on_sample; pb_opts.ctx = &cpu_seen; - pb = perf_buffer__new(bpf_map__fd(perf_buf_map), 1, &pb_opts); + pb = perf_buffer__new(bpf_map__fd(skel->maps.perf_buf_map), 1, &pb_opts); if (CHECK(IS_ERR(pb), "perf_buf__new", "err %ld\n", PTR_ERR(pb))) - goto out_detach; + goto out_close; /* trigger kprobe on every CPU */ CPU_ZERO(&cpu_seen); @@ -94,7 +78,7 @@ void test_perf_buffer(void) &cpu_set); if (err && CHECK(err, "set_affinity", "cpu #%d, err %d\n", i, err)) - goto out_detach; + goto out_close; usleep(1); } @@ -110,9 +94,7 @@ void test_perf_buffer(void) out_free_pb: perf_buffer__free(pb); -out_detach: - bpf_link__destroy(link); out_close: - bpf_object__close(obj); + test_perf_buffer__destroy(skel); free(online); } diff --git a/tools/testing/selftests/bpf/progs/test_perf_buffer.c b/tools/testing/selftests/bpf/progs/test_perf_buffer.c index ad59c4c9aba8..8207a2dc2f9d 100644 --- a/tools/testing/selftests/bpf/progs/test_perf_buffer.c +++ b/tools/testing/selftests/bpf/progs/test_perf_buffer.c @@ -12,8 +12,8 @@ struct { __uint(value_size, sizeof(int)); } perf_buf_map SEC(".maps"); -SEC("kprobe/sys_nanosleep") -int BPF_KPROBE(handle_sys_nanosleep_entry) +SEC("tp/raw_syscalls/sys_enter") +int handle_sys_enter(void *ctx) { int cpu = bpf_get_smp_processor_id(); -- cgit v1.2.3 From df62f2ec3df698e16bdc3dd44de1d337a9eac6b3 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 9 Jul 2020 15:12:42 +0200 Subject: selftests/mptcp: add diag interface tests basic functional test, triggering the msk diag interface code. Require appropriate iproute2 support, skip elsewhere. Reviewed-by: Mat Martineau Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- tools/testing/selftests/net/mptcp/Makefile | 2 +- tools/testing/selftests/net/mptcp/diag.sh | 121 ++++++++++++++++++++++ tools/testing/selftests/net/mptcp/mptcp_connect.c | 22 +++- 3 files changed, 140 insertions(+), 5 deletions(-) create mode 100755 tools/testing/selftests/net/mptcp/diag.sh (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index f50976ee7d44..aa254aefc2c3 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -5,7 +5,7 @@ KSFT_KHDR_INSTALL := 1 CFLAGS = -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include -TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh +TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh TEST_GEN_FILES = mptcp_connect pm_nl_ctl diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh new file mode 100755 index 000000000000..39edce4f541c --- /dev/null +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -0,0 +1,121 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) +ns="ns1-$rndh" +ksft_skip=4 +test_cnt=1 +ret=0 +pids=() + +flush_pids() +{ + # mptcp_connect in join mode will sleep a bit before completing, + # give it some time + sleep 1.1 + + for pid in ${pids[@]}; do + [ -d /proc/$pid ] && kill -SIGUSR1 $pid >/dev/null 2>&1 + done + pids=() +} + +cleanup() +{ + ip netns del $ns + for pid in ${pids[@]}; do + [ -d /proc/$pid ] && kill -9 $pid >/dev/null 2>&1 + done +} + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi +ss -h | grep -q MPTCP +if [ $? -ne 0 ];then + echo "SKIP: ss tool does not support MPTCP" + exit $ksft_skip +fi + +__chk_nr() +{ + local condition="$1" + local expected=$2 + local msg nr + + shift 2 + msg=$* + nr=$(ss -inmHMN $ns | $condition) + + printf "%-50s" "$msg" + if [ $nr != $expected ]; then + echo "[ fail ] expected $expected found $nr" + ret=$test_cnt + else + echo "[ ok ]" + fi + test_cnt=$((test_cnt+1)) +} + +chk_msk_nr() +{ + __chk_nr "grep -c token:" $* +} + +chk_msk_fallback_nr() +{ + __chk_nr "grep -c fallback" $* +} + +chk_msk_remote_key_nr() +{ + __chk_nr "grep -c remote_key" $* +} + + +trap cleanup EXIT +ip netns add $ns +ip -n $ns link set dev lo up + +echo "a" | ip netns exec $ns ./mptcp_connect -p 10000 -l 0.0.0.0 -t 100 >/dev/null & +sleep 0.1 +pids[0]=$! +chk_msk_nr 0 "no msk on netns creation" + +echo "b" | ip netns exec $ns ./mptcp_connect -p 10000 127.0.0.1 -j -t 100 >/dev/null & +sleep 0.1 +pids[1]=$! +chk_msk_nr 2 "after MPC handshake " +chk_msk_remote_key_nr 2 "....chk remote_key" +chk_msk_fallback_nr 0 "....chk no fallback" +flush_pids + + +echo "a" | ip netns exec $ns ./mptcp_connect -p 10001 -s TCP -l 0.0.0.0 -t 100 >/dev/null & +pids[0]=$! +sleep 0.1 +echo "b" | ip netns exec $ns ./mptcp_connect -p 10001 127.0.0.1 -j -t 100 >/dev/null & +pids[1]=$! +sleep 0.1 +chk_msk_fallback_nr 1 "check fallback" +flush_pids + +NR_CLIENTS=100 +for I in `seq 1 $NR_CLIENTS`; do + echo "a" | ip netns exec $ns ./mptcp_connect -p $((I+10001)) -l 0.0.0.0 -t 100 -w 10 >/dev/null & + pids[$((I*2))]=$! +done +sleep 0.1 + +for I in `seq 1 $NR_CLIENTS`; do + echo "b" | ip netns exec $ns ./mptcp_connect -p $((I+10001)) 127.0.0.1 -t 100 -w 10 >/dev/null & + pids[$((I*2 + 1))]=$! +done +sleep 1.5 + +chk_msk_nr $((NR_CLIENTS*2)) "many msk socket present" +flush_pids + +exit $ret diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index cedee5b952ba..cad6f73a5fd0 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include @@ -36,6 +37,7 @@ extern int optind; static int poll_timeout = 10 * 1000; static bool listen_mode; +static bool quit; enum cfg_mode { CFG_MODE_POLL, @@ -52,11 +54,12 @@ static int pf = AF_INET; static int cfg_sndbuf; static int cfg_rcvbuf; static bool cfg_join; +static int cfg_wait; static void die_usage(void) { fprintf(stderr, "Usage: mptcp_connect [-6] [-u] [-s MPTCP|TCP] [-p port] [-m mode]" - "[-l] connect_address\n"); + "[-l] [-w sec] connect_address\n"); fprintf(stderr, "\t-6 use ipv6\n"); fprintf(stderr, "\t-t num -- set poll timeout to num\n"); fprintf(stderr, "\t-S num -- set SO_SNDBUF to num\n"); @@ -65,9 +68,15 @@ static void die_usage(void) fprintf(stderr, "\t-m [MPTCP|TCP] -- use tcp or mptcp sockets\n"); fprintf(stderr, "\t-s [mmap|poll] -- use poll (default) or mmap\n"); fprintf(stderr, "\t-u -- check mptcp ulp\n"); + fprintf(stderr, "\t-w num -- wait num sec before closing the socket\n"); exit(1); } +static void handle_signal(int nr) +{ + quit = true; +} + static const char *getxinfo_strerr(int err) { if (err == EAI_SYSTEM) @@ -418,8 +427,8 @@ static int copyfd_io_poll(int infd, int peerfd, int outfd) } /* leave some time for late join/announce */ - if (cfg_join) - usleep(400000); + if (cfg_wait) + usleep(cfg_wait); close(peerfd); return 0; @@ -812,11 +821,12 @@ static void parse_opts(int argc, char **argv) { int c; - while ((c = getopt(argc, argv, "6jlp:s:hut:m:S:R:")) != -1) { + while ((c = getopt(argc, argv, "6jlp:s:hut:m:S:R:w:")) != -1) { switch (c) { case 'j': cfg_join = true; cfg_mode = CFG_MODE_POLL; + cfg_wait = 400000; break; case 'l': listen_mode = true; @@ -850,6 +860,9 @@ static void parse_opts(int argc, char **argv) case 'R': cfg_rcvbuf = parse_int(optarg); break; + case 'w': + cfg_wait = atoi(optarg)*1000000; + break; } } @@ -865,6 +878,7 @@ int main(int argc, char *argv[]) { init_rng(); + signal(SIGUSR1, handle_signal); parse_opts(argc, argv); if (tcpulp_audit) -- cgit v1.2.3 From f3348a82e72795ce218264fd00ef5cf5137836a9 Mon Sep 17 00:00:00 2001 From: Danielle Ratson Date: Thu, 9 Jul 2020 16:18:22 +0300 Subject: selftests: net: Add port split test Test port split configuration using previously added number of port lanes attribute. Check that all the splittable ports are successfully split to their maximum number of lanes and below, and that those which are not splittable fail to be split. Test output example: TEST: swp4 is unsplittable [ OK ] TEST: split port swp53 into 4 [ OK ] TEST: Unsplit port pci/0000:03:00.0/25 [ OK ] TEST: split port swp53 into 2 [ OK ] TEST: Unsplit port pci/0000:03:00.0/25 [ OK ] Signed-off-by: Danielle Ratson Reviewed-by: Petr Machata Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- tools/testing/selftests/net/Makefile | 1 + tools/testing/selftests/net/devlink_port_split.py | 277 ++++++++++++++++++++++ 2 files changed, 278 insertions(+) create mode 100755 tools/testing/selftests/net/devlink_port_split.py (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index bfacb960450f..9491bbaa0831 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -18,6 +18,7 @@ TEST_PROGS += reuseaddr_ports_exhausted.sh TEST_PROGS += txtimestamp.sh TEST_PROGS += vrf-xfrm-tests.sh TEST_PROGS += rxtimestamp.sh +TEST_PROGS += devlink_port_split.py TEST_PROGS_EXTENDED := in_netns.sh TEST_GEN_FILES = socket nettest TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any diff --git a/tools/testing/selftests/net/devlink_port_split.py b/tools/testing/selftests/net/devlink_port_split.py new file mode 100755 index 000000000000..58bb7e9b88ce --- /dev/null +++ b/tools/testing/selftests/net/devlink_port_split.py @@ -0,0 +1,277 @@ +#!/usr/bin/python3 +# SPDX-License-Identifier: GPL-2.0 + +from subprocess import PIPE, Popen +import json +import time +import argparse +import collections +import sys + +# +# Test port split configuration using devlink-port lanes attribute. +# The test is skipped in case the attribute is not available. +# +# First, check that all the ports with 1 lane fail to split. +# Second, check that all the ports with more than 1 lane can be split +# to all valid configurations (e.g., split to 2, split to 4 etc.) +# + + +Port = collections.namedtuple('Port', 'bus_info name') + + +def run_command(cmd, should_fail=False): + """ + Run a command in subprocess. + Return: Tuple of (stdout, stderr). + """ + + p = Popen(cmd, stdout=PIPE, stderr=PIPE, shell=True) + stdout, stderr = p.communicate() + stdout, stderr = stdout.decode(), stderr.decode() + + if stderr != "" and not should_fail: + print("Error sending command: %s" % cmd) + print(stdout) + print(stderr) + return stdout, stderr + + +class devlink_ports(object): + """ + Class that holds information on the devlink ports, required to the tests; + if_names: A list of interfaces in the devlink ports. + """ + + def get_if_names(dev): + """ + Get a list of physical devlink ports. + Return: Array of tuples (bus_info/port, if_name). + """ + + arr = [] + + cmd = "devlink -j port show" + stdout, stderr = run_command(cmd) + assert stderr == "" + ports = json.loads(stdout)['port'] + + for port in ports: + if dev in port: + if ports[port]['flavour'] == 'physical': + arr.append(Port(bus_info=port, name=ports[port]['netdev'])) + + return arr + + def __init__(self, dev): + self.if_names = devlink_ports.get_if_names(dev) + + +def get_max_lanes(port): + """ + Get the $port's maximum number of lanes. + Return: number of lanes, e.g. 1, 2, 4 and 8. + """ + + cmd = "devlink -j port show %s" % port + stdout, stderr = run_command(cmd) + assert stderr == "" + values = list(json.loads(stdout)['port'].values())[0] + + if 'lanes' in values: + lanes = values['lanes'] + else: + lanes = 0 + return lanes + + +def get_split_ability(port): + """ + Get the $port split ability. + Return: split ability, true or false. + """ + + cmd = "devlink -j port show %s" % port.name + stdout, stderr = run_command(cmd) + assert stderr == "" + values = list(json.loads(stdout)['port'].values())[0] + + return values['splittable'] + + +def split(k, port, should_fail=False): + """ + Split $port into $k ports. + If should_fail == True, the split should fail. Otherwise, should pass. + Return: Array of sub ports after splitting. + If the $port wasn't split, the array will be empty. + """ + + cmd = "devlink port split %s count %s" % (port.bus_info, k) + stdout, stderr = run_command(cmd, should_fail=should_fail) + + if should_fail: + if not test(stderr != "", "%s is unsplittable" % port.name): + print("split an unsplittable port %s" % port.name) + return create_split_group(port, k) + else: + if stderr == "": + return create_split_group(port, k) + print("didn't split a splittable port %s" % port.name) + + return [] + + +def unsplit(port): + """ + Unsplit $port. + """ + + cmd = "devlink port unsplit %s" % port + stdout, stderr = run_command(cmd) + test(stderr == "", "Unsplit port %s" % port) + + +def exists(port, dev): + """ + Check if $port exists in the devlink ports. + Return: True is so, False otherwise. + """ + + return any(dev_port.name == port + for dev_port in devlink_ports.get_if_names(dev)) + + +def exists_and_lanes(ports, lanes, dev): + """ + Check if every port in the list $ports exists in the devlink ports and has + $lanes number of lanes after splitting. + Return: True if both are True, False otherwise. + """ + + for port in ports: + max_lanes = get_max_lanes(port) + if not exists(port, dev): + print("port %s doesn't exist in devlink ports" % port) + return False + if max_lanes != lanes: + print("port %s has %d lanes, but %s were expected" + % (port, lanes, max_lanes)) + return False + return True + + +def test(cond, msg): + """ + Check $cond and print a message accordingly. + Return: True is pass, False otherwise. + """ + + if cond: + print("TEST: %-60s [ OK ]" % msg) + else: + print("TEST: %-60s [FAIL]" % msg) + + return cond + + +def create_split_group(port, k): + """ + Create the split group for $port. + Return: Array with $k elements, which are the split port group. + """ + + return list(port.name + "s" + str(i) for i in range(k)) + + +def split_unsplittable_port(port, k): + """ + Test that splitting of unsplittable port fails. + """ + + # split to max + new_split_group = split(k, port, should_fail=True) + + if new_split_group != []: + unsplit(port.bus_info) + + +def split_splittable_port(port, k, lanes, dev): + """ + Test that splitting of splittable port passes correctly. + """ + + new_split_group = split(k, port) + + # Once the split command ends, it takes some time to the sub ifaces' + # to get their names. Use udevadm to continue only when all current udev + # events are handled. + cmd = "udevadm settle" + stdout, stderr = run_command(cmd) + assert stderr == "" + + if new_split_group != []: + test(exists_and_lanes(new_split_group, lanes/k, dev), + "split port %s into %s" % (port.name, k)) + + unsplit(port.bus_info) + + +def make_parser(): + parser = argparse.ArgumentParser(description='A test for port splitting.') + parser.add_argument('--dev', + help='The devlink handle of the device under test. ' + + 'The default is the first registered devlink ' + + 'handle.') + + return parser + + +def main(cmdline=None): + parser = make_parser() + args = parser.parse_args(cmdline) + + dev = args.dev + if not dev: + cmd = "devlink -j dev show" + stdout, stderr = run_command(cmd) + assert stderr == "" + + devs = json.loads(stdout)['dev'] + dev = list(devs.keys())[0] + + cmd = "devlink dev show %s" % dev + stdout, stderr = run_command(cmd) + if stderr != "": + print("devlink device %s can not be found" % dev) + sys.exit(1) + + ports = devlink_ports(dev) + + for port in ports.if_names: + max_lanes = get_max_lanes(port.name) + + # If max lanes is 0, do not test port splitting at all + if max_lanes == 0: + continue + + # If 1 lane, shouldn't be able to split + elif max_lanes == 1: + test(not get_split_ability(port), + "%s should not be able to split" % port.name) + split_unsplittable_port(port, max_lanes) + + # Else, splitting should pass and all the split ports should exist. + else: + lane = max_lanes + test(get_split_ability(port), + "%s should be able to split" % port.name) + while lane > 1: + split_splittable_port(port, lane, max_lanes, dev) + + lane //= 2 + + +if __name__ == "__main__": + main() -- cgit v1.2.3 From 91f430b2c49d2d8f4445824f70a8cf7b73e1094c Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 9 Jul 2020 17:42:49 -0700 Subject: selftests: net: add a test for UDP tunnel info infra Add validating the UDP tunnel infra works. $ ./udp_tunnel_nic.sh PASSED all 383 checks Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- .../drivers/net/netdevsim/udp_tunnel_nic.sh | 786 +++++++++++++++++++++ 1 file changed, 786 insertions(+) create mode 100644 tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh new file mode 100644 index 000000000000..ba1d53b9f815 --- /dev/null +++ b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh @@ -0,0 +1,786 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0-only + +VNI_GEN=$RANDOM +NSIM_ID=$((RANDOM % 1024)) +NSIM_DEV_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_ID +NSIM_DEV_DFS=/sys/kernel/debug/netdevsim/netdevsim$NSIM_ID +NSIM_NETDEV= +HAS_ETHTOOL= +EXIT_STATUS=0 +num_cases=0 +num_errors=0 + +clean_up_devs=( ) + +function err_cnt { + echo "ERROR:" $@ + EXIT_STATUS=1 + ((num_errors++)) + ((num_cases++)) +} + +function pass_cnt { + ((num_cases++)) +} + +function cleanup_tuns { + for dev in "${clean_up_devs[@]}"; do + [ -e /sys/class/net/$dev ] && ip link del dev $dev + done + clean_up_devs=( ) +} + +function cleanup_nsim { + if [ -e $NSIM_DEV_SYS ]; then + echo $NSIM_ID > /sys/bus/netdevsim/del_device + fi +} + +function cleanup { + cleanup_tuns + cleanup_nsim +} + +trap cleanup EXIT + +function new_vxlan { + local dev=$1 + local dstport=$2 + local lower=$3 + local ipver=$4 + local flags=$5 + + local group ipfl + + [ "$ipver" != '6' ] && group=239.1.1.1 || group=fff1::1 + [ "$ipver" != '6' ] || ipfl="-6" + + [[ ! "$flags" =~ "external" ]] && flags="$flags id $((VNI_GEN++))" + + ip $ipfl link add $dev type vxlan \ + group $group \ + dev $lower \ + dstport $dstport \ + $flags + + ip link set dev $dev up + + clean_up_devs=("${clean_up_devs[@]}" $dev) + + check_tables +} + +function new_geneve { + local dev=$1 + local dstport=$2 + local ipver=$3 + local flags=$4 + + local group ipfl + + [ "$ipver" != '6' ] && remote=1.1.1.2 || group=::2 + [ "$ipver" != '6' ] || ipfl="-6" + + [[ ! "$flags" =~ "external" ]] && flags="$flags vni $((VNI_GEN++))" + + ip $ipfl link add $dev type geneve \ + remote $remote \ + dstport $dstport \ + $flags + + ip link set dev $dev up + + clean_up_devs=("${clean_up_devs[@]}" $dev) + + check_tables +} + +function del_dev { + local dev=$1 + + ip link del dev $dev + check_tables +} + +# Helpers for netdevsim port/type encoding +function mke { + local port=$1 + local type=$2 + + echo $((port << 16 | type)) +} + +function pre { + local val=$1 + + echo -e "port: $((val >> 16))\ttype: $((val & 0xffff))" +} + +function pre_ethtool { + local val=$1 + local port=$((val >> 16)) + local type=$((val & 0xffff)) + + case $type in + 1) + type_name="vxlan" + ;; + 2) + type_name="geneve" + ;; + 4) + type_name="vxlan-gpe" + ;; + *) + type_name="bit X" + ;; + esac + + echo "port $port, $type_name" +} + +function check_table { + local path=$NSIM_DEV_DFS/ports/$port/udp_ports_table$1 + local -n expected=$2 + local last=$3 + + read -a have < $path + + if [ ${#expected[@]} -ne ${#have[@]} ]; then + echo "check_table: BAD NUMBER OF ITEMS" + return 0 + fi + + for i in "${!expected[@]}"; do + if [ -n "$HAS_ETHTOOL" -a ${expected[i]} -ne 0 ]; then + pp_expected=`pre_ethtool ${expected[i]}` + ethtool --show-tunnels $NSIM_NETDEV | grep "$pp_expected" >/dev/null + if [ $? -ne 0 -a $last -ne 0 ]; then + err_cnt "ethtool table $1 on port $port: $pfx - $msg" + echo " check_table: ethtool does not contain '$pp_expected'" + ethtool --show-tunnels $NSIM_NETDEV + return 0 + + fi + fi + + if [ ${expected[i]} != ${have[i]} ]; then + if [ $last -ne 0 ]; then + err_cnt "table $1 on port $port: $pfx - $msg" + echo " check_table: wrong entry $i" + echo " expected: `pre ${expected[i]}`" + echo " have: `pre ${have[i]}`" + return 0 + fi + return 1 + fi + done + + pass_cnt + return 0 +} + +function check_tables { + # Need retries in case we have workqueue making the changes + local retries=10 + + while ! check_table 0 exp0 $((retries == 0)); do + sleep 0.02 + ((retries--)) + done + while ! check_table 1 exp1 $((retries == 0)); do + sleep 0.02 + ((retries--)) + done +} + +function print_table { + local path=$NSIM_DEV_DFS/ports/$port/udp_ports_table$1 + read -a have < $path + + tree $NSIM_DEV_DFS/ + + echo "Port $port table $1:" + + for i in "${!have[@]}"; do + echo " `pre ${have[i]}`" + done + +} + +function print_tables { + print_table 0 + print_table 1 +} + +function get_netdev_name { + local -n old=$1 + + new=$(ls /sys/class/net) + + for netdev in $new; do + for check in $old; do + [ $netdev == $check ] && break + done + + if [ $netdev != $check ]; then + echo $netdev + break + fi + done +} + +### +### Code start +### + +# Probe ethtool support +ethtool -h | grep show-tunnels 2>&1 >/dev/null && HAS_ETHTOOL=y + +modprobe netdevsim + +# Basic test +pfx="basic" + +for port in 0 1; do + old_netdevs=$(ls /sys/class/net) + if [ $port -eq 0 ]; then + echo $NSIM_ID > /sys/bus/netdevsim/new_device + else + echo 1 > $NSIM_DEV_DFS/udp_ports_open_only + echo 1 > $NSIM_DEV_DFS/udp_ports_sleep + echo 1 > $NSIM_DEV_SYS/new_port + fi + NSIM_NETDEV=`get_netdev_name old_netdevs` + + msg="new NIC device created" + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) + check_tables + + msg="VxLAN v4 devices" + exp0=( `mke 4789 1` 0 0 0 ) + new_vxlan vxlan0 4789 $NSIM_NETDEV + new_vxlan vxlan1 4789 $NSIM_NETDEV + + msg="VxLAN v4 devices go down" + exp0=( 0 0 0 0 ) + ifconfig vxlan1 down + ifconfig vxlan0 down + check_tables + + msg="VxLAN v6 devices" + exp0=( `mke 4789 1` 0 0 0 ) + new_vxlan vxlanA 4789 $NSIM_NETDEV 6 + + for ifc in vxlan0 vxlan1; do + ifconfig $ifc up + done + + new_vxlan vxlanB 4789 $NSIM_NETDEV 6 + + msg="another VxLAN v6 devices" + exp0=( `mke 4789 1` `mke 4790 1` 0 0 ) + new_vxlan vxlanC 4790 $NSIM_NETDEV 6 + + msg="Geneve device" + exp1=( `mke 6081 2` 0 0 0 ) + new_geneve gnv0 6081 + + msg="NIC device goes down" + ifconfig $NSIM_NETDEV down + if [ $port -eq 1 ]; then + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) + fi + check_tables + msg="NIC device goes up again" + ifconfig $NSIM_NETDEV up + exp0=( `mke 4789 1` `mke 4790 1` 0 0 ) + exp1=( `mke 6081 2` 0 0 0 ) + check_tables + + cleanup_tuns + + msg="tunnels destroyed" + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) + check_tables + + modprobe -r geneve + modprobe -r vxlan + modprobe -r udp_tunnel + + check_tables +done + +modprobe -r netdevsim + +# Module tests +pfx="module tests" + +if modinfo netdevsim | grep udp_tunnel >/dev/null; then + err_cnt "netdevsim depends on udp_tunnel" +else + pass_cnt +fi + +modprobe netdevsim + +old_netdevs=$(ls /sys/class/net) +port=0 +echo $NSIM_ID > /sys/bus/netdevsim/new_device +echo 0 > $NSIM_DEV_SYS/del_port +echo 1000 > $NSIM_DEV_DFS/udp_ports_sleep +echo 0 > $NSIM_DEV_SYS/new_port +NSIM_NETDEV=`get_netdev_name old_netdevs` + +msg="create VxLANs" +exp0=( 0 0 0 0 ) # sleep is longer than out wait +new_vxlan vxlan0 10000 $NSIM_NETDEV + +modprobe -r vxlan +modprobe -r udp_tunnel + +msg="remove tunnels" +exp0=( 0 0 0 0 ) +check_tables + +msg="create VxLANs" +exp0=( 0 0 0 0 ) # sleep is longer than out wait +new_vxlan vxlan0 10000 $NSIM_NETDEV + +exp0=( 0 0 0 0 ) + +modprobe -r netdevsim +modprobe netdevsim + +# Overflow the table + +function overflow_table0 { + local pfx=$1 + + msg="create VxLANs 1/5" + exp0=( `mke 10000 1` 0 0 0 ) + new_vxlan vxlan0 10000 $NSIM_NETDEV + + msg="create VxLANs 2/5" + exp0=( `mke 10000 1` `mke 10001 1` 0 0 ) + new_vxlan vxlan1 10001 $NSIM_NETDEV + + msg="create VxLANs 3/5" + exp0=( `mke 10000 1` `mke 10001 1` `mke 10002 1` 0 ) + new_vxlan vxlan2 10002 $NSIM_NETDEV + + msg="create VxLANs 4/5" + exp0=( `mke 10000 1` `mke 10001 1` `mke 10002 1` `mke 10003 1` ) + new_vxlan vxlan3 10003 $NSIM_NETDEV + + msg="create VxLANs 5/5" + new_vxlan vxlan4 10004 $NSIM_NETDEV +} + +function overflow_table1 { + local pfx=$1 + + msg="create GENEVE 1/5" + exp1=( `mke 20000 2` 0 0 0 ) + new_geneve gnv0 20000 + + msg="create GENEVE 2/5" + exp1=( `mke 20000 2` `mke 20001 2` 0 0 ) + new_geneve gnv1 20001 + + msg="create GENEVE 3/5" + exp1=( `mke 20000 2` `mke 20001 2` `mke 20002 2` 0 ) + new_geneve gnv2 20002 + + msg="create GENEVE 4/5" + exp1=( `mke 20000 2` `mke 20001 2` `mke 20002 2` `mke 20003 2` ) + new_geneve gnv3 20003 + + msg="create GENEVE 5/5" + new_geneve gnv4 20004 +} + +echo $NSIM_ID > /sys/bus/netdevsim/new_device +echo 0 > $NSIM_DEV_SYS/del_port + +for port in 0 1; do + if [ $port -ne 0 ]; then + echo 1 > $NSIM_DEV_DFS/udp_ports_open_only + echo 1 > $NSIM_DEV_DFS/udp_ports_sleep + fi + + echo $port > $NSIM_DEV_SYS/new_port + ifconfig $NSIM_NETDEV up + + overflow_table0 "overflow NIC table" + overflow_table1 "overflow NIC table" + + msg="replace VxLAN in overflow table" + exp0=( `mke 10000 1` `mke 10004 1` `mke 10002 1` `mke 10003 1` ) + del_dev vxlan1 + + msg="vacate VxLAN in overflow table" + exp0=( `mke 10000 1` `mke 10004 1` 0 `mke 10003 1` ) + del_dev vxlan2 + + msg="replace GENEVE in overflow table" + exp1=( `mke 20000 2` `mke 20004 2` `mke 20002 2` `mke 20003 2` ) + del_dev gnv1 + + msg="vacate GENEVE in overflow table" + exp1=( `mke 20000 2` `mke 20004 2` 0 `mke 20003 2` ) + del_dev gnv2 + + msg="table sharing - share" + exp1=( `mke 20000 2` `mke 20004 2` `mke 30001 4` `mke 20003 2` ) + new_vxlan vxlanG0 30001 $NSIM_NETDEV 4 "gpe external" + + msg="table sharing - overflow" + new_vxlan vxlanG1 30002 $NSIM_NETDEV 4 "gpe external" + msg="table sharing - overflow v6" + new_vxlan vxlanG2 30002 $NSIM_NETDEV 6 "gpe external" + + exp1=( `mke 20000 2` `mke 30002 4` `mke 30001 4` `mke 20003 2` ) + del_dev gnv4 + + msg="destroy NIC" + echo $port > $NSIM_DEV_SYS/del_port + + cleanup_tuns + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) +done + +cleanup_nsim + +# Sync all +pfx="sync all" + +echo $NSIM_ID > /sys/bus/netdevsim/new_device +echo 0 > $NSIM_DEV_SYS/del_port +echo 1 > $NSIM_DEV_DFS/udp_ports_sync_all + +for port in 0 1; do + if [ $port -ne 0 ]; then + echo 1 > $NSIM_DEV_DFS/udp_ports_open_only + echo 1 > $NSIM_DEV_DFS/udp_ports_sleep + fi + + echo $port > $NSIM_DEV_SYS/new_port + ifconfig $NSIM_NETDEV up + + overflow_table0 "overflow NIC table" + overflow_table1 "overflow NIC table" + + msg="replace VxLAN in overflow table" + exp0=( `mke 10000 1` `mke 10004 1` `mke 10002 1` `mke 10003 1` ) + del_dev vxlan1 + + msg="vacate VxLAN in overflow table" + exp0=( `mke 10000 1` `mke 10004 1` 0 `mke 10003 1` ) + del_dev vxlan2 + + msg="replace GENEVE in overflow table" + exp1=( `mke 20000 2` `mke 20004 2` `mke 20002 2` `mke 20003 2` ) + del_dev gnv1 + + msg="vacate GENEVE in overflow table" + exp1=( `mke 20000 2` `mke 20004 2` 0 `mke 20003 2` ) + del_dev gnv2 + + msg="table sharing - share" + exp1=( `mke 20000 2` `mke 20004 2` `mke 30001 4` `mke 20003 2` ) + new_vxlan vxlanG0 30001 $NSIM_NETDEV 4 "gpe external" + + msg="table sharing - overflow" + new_vxlan vxlanG1 30002 $NSIM_NETDEV 4 "gpe external" + msg="table sharing - overflow v6" + new_vxlan vxlanG2 30002 $NSIM_NETDEV 6 "gpe external" + + exp1=( `mke 20000 2` `mke 30002 4` `mke 30001 4` `mke 20003 2` ) + del_dev gnv4 + + msg="destroy NIC" + echo $port > $NSIM_DEV_SYS/del_port + + cleanup_tuns + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) +done + +cleanup_nsim + +# Destroy full NIC +pfx="destroy full" + +echo $NSIM_ID > /sys/bus/netdevsim/new_device +echo 0 > $NSIM_DEV_SYS/del_port + +for port in 0 1; do + if [ $port -ne 0 ]; then + echo 1 > $NSIM_DEV_DFS/udp_ports_open_only + echo 1 > $NSIM_DEV_DFS/udp_ports_sleep + fi + + echo $port > $NSIM_DEV_SYS/new_port + ifconfig $NSIM_NETDEV up + + overflow_table0 "destroy NIC" + overflow_table1 "destroy NIC" + + msg="destroy NIC" + echo $port > $NSIM_DEV_SYS/del_port + + cleanup_tuns + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) +done + +cleanup_nsim + +# IPv4 only +pfx="IPv4 only" + +echo $NSIM_ID > /sys/bus/netdevsim/new_device +echo 0 > $NSIM_DEV_SYS/del_port +echo 1 > $NSIM_DEV_DFS/udp_ports_ipv4_only + +for port in 0 1; do + if [ $port -ne 0 ]; then + echo 1 > $NSIM_DEV_DFS/udp_ports_open_only + echo 1 > $NSIM_DEV_DFS/udp_ports_sleep + fi + + echo $port > $NSIM_DEV_SYS/new_port + ifconfig $NSIM_NETDEV up + + msg="create VxLANs v6" + new_vxlan vxlanA0 10000 $NSIM_NETDEV 6 + + msg="create VxLANs v6" + new_vxlan vxlanA1 10000 $NSIM_NETDEV 6 + + ip link set dev vxlanA0 down + ip link set dev vxlanA0 up + check_tables + + msg="create VxLANs v4" + exp0=( `mke 10000 1` 0 0 0 ) + new_vxlan vxlan0 10000 $NSIM_NETDEV + + msg="down VxLANs v4" + exp0=( 0 0 0 0 ) + ip link set dev vxlan0 down + check_tables + + msg="up VxLANs v4" + exp0=( `mke 10000 1` 0 0 0 ) + ip link set dev vxlan0 up + check_tables + + msg="destroy VxLANs v4" + exp0=( 0 0 0 0 ) + del_dev vxlan0 + + msg="recreate VxLANs v4" + exp0=( `mke 10000 1` 0 0 0 ) + new_vxlan vxlan0 10000 $NSIM_NETDEV + + del_dev vxlanA0 + del_dev vxlanA1 + + msg="destroy NIC" + echo $port > $NSIM_DEV_SYS/del_port + + cleanup_tuns + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) +done + +cleanup_nsim + +# Failures +pfx="error injection" + +echo $NSIM_ID > /sys/bus/netdevsim/new_device +echo 0 > $NSIM_DEV_SYS/del_port + +for port in 0 1; do + if [ $port -ne 0 ]; then + echo 1 > $NSIM_DEV_DFS/udp_ports_open_only + echo 1 > $NSIM_DEV_DFS/udp_ports_sleep + fi + + echo $port > $NSIM_DEV_SYS/new_port + ifconfig $NSIM_NETDEV up + + echo 110 > $NSIM_DEV_DFS/ports/$port/udp_ports_inject_error + + msg="1 - create VxLANs v6" + exp0=( 0 0 0 0 ) + new_vxlan vxlanA0 10000 $NSIM_NETDEV 6 + + msg="1 - create VxLANs v4" + exp0=( `mke 10000 1` 0 0 0 ) + new_vxlan vxlan0 10000 $NSIM_NETDEV + + msg="1 - remove VxLANs v4" + del_dev vxlan0 + + msg="1 - remove VxLANs v6" + exp0=( 0 0 0 0 ) + del_dev vxlanA0 + + msg="2 - create GENEVE" + exp1=( `mke 20000 2` 0 0 0 ) + new_geneve gnv0 20000 + + msg="2 - destroy GENEVE" + echo 2 > $NSIM_DEV_DFS/ports/$port/udp_ports_inject_error + exp1=( `mke 20000 2` 0 0 0 ) + del_dev gnv0 + + msg="2 - create second GENEVE" + exp1=( 0 `mke 20001 2` 0 0 ) + new_geneve gnv0 20001 + + msg="destroy NIC" + echo $port > $NSIM_DEV_SYS/del_port + + cleanup_tuns + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) +done + +cleanup_nsim + +# netdev flags +pfx="netdev flags" + +echo $NSIM_ID > /sys/bus/netdevsim/new_device +echo 0 > $NSIM_DEV_SYS/del_port + +for port in 0 1; do + if [ $port -ne 0 ]; then + echo 1 > $NSIM_DEV_DFS/udp_ports_open_only + echo 1 > $NSIM_DEV_DFS/udp_ports_sleep + fi + + echo $port > $NSIM_DEV_SYS/new_port + ifconfig $NSIM_NETDEV up + + msg="create VxLANs v6" + exp0=( `mke 10000 1` 0 0 0 ) + new_vxlan vxlanA0 10000 $NSIM_NETDEV 6 + + msg="create VxLANs v4" + new_vxlan vxlan0 10000 $NSIM_NETDEV + + msg="turn off" + exp0=( 0 0 0 0 ) + ethtool -K $NSIM_NETDEV rx-udp_tunnel-port-offload off + check_tables + + msg="turn on" + exp0=( `mke 10000 1` 0 0 0 ) + ethtool -K $NSIM_NETDEV rx-udp_tunnel-port-offload on + check_tables + + msg="remove both" + del_dev vxlanA0 + exp0=( 0 0 0 0 ) + del_dev vxlan0 + check_tables + + ethtool -K $NSIM_NETDEV rx-udp_tunnel-port-offload off + + msg="create VxLANs v4 - off" + exp0=( 0 0 0 0 ) + new_vxlan vxlan0 10000 $NSIM_NETDEV + + msg="created off - turn on" + exp0=( `mke 10000 1` 0 0 0 ) + ethtool -K $NSIM_NETDEV rx-udp_tunnel-port-offload on + check_tables + + msg="destroy NIC" + echo $port > $NSIM_DEV_SYS/del_port + + cleanup_tuns + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) +done + +cleanup_nsim + +# device initiated reset +pfx="reset notification" + +echo $NSIM_ID > /sys/bus/netdevsim/new_device +echo 0 > $NSIM_DEV_SYS/del_port + +for port in 0 1; do + if [ $port -ne 0 ]; then + echo 1 > $NSIM_DEV_DFS/udp_ports_open_only + echo 1 > $NSIM_DEV_DFS/udp_ports_sleep + fi + + echo $port > $NSIM_DEV_SYS/new_port + ifconfig $NSIM_NETDEV up + + msg="create VxLANs v6" + exp0=( `mke 10000 1` 0 0 0 ) + new_vxlan vxlanA0 10000 $NSIM_NETDEV 6 + + msg="create VxLANs v4" + new_vxlan vxlan0 10000 $NSIM_NETDEV + + echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset + check_tables + + msg="NIC device goes down" + ifconfig $NSIM_NETDEV down + if [ $port -eq 1 ]; then + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) + fi + check_tables + + echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset + check_tables + + msg="NIC device goes up again" + ifconfig $NSIM_NETDEV up + exp0=( `mke 10000 1` 0 0 0 ) + check_tables + + msg="remove both" + del_dev vxlanA0 + exp0=( 0 0 0 0 ) + del_dev vxlan0 + check_tables + + echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset + check_tables + + msg="destroy NIC" + echo $port > $NSIM_DEV_SYS/del_port + + cleanup_tuns + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) +done + +modprobe -r netdevsim + +if [ $num_errors -eq 0 ]; then + echo "PASSED all $num_cases checks" +else + echo "FAILED $num_errors/$num_cases checks" +fi + +exit $EXIT_STATUS -- cgit v1.2.3 From cc15a20d5f3abc3cbd7911b70156b7b9e2bc7d41 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Sat, 11 Jul 2020 23:53:29 +0200 Subject: selftests/bpf: Add test for resolve_btfids Adding resolve_btfids test under test_progs suite. It's possible to use btf_ids.h header and its logic in user space application, so we can add easy test for it. The test defines BTF_ID_LIST and checks it gets properly resolved. For this reason the test_progs binary (and other binaries that use TRUNNER* macros) is processed with resolve_btfids tool, which resolves BTF IDs in .BTF_ids section. The BTF data are taken from btf_data.o object rceated from progs/btf_data.c. Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Tested-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200711215329.41165-10-jolsa@kernel.org --- tools/testing/selftests/bpf/Makefile | 15 ++- .../selftests/bpf/prog_tests/resolve_btfids.c | 111 +++++++++++++++++++++ tools/testing/selftests/bpf/progs/btf_data.c | 50 ++++++++++ 3 files changed, 175 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/bpf/prog_tests/resolve_btfids.c create mode 100644 tools/testing/selftests/bpf/progs/btf_data.c (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 1f9c696b3edf..e7a8cf83ba48 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -111,6 +111,7 @@ SCRATCH_DIR := $(OUTPUT)/tools BUILD_DIR := $(SCRATCH_DIR)/build INCLUDE_DIR := $(SCRATCH_DIR)/include BPFOBJ := $(BUILD_DIR)/libbpf/libbpf.a +RESOLVE_BTFIDS := $(BUILD_DIR)/resolve_btfids/resolve_btfids # Define simple and short `make test_progs`, `make test_sysctl`, etc targets # to build individual tests. @@ -177,7 +178,7 @@ $(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \ $(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(BUILD_DIR)/libbpf/ \ DESTDIR=$(SCRATCH_DIR) prefix= all install_headers -$(BUILD_DIR)/libbpf $(BUILD_DIR)/bpftool $(INCLUDE_DIR): +$(BUILD_DIR)/libbpf $(BUILD_DIR)/bpftool $(BUILD_DIR)/resolve_btfids $(INCLUDE_DIR): $(call msg,MKDIR,,$@) mkdir -p $@ @@ -190,6 +191,16 @@ else cp "$(VMLINUX_H)" $@ endif +$(RESOLVE_BTFIDS): $(BPFOBJ) | $(BUILD_DIR)/resolve_btfids \ + $(TOOLSDIR)/bpf/resolve_btfids/main.c \ + $(TOOLSDIR)/lib/rbtree.c \ + $(TOOLSDIR)/lib/zalloc.c \ + $(TOOLSDIR)/lib/string.c \ + $(TOOLSDIR)/lib/ctype.c \ + $(TOOLSDIR)/lib/str_error_r.c + $(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/resolve_btfids \ + OUTPUT=$(BUILD_DIR)/resolve_btfids/ BPFOBJ=$(BPFOBJ) + # Get Clang's default includes on this system, as opposed to those seen by # '-target bpf'. This fixes "missing" files on some architectures/distros, # such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc. @@ -352,9 +363,11 @@ endif $(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS) \ $(TRUNNER_EXTRA_OBJS) $$(BPFOBJ) \ + $(RESOLVE_BTFIDS) \ | $(TRUNNER_BINARY)-extras $$(call msg,BINARY,,$$@) $$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) -o $$@ + $(RESOLVE_BTFIDS) --no-fail --btf btf_data.o $$@ endef diff --git a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c new file mode 100644 index 000000000000..403be6f36cba --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c @@ -0,0 +1,111 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include +#include +#include +#include +#include +#include "test_progs.h" + +static int duration; + +struct symbol { + const char *name; + int type; + int id; +}; + +struct symbol test_symbols[] = { + { "unused", BTF_KIND_UNKN, 0 }, + { "S", BTF_KIND_TYPEDEF, -1 }, + { "T", BTF_KIND_TYPEDEF, -1 }, + { "U", BTF_KIND_TYPEDEF, -1 }, + { "S", BTF_KIND_STRUCT, -1 }, + { "U", BTF_KIND_UNION, -1 }, + { "func", BTF_KIND_FUNC, -1 }, +}; + +BTF_ID_LIST(test_list) +BTF_ID_UNUSED +BTF_ID(typedef, S) +BTF_ID(typedef, T) +BTF_ID(typedef, U) +BTF_ID(struct, S) +BTF_ID(union, U) +BTF_ID(func, func) + +static int +__resolve_symbol(struct btf *btf, int type_id) +{ + const struct btf_type *type; + const char *str; + unsigned int i; + + type = btf__type_by_id(btf, type_id); + if (!type) { + PRINT_FAIL("Failed to get type for ID %d\n", type_id); + return -1; + } + + for (i = 0; i < ARRAY_SIZE(test_symbols); i++) { + if (test_symbols[i].id != -1) + continue; + + if (BTF_INFO_KIND(type->info) != test_symbols[i].type) + continue; + + str = btf__name_by_offset(btf, type->name_off); + if (!str) { + PRINT_FAIL("Failed to get name for BTF ID %d\n", type_id); + return -1; + } + + if (!strcmp(str, test_symbols[i].name)) + test_symbols[i].id = type_id; + } + + return 0; +} + +static int resolve_symbols(void) +{ + struct btf *btf; + int type_id; + __u32 nr; + + btf = btf__parse_elf("btf_data.o", NULL); + if (CHECK(libbpf_get_error(btf), "resolve", + "Failed to load BTF from btf_data.o\n")) + return -1; + + nr = btf__get_nr_types(btf); + + for (type_id = 1; type_id <= nr; type_id++) { + if (__resolve_symbol(btf, type_id)) + break; + } + + btf__free(btf); + return 0; +} + +int test_resolve_btfids(void) +{ + unsigned int i; + int ret = 0; + + if (resolve_symbols()) + return -1; + + /* Check BTF_ID_LIST(test_list) IDs */ + for (i = 0; i < ARRAY_SIZE(test_symbols) && !ret; i++) { + ret = CHECK(test_list[i] != test_symbols[i].id, + "id_check", + "wrong ID for %s (%d != %d)\n", test_symbols[i].name, + test_list[i], test_symbols[i].id); + } + + return ret; +} diff --git a/tools/testing/selftests/bpf/progs/btf_data.c b/tools/testing/selftests/bpf/progs/btf_data.c new file mode 100644 index 000000000000..baa525275bde --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf_data.c @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +struct S { + int a; + int b; + int c; +}; + +union U { + int a; + int b; + int c; +}; + +struct S1 { + int a; + int b; + int c; +}; + +union U1 { + int a; + int b; + int c; +}; + +typedef int T; +typedef int S; +typedef int U; +typedef int T1; +typedef int S1; +typedef int U1; + +struct root_struct { + S m_1; + T m_2; + U m_3; + S1 m_4; + T1 m_5; + U1 m_6; + struct S m_7; + struct S1 m_8; + union U m_9; + union U1 m_10; +}; + +int func(struct root_struct *root) +{ + return 0; +} -- cgit v1.2.3 From 59e8b60bf068180fcadb0ae06ce8f6f835132ce6 Mon Sep 17 00:00:00 2001 From: Alan Maguire Date: Mon, 13 Jul 2020 12:52:34 +0100 Subject: selftests/bpf: Add selftests verifying bpf_trace_printk() behaviour Simple selftests that verifies bpf_trace_printk() returns a sensible value and tracing messages appear. Signed-off-by: Alan Maguire Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/1594641154-18897-3-git-send-email-alan.maguire@oracle.com --- .../selftests/bpf/prog_tests/trace_printk.c | 75 ++++++++++++++++++++++ tools/testing/selftests/bpf/progs/trace_printk.c | 21 ++++++ 2 files changed, 96 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/trace_printk.c create mode 100644 tools/testing/selftests/bpf/progs/trace_printk.c (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/trace_printk.c b/tools/testing/selftests/bpf/prog_tests/trace_printk.c new file mode 100644 index 000000000000..39b0decb1bb2 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/trace_printk.c @@ -0,0 +1,75 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020, Oracle and/or its affiliates. */ + +#include + +#include "trace_printk.skel.h" + +#define TRACEBUF "/sys/kernel/debug/tracing/trace_pipe" +#define SEARCHMSG "testing,testing" + +void test_trace_printk(void) +{ + int err, iter = 0, duration = 0, found = 0; + struct trace_printk__bss *bss; + struct trace_printk *skel; + char *buf = NULL; + FILE *fp = NULL; + size_t buflen; + + skel = trace_printk__open(); + if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) + return; + + err = trace_printk__load(skel); + if (CHECK(err, "skel_load", "failed to load skeleton: %d\n", err)) + goto cleanup; + + bss = skel->bss; + + err = trace_printk__attach(skel); + if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) + goto cleanup; + + fp = fopen(TRACEBUF, "r"); + if (CHECK(fp == NULL, "could not open trace buffer", + "error %d opening %s", errno, TRACEBUF)) + goto cleanup; + + /* We do not want to wait forever if this test fails... */ + fcntl(fileno(fp), F_SETFL, O_NONBLOCK); + + /* wait for tracepoint to trigger */ + usleep(1); + trace_printk__detach(skel); + + if (CHECK(bss->trace_printk_ran == 0, + "bpf_trace_printk never ran", + "ran == %d", bss->trace_printk_ran)) + goto cleanup; + + if (CHECK(bss->trace_printk_ret <= 0, + "bpf_trace_printk returned <= 0 value", + "got %d", bss->trace_printk_ret)) + goto cleanup; + + /* verify our search string is in the trace buffer */ + while (getline(&buf, &buflen, fp) >= 0 || errno == EAGAIN) { + if (strstr(buf, SEARCHMSG) != NULL) + found++; + if (found == bss->trace_printk_ran) + break; + if (++iter > 1000) + break; + } + + if (CHECK(!found, "message from bpf_trace_printk not found", + "no instance of %s in %s", SEARCHMSG, TRACEBUF)) + goto cleanup; + +cleanup: + trace_printk__destroy(skel); + free(buf); + if (fp) + fclose(fp); +} diff --git a/tools/testing/selftests/bpf/progs/trace_printk.c b/tools/testing/selftests/bpf/progs/trace_printk.c new file mode 100644 index 000000000000..8ca7f399b670 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/trace_printk.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020, Oracle and/or its affiliates. + +#include "vmlinux.h" +#include +#include + +char _license[] SEC("license") = "GPL"; + +int trace_printk_ret = 0; +int trace_printk_ran = 0; + +SEC("tp/raw_syscalls/sys_enter") +int sys_enter(void *ctx) +{ + static const char fmt[] = "testing,testing %d\n"; + + trace_printk_ret = bpf_trace_printk(fmt, sizeof(fmt), + ++trace_printk_ran); + return 0; +} -- cgit v1.2.3 From 0b20933d8cfe2bf6473e9b581b5d1ed9a2117ecc Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 13 Jul 2020 16:24:09 -0700 Subject: tools/bpftool: Strip away modifiers from global variables Reliably remove all the type modifiers from read-only (.rodata) global variable definitions, including cases of inner field const modifiers and arrays of const values. Also modify one of selftests to ensure that const volatile struct doesn't prevent user-space from modifying .rodata variable. Fixes: 985ead416df3 ("bpftool: Add skeleton codegen command") Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200713232409.3062144-3-andriin@fb.com --- tools/bpf/bpftool/gen.c | 23 ++++++++++------------- tools/lib/bpf/btf.h | 2 +- tools/testing/selftests/bpf/prog_tests/skeleton.c | 6 +++--- tools/testing/selftests/bpf/progs/test_skeleton.c | 6 ++++-- 4 files changed, 18 insertions(+), 19 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c index 10de76b296ba..b59d26e89367 100644 --- a/tools/bpf/bpftool/gen.c +++ b/tools/bpf/bpftool/gen.c @@ -88,7 +88,7 @@ static const char *get_map_ident(const struct bpf_map *map) return NULL; } -static void codegen_btf_dump_printf(void *ct, const char *fmt, va_list args) +static void codegen_btf_dump_printf(void *ctx, const char *fmt, va_list args) { vprintf(fmt, args); } @@ -104,17 +104,20 @@ static int codegen_datasec_def(struct bpf_object *obj, int i, err, off = 0, pad_cnt = 0, vlen = btf_vlen(sec); const char *sec_ident; char var_ident[256]; + bool strip_mods = false; - if (strcmp(sec_name, ".data") == 0) + if (strcmp(sec_name, ".data") == 0) { sec_ident = "data"; - else if (strcmp(sec_name, ".bss") == 0) + } else if (strcmp(sec_name, ".bss") == 0) { sec_ident = "bss"; - else if (strcmp(sec_name, ".rodata") == 0) + } else if (strcmp(sec_name, ".rodata") == 0) { sec_ident = "rodata"; - else if (strcmp(sec_name, ".kconfig") == 0) + strip_mods = true; + } else if (strcmp(sec_name, ".kconfig") == 0) { sec_ident = "kconfig"; - else + } else { return 0; + } printf(" struct %s__%s {\n", obj_name, sec_ident); for (i = 0; i < vlen; i++, sec_var++) { @@ -123,16 +126,10 @@ static int codegen_datasec_def(struct bpf_object *obj, DECLARE_LIBBPF_OPTS(btf_dump_emit_type_decl_opts, opts, .field_name = var_ident, .indent_level = 2, + .strip_mods = strip_mods, ); int need_off = sec_var->offset, align_off, align; __u32 var_type_id = var->type; - const struct btf_type *t; - - t = btf__type_by_id(btf, var_type_id); - while (btf_is_mod(t)) { - var_type_id = t->type; - t = btf__type_by_id(btf, var_type_id); - } if (off > need_off) { p_err("Something is wrong for %s's variable #%d: need offset %d, already at %d.\n", diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 227d3f844801..491c7b41ffdc 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -147,7 +147,7 @@ struct btf_dump_emit_type_decl_opts { /* strip all the const/volatile/restrict mods */ bool strip_mods; }; -#define btf_dump_emit_type_decl_opts__last_field indent_level +#define btf_dump_emit_type_decl_opts__last_field strip_mods LIBBPF_API int btf_dump__emit_type_decl(struct btf_dump *d, __u32 id, diff --git a/tools/testing/selftests/bpf/prog_tests/skeleton.c b/tools/testing/selftests/bpf/prog_tests/skeleton.c index fa153cf67b1b..fe87b77af459 100644 --- a/tools/testing/selftests/bpf/prog_tests/skeleton.c +++ b/tools/testing/selftests/bpf/prog_tests/skeleton.c @@ -41,7 +41,7 @@ void test_skeleton(void) CHECK(bss->in4 != 0, "in4", "got %lld != exp %lld\n", bss->in4, 0LL); CHECK(bss->out4 != 0, "out4", "got %lld != exp %lld\n", bss->out4, 0LL); - CHECK(rodata->in6 != 0, "in6", "got %d != exp %d\n", rodata->in6, 0); + CHECK(rodata->in.in6 != 0, "in6", "got %d != exp %d\n", rodata->in.in6, 0); CHECK(bss->out6 != 0, "out6", "got %d != exp %d\n", bss->out6, 0); /* validate we can pre-setup global variables, even in .bss */ @@ -49,7 +49,7 @@ void test_skeleton(void) data->in2 = 11; bss->in3 = 12; bss->in4 = 13; - rodata->in6 = 14; + rodata->in.in6 = 14; err = test_skeleton__load(skel); if (CHECK(err, "skel_load", "failed to load skeleton: %d\n", err)) @@ -60,7 +60,7 @@ void test_skeleton(void) CHECK(data->in2 != 11, "in2", "got %lld != exp %lld\n", data->in2, 11LL); CHECK(bss->in3 != 12, "in3", "got %d != exp %d\n", bss->in3, 12); CHECK(bss->in4 != 13, "in4", "got %lld != exp %lld\n", bss->in4, 13LL); - CHECK(rodata->in6 != 14, "in6", "got %d != exp %d\n", rodata->in6, 14); + CHECK(rodata->in.in6 != 14, "in6", "got %d != exp %d\n", rodata->in.in6, 14); /* now set new values and attach to get them into outX variables */ data->in1 = 1; diff --git a/tools/testing/selftests/bpf/progs/test_skeleton.c b/tools/testing/selftests/bpf/progs/test_skeleton.c index 77ae86f44db5..374ccef704e1 100644 --- a/tools/testing/selftests/bpf/progs/test_skeleton.c +++ b/tools/testing/selftests/bpf/progs/test_skeleton.c @@ -20,7 +20,9 @@ long long in4 __attribute__((aligned(64))) = 0; struct s in5 = {}; /* .rodata section */ -const volatile int in6 = 0; +const volatile struct { + const int in6; +} in = {}; /* .data section */ int out1 = -1; @@ -46,7 +48,7 @@ int handler(const void *ctx) out3 = in3; out4 = in4; out5 = in5; - out6 = in6; + out6 = in.in6; bpf_syscall = CONFIG_BPF_SYSCALL; kern_ver = LINUX_KERNEL_VERSION; -- cgit v1.2.3 From 1add92121e39ee5e4af21562eb59bd562c8033e3 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Sat, 11 Jul 2020 00:55:15 +0300 Subject: selftests: mlxsw: RED: Test offload of mirror on RED early_drop qevent Add a selftest for offloading a mirror action attached to the block associated with RED early_drop qevent. Signed-off-by: Petr Machata Signed-off-by: David S. Miller --- .../selftests/drivers/net/mlxsw/sch_red_core.sh | 106 ++++++++++++++++++++- .../selftests/drivers/net/mlxsw/sch_red_ets.sh | 11 +++ .../selftests/drivers/net/mlxsw/sch_red_root.sh | 8 ++ 3 files changed, 122 insertions(+), 3 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh index 0d347d48c112..45042105ead7 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh @@ -121,6 +121,7 @@ h1_destroy() h2_create() { host_create $h2 2 + tc qdisc add dev $h2 clsact # Some of the tests in this suite use multicast traffic. As this traffic # enters BR2_10 resp. BR2_11, it is flooded to all other ports. Thus @@ -141,6 +142,7 @@ h2_create() h2_destroy() { ethtool -s $h2 autoneg on + tc qdisc del dev $h2 clsact host_destroy $h2 } @@ -336,6 +338,17 @@ get_qdisc_npackets() qdisc_stats_get $swp3 $(get_qdisc_handle $vlan) .packets } +send_packets() +{ + local vlan=$1; shift + local proto=$1; shift + local pkts=$1; shift + + $MZ $h2.$vlan -p 8000 -a own -b $h3_mac \ + -A $(ipaddr 2 $vlan) -B $(ipaddr 3 $vlan) \ + -t $proto -q -c $pkts "$@" +} + # This sends traffic in an attempt to build a backlog of $size. Returns 0 on # success. After 10 failed attempts it bails out and returns 1. It dumps the # backlog size to stdout. @@ -364,9 +377,7 @@ build_backlog() return 1 fi - $MZ $h2.$vlan -p 8000 -a own -b $h3_mac \ - -A $(ipaddr 2 $vlan) -B $(ipaddr 3 $vlan) \ - -t $proto -q -c $pkts "$@" + send_packets $vlan $proto $pkts "$@" done } @@ -531,3 +542,92 @@ do_mc_backlog_test() log_test "TC $((vlan - 10)): Qdisc reports MC backlog" } + +do_drop_test() +{ + local vlan=$1; shift + local limit=$1; shift + local trigger=$1; shift + local subtest=$1; shift + local fetch_counter=$1; shift + local backlog + local base + local now + local pct + + RET=0 + + start_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) $h3_mac + + # Create a bit of a backlog and observe no mirroring due to drops. + qevent_rule_install_$subtest + base=$($fetch_counter) + + build_backlog $vlan $((2 * limit / 3)) udp >/dev/null + + busywait 1100 until_counter_is ">= $((base + 1))" $fetch_counter >/dev/null + check_fail $? "Spurious packets observed without buffer pressure" + + qevent_rule_uninstall_$subtest + + # Push to the queue until it's at the limit. The configured limit is + # rounded by the qdisc and then by the driver, so this is the best we + # can do to get to the real limit of the system. Do this with the rules + # uninstalled so that the inevitable drops don't get counted. + build_backlog $vlan $((3 * limit / 2)) udp >/dev/null + + qevent_rule_install_$subtest + base=$($fetch_counter) + + send_packets $vlan udp 11 + + now=$(busywait 1100 until_counter_is ">= $((base + 10))" $fetch_counter) + check_err $? "Dropped packets not observed: 11 expected, $((now - base)) seen" + + # When no extra traffic is injected, there should be no mirroring. + busywait 1100 until_counter_is ">= $((base + 20))" $fetch_counter >/dev/null + check_fail $? "Spurious packets observed" + + # When the rule is uninstalled, there should be no mirroring. + qevent_rule_uninstall_$subtest + send_packets $vlan udp 11 + busywait 1100 until_counter_is ">= $((base + 20))" $fetch_counter >/dev/null + check_fail $? "Spurious packets observed after uninstall" + + log_test "TC $((vlan - 10)): ${trigger}ped packets $subtest'd" + + stop_traffic + sleep 1 +} + +qevent_rule_install_mirror() +{ + tc filter add block 10 pref 1234 handle 102 matchall skip_sw \ + action mirred egress mirror dev $swp2 hw_stats disabled +} + +qevent_rule_uninstall_mirror() +{ + tc filter del block 10 pref 1234 handle 102 matchall +} + +qevent_counter_fetch_mirror() +{ + tc_rule_handle_stats_get "dev $h2 ingress" 101 +} + +do_drop_mirror_test() +{ + local vlan=$1; shift + local limit=$1; shift + local qevent_name=$1; shift + + tc filter add dev $h2 ingress pref 1 handle 101 prot ip \ + flower skip_sw ip_proto udp \ + action drop + + do_drop_test "$vlan" "$limit" "$qevent_name" mirror \ + qevent_counter_fetch_mirror + + tc filter del dev $h2 ingress pref 1 handle 101 flower +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh index 1c36c576613b..c8968b041bea 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh @@ -7,6 +7,7 @@ ALL_TESTS=" ecn_nodrop_test red_test mc_backlog_test + red_mirror_test " : ${QDISC:=ets} source sch_red_core.sh @@ -83,6 +84,16 @@ mc_backlog_test() uninstall_qdisc } +red_mirror_test() +{ + install_qdisc qevent early_drop block 10 + + do_drop_mirror_test 10 $BACKLOG1 early_drop + do_drop_mirror_test 11 $BACKLOG2 early_drop + + uninstall_qdisc +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh index 558667ea11ec..ede9c38d3eff 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh @@ -7,6 +7,7 @@ ALL_TESTS=" ecn_nodrop_test red_test mc_backlog_test + red_mirror_test " source sch_red_core.sh @@ -57,6 +58,13 @@ mc_backlog_test() uninstall_qdisc } +red_mirror_test() +{ + install_qdisc qevent early_drop block 10 + do_drop_mirror_test 10 $BACKLOG + uninstall_qdisc +} + trap cleanup EXIT setup_prepare -- cgit v1.2.3 From f7d40ee7eff8fde2b0701b80c2aa3ba354f8f520 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 13 Jul 2020 20:55:48 -0700 Subject: selftests/bpf: Fix merge conflict resolution Remove double definition of structs. Fixes: 71930d61025e ("Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net") Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/progs/bpf_iter_netlink.c | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c index b9c2756c5c97..7de98a68599a 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c @@ -7,20 +7,6 @@ char _license[] SEC("license") = "GPL"; -#define sk_rmem_alloc sk_backlog.rmem_alloc -#define sk_refcnt __sk_common.skc_refcnt - -struct bpf_iter_meta { - struct seq_file *seq; - __u64 session_id; - __u64 seq_num; -} __attribute__((preserve_access_index)); - -struct bpf_iter__netlink { - struct bpf_iter_meta *meta; - struct netlink_sock *sk; -} __attribute__((preserve_access_index)); - static __attribute__((noinline)) struct inode *SOCK_INODE(struct socket *socket) { return &container_of(socket, struct socket_alloc, socket)->vfs_inode; -- cgit v1.2.3 From afe231d32eb5fa4f4975596958c48c3a77fa1773 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 15 Jul 2020 11:27:30 +0300 Subject: selftests: forwarding: Add tc-police tests Test tc-police action in various scenarios such as Rx policing, Tx policing, shared policer and police piped to mirred. The test passes with both veth pairs and loopbacked ports. # ./tc_police.sh TEST: police on rx [ OK ] TEST: police on tx [ OK ] TEST: police with shared policer - rx [ OK ] TEST: police with shared policer - tx [ OK ] TEST: police rx and mirror [ OK ] TEST: police tx and mirror [ OK ] Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Signed-off-by: Jakub Kicinski --- .../testing/selftests/net/forwarding/tc_police.sh | 333 +++++++++++++++++++++ 1 file changed, 333 insertions(+) create mode 100755 tools/testing/selftests/net/forwarding/tc_police.sh (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/net/forwarding/tc_police.sh b/tools/testing/selftests/net/forwarding/tc_police.sh new file mode 100755 index 000000000000..160f9cccdfb7 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/tc_police.sh @@ -0,0 +1,333 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test tc-police action. +# +# +---------------------------------+ +# | H1 (vrf) | +# | + $h1 | +# | | 192.0.2.1/24 | +# | | | +# | | default via 192.0.2.2 | +# +----|----------------------------+ +# | +# +----|----------------------------------------------------------------------+ +# | SW | | +# | + $rp1 | +# | 192.0.2.2/24 | +# | | +# | 198.51.100.2/24 203.0.113.2/24 | +# | + $rp2 + $rp3 | +# | | | | +# +----|-----------------------------------------|----------------------------+ +# | | +# +----|----------------------------+ +----|----------------------------+ +# | | default via 198.51.100.2 | | | default via 203.0.113.2 | +# | | | | | | +# | | 198.51.100.1/24 | | | 203.0.113.1/24 | +# | + $h2 | | + $h3 | +# | H2 (vrf) | | H3 (vrf) | +# +---------------------------------+ +---------------------------------+ + +ALL_TESTS=" + police_rx_test + police_tx_test + police_shared_test + police_rx_mirror_test + police_tx_mirror_test +" +NUM_NETIFS=6 +source tc_common.sh +source lib.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/24 + + ip -4 route add default vrf v$h1 nexthop via 192.0.2.2 +} + +h1_destroy() +{ + ip -4 route del default vrf v$h1 nexthop via 192.0.2.2 + + simple_if_fini $h1 192.0.2.1/24 +} + +h2_create() +{ + simple_if_init $h2 198.51.100.1/24 + + ip -4 route add default vrf v$h2 nexthop via 198.51.100.2 + + tc qdisc add dev $h2 clsact +} + +h2_destroy() +{ + tc qdisc del dev $h2 clsact + + ip -4 route del default vrf v$h2 nexthop via 198.51.100.2 + + simple_if_fini $h2 198.51.100.1/24 +} + +h3_create() +{ + simple_if_init $h3 203.0.113.1/24 + + ip -4 route add default vrf v$h3 nexthop via 203.0.113.2 + + tc qdisc add dev $h3 clsact +} + +h3_destroy() +{ + tc qdisc del dev $h3 clsact + + ip -4 route del default vrf v$h3 nexthop via 203.0.113.2 + + simple_if_fini $h3 203.0.113.1/24 +} + +router_create() +{ + ip link set dev $rp1 up + ip link set dev $rp2 up + ip link set dev $rp3 up + + __addr_add_del $rp1 add 192.0.2.2/24 + __addr_add_del $rp2 add 198.51.100.2/24 + __addr_add_del $rp3 add 203.0.113.2/24 + + tc qdisc add dev $rp1 clsact + tc qdisc add dev $rp2 clsact +} + +router_destroy() +{ + tc qdisc del dev $rp2 clsact + tc qdisc del dev $rp1 clsact + + __addr_add_del $rp3 del 203.0.113.2/24 + __addr_add_del $rp2 del 198.51.100.2/24 + __addr_add_del $rp1 del 192.0.2.2/24 + + ip link set dev $rp3 down + ip link set dev $rp2 down + ip link set dev $rp1 down +} + +police_common_test() +{ + local test_name=$1; shift + + RET=0 + + # Rule to measure bandwidth on ingress of $h2 + tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \ + dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \ + action drop + + mausezahn $h1 -a own -b $(mac_get $rp1) -A 192.0.2.1 -B 198.51.100.1 \ + -t udp sp=12345,dp=54321 -p 1000 -c 0 -q & + + local t0=$(tc_rule_stats_get $h2 1 ingress .bytes) + sleep 10 + local t1=$(tc_rule_stats_get $h2 1 ingress .bytes) + + local er=$((80 * 1000 * 1000)) + local nr=$(rate $t0 $t1 10) + local nr_pct=$((100 * (nr - er) / er)) + ((-10 <= nr_pct && nr_pct <= 10)) + check_err $? "Expected rate $(humanize $er), got $(humanize $nr), which is $nr_pct% off. Required accuracy is +-10%." + + log_test "$test_name" + + { kill %% && wait %%; } 2>/dev/null + tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower +} + +police_rx_test() +{ + # Rule to police traffic destined to $h2 on ingress of $rp1 + tc filter add dev $rp1 ingress protocol ip pref 1 handle 101 flower \ + dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \ + action police rate 80mbit burst 16k conform-exceed drop/ok + + police_common_test "police on rx" + + tc filter del dev $rp1 ingress protocol ip pref 1 handle 101 flower +} + +police_tx_test() +{ + # Rule to police traffic destined to $h2 on egress of $rp2 + tc filter add dev $rp2 egress protocol ip pref 1 handle 101 flower \ + dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \ + action police rate 80mbit burst 16k conform-exceed drop/ok + + police_common_test "police on tx" + + tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower +} + +police_shared_common_test() +{ + local dport=$1; shift + local test_name=$1; shift + + RET=0 + + mausezahn $h1 -a own -b $(mac_get $rp1) -A 192.0.2.1 -B 198.51.100.1 \ + -t udp sp=12345,dp=$dport -p 1000 -c 0 -q & + + local t0=$(tc_rule_stats_get $h2 1 ingress .bytes) + sleep 10 + local t1=$(tc_rule_stats_get $h2 1 ingress .bytes) + + local er=$((80 * 1000 * 1000)) + local nr=$(rate $t0 $t1 10) + local nr_pct=$((100 * (nr - er) / er)) + ((-10 <= nr_pct && nr_pct <= 10)) + check_err $? "Expected rate $(humanize $er), got $(humanize $nr), which is $nr_pct% off. Required accuracy is +-10%." + + log_test "$test_name" + + { kill %% && wait %%; } 2>/dev/null +} + +police_shared_test() +{ + # Rule to measure bandwidth on ingress of $h2 + tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \ + dst_ip 198.51.100.1 ip_proto udp src_port 12345 \ + action drop + + # Rule to police traffic destined to $h2 on ingress of $rp1 + tc filter add dev $rp1 ingress protocol ip pref 1 handle 101 flower \ + dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \ + action police rate 80mbit burst 16k conform-exceed drop/ok \ + index 10 + + # Rule to police a different flow destined to $h2 on egress of $rp2 + # using same policer + tc filter add dev $rp2 egress protocol ip pref 1 handle 101 flower \ + dst_ip 198.51.100.1 ip_proto udp dst_port 22222 \ + action police index 10 + + police_shared_common_test 54321 "police with shared policer - rx" + + police_shared_common_test 22222 "police with shared policer - tx" + + tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower + tc filter del dev $rp1 ingress protocol ip pref 1 handle 101 flower + tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower +} + +police_mirror_common_test() +{ + local pol_if=$1; shift + local dir=$1; shift + local test_name=$1; shift + + RET=0 + + # Rule to measure bandwidth on ingress of $h2 + tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \ + dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \ + action drop + + # Rule to measure bandwidth of mirrored traffic on ingress of $h3 + tc filter add dev $h3 ingress protocol ip pref 1 handle 101 flower \ + dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \ + action drop + + # Rule to police traffic destined to $h2 and mirror to $h3 + tc filter add dev $pol_if $dir protocol ip pref 1 handle 101 flower \ + dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \ + action police rate 80mbit burst 16k conform-exceed drop/pipe \ + action mirred egress mirror dev $rp3 + + mausezahn $h1 -a own -b $(mac_get $rp1) -A 192.0.2.1 -B 198.51.100.1 \ + -t udp sp=12345,dp=54321 -p 1000 -c 0 -q & + + local t0=$(tc_rule_stats_get $h2 1 ingress .bytes) + sleep 10 + local t1=$(tc_rule_stats_get $h2 1 ingress .bytes) + + local er=$((80 * 1000 * 1000)) + local nr=$(rate $t0 $t1 10) + local nr_pct=$((100 * (nr - er) / er)) + ((-10 <= nr_pct && nr_pct <= 10)) + check_err $? "Expected rate $(humanize $er), got $(humanize $nr), which is $nr_pct% off. Required accuracy is +-10%." + + local t0=$(tc_rule_stats_get $h3 1 ingress .bytes) + sleep 10 + local t1=$(tc_rule_stats_get $h3 1 ingress .bytes) + + local er=$((80 * 1000 * 1000)) + local nr=$(rate $t0 $t1 10) + local nr_pct=$((100 * (nr - er) / er)) + ((-10 <= nr_pct && nr_pct <= 10)) + check_err $? "Expected rate $(humanize $er), got $(humanize $nr), which is $nr_pct% off. Required accuracy is +-10%." + + log_test "$test_name" + + { kill %% && wait %%; } 2>/dev/null + tc filter del dev $pol_if $dir protocol ip pref 1 handle 101 flower + tc filter del dev $h3 ingress protocol ip pref 1 handle 101 flower + tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower +} + +police_rx_mirror_test() +{ + police_mirror_common_test $rp1 ingress "police rx and mirror" +} + +police_tx_mirror_test() +{ + police_mirror_common_test $rp2 egress "police tx and mirror" +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + rp1=${NETIFS[p2]} + + rp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + rp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + forwarding_enable + + h1_create + h2_create + h3_create + router_create +} + +cleanup() +{ + pre_cleanup + + router_destroy + h3_destroy + h2_destroy + h1_destroy + + forwarding_restore + vrf_cleanup +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS -- cgit v1.2.3 From cb12d176326722e2f4ede4e459e86ea36607c555 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 15 Jul 2020 11:27:31 +0300 Subject: selftests: mlxsw: tc_restrictions: Test tc-police restrictions Test that upper and lower limits on rate and burst size imposed by the device are rejected by the kernel. Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Signed-off-by: Jakub Kicinski --- .../selftests/drivers/net/mlxsw/tc_restrictions.sh | 76 ++++++++++++++++++++++ 1 file changed, 76 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh index 9241250c5921..553cb9fad508 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh @@ -11,6 +11,8 @@ ALL_TESTS=" matchall_mirror_behind_flower_ingress_test matchall_sample_behind_flower_ingress_test matchall_mirror_behind_flower_egress_test + police_limits_test + multi_police_test " NUM_NETIFS=2 @@ -287,6 +289,80 @@ matchall_mirror_behind_flower_egress_test() matchall_behind_flower_egress_test "mirror" "mirred egress mirror dev $swp2" } +police_limits_test() +{ + RET=0 + + tc qdisc add dev $swp1 clsact + + tc filter add dev $swp1 ingress pref 1 proto ip handle 101 \ + flower skip_sw \ + action police rate 0.5kbit burst 1m conform-exceed drop/ok + check_fail $? "Incorrect success to add police action with too low rate" + + tc filter add dev $swp1 ingress pref 1 proto ip handle 101 \ + flower skip_sw \ + action police rate 2.5tbit burst 1g conform-exceed drop/ok + check_fail $? "Incorrect success to add police action with too high rate" + + tc filter add dev $swp1 ingress pref 1 proto ip handle 101 \ + flower skip_sw \ + action police rate 1.5kbit burst 1m conform-exceed drop/ok + check_err $? "Failed to add police action with low rate" + + tc filter del dev $swp1 ingress protocol ip pref 1 handle 101 flower + + tc filter add dev $swp1 ingress pref 1 proto ip handle 101 \ + flower skip_sw \ + action police rate 1.9tbit burst 1g conform-exceed drop/ok + check_err $? "Failed to add police action with high rate" + + tc filter del dev $swp1 ingress protocol ip pref 1 handle 101 flower + + tc filter add dev $swp1 ingress pref 1 proto ip handle 101 \ + flower skip_sw \ + action police rate 1.5kbit burst 512b conform-exceed drop/ok + check_fail $? "Incorrect success to add police action with too low burst size" + + tc filter add dev $swp1 ingress pref 1 proto ip handle 101 \ + flower skip_sw \ + action police rate 1.5kbit burst 2k conform-exceed drop/ok + check_err $? "Failed to add police action with low burst size" + + tc filter del dev $swp1 ingress protocol ip pref 1 handle 101 flower + + tc qdisc del dev $swp1 clsact + + log_test "police rate and burst limits" +} + +multi_police_test() +{ + RET=0 + + # It is forbidden in mlxsw driver to have multiple police + # actions in a single rule. + + tc qdisc add dev $swp1 clsact + + tc filter add dev $swp1 ingress protocol ip pref 1 handle 101 \ + flower skip_sw \ + action police rate 100mbit burst 100k conform-exceed drop/ok + check_err $? "Failed to add rule with single police action" + + tc filter del dev $swp1 ingress protocol ip pref 1 handle 101 flower + + tc filter add dev $swp1 ingress protocol ip pref 1 handle 101 \ + flower skip_sw \ + action police rate 100mbit burst 100k conform-exceed drop/pipe \ + action police rate 200mbit burst 200k conform-exceed drop/ok + check_fail $? "Incorrect success to add rule with two police actions" + + tc qdisc del dev $swp1 clsact + + log_test "multi police" +} + setup_prepare() { swp1=${NETIFS[p1]} -- cgit v1.2.3 From 5061e773264b11fdc51c61d6619aca76efd3424f Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 15 Jul 2020 11:27:32 +0300 Subject: selftests: mlxsw: Add scale test for tc-police Query the maximum number of supported policers using devlink-resource and test that this number can be reached by configuring tc filters with police action. Test that an error is returned in case the maximum number is exceeded. Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Signed-off-by: Jakub Kicinski --- .../drivers/net/mlxsw/spectrum-2/resource_scale.sh | 2 +- .../net/mlxsw/spectrum-2/tc_police_scale.sh | 16 ++++ .../drivers/net/mlxsw/spectrum/resource_scale.sh | 2 +- .../drivers/net/mlxsw/spectrum/tc_police_scale.sh | 16 ++++ .../selftests/drivers/net/mlxsw/tc_police_scale.sh | 92 ++++++++++++++++++++++ 5 files changed, 126 insertions(+), 2 deletions(-) create mode 100644 tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_police_scale.sh create mode 100644 tools/testing/selftests/drivers/net/mlxsw/spectrum/tc_police_scale.sh create mode 100644 tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh index fd583a171db7..d7cf33a3f18d 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh @@ -28,7 +28,7 @@ cleanup() trap cleanup EXIT -ALL_TESTS="router tc_flower mirror_gre" +ALL_TESTS="router tc_flower mirror_gre tc_police" for current_test in ${TESTS:-$ALL_TESTS}; do source ${current_test}_scale.sh diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_police_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_police_scale.sh new file mode 100644 index 000000000000..e79ac0dad1f4 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_police_scale.sh @@ -0,0 +1,16 @@ +# SPDX-License-Identifier: GPL-2.0 +source ../tc_police_scale.sh + +tc_police_get_target() +{ + local should_fail=$1; shift + local target + + target=$(devlink_resource_size_get global_policers single_rate_policers) + + if ((! should_fail)); then + echo $target + else + echo $((target + 1)) + fi +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh index 43ba1b438f6d..43f662401bc3 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh @@ -22,7 +22,7 @@ cleanup() devlink_sp_read_kvd_defaults trap cleanup EXIT -ALL_TESTS="router tc_flower mirror_gre" +ALL_TESTS="router tc_flower mirror_gre tc_police" for current_test in ${TESTS:-$ALL_TESTS}; do source ${current_test}_scale.sh diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/tc_police_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/tc_police_scale.sh new file mode 100644 index 000000000000..e79ac0dad1f4 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/tc_police_scale.sh @@ -0,0 +1,16 @@ +# SPDX-License-Identifier: GPL-2.0 +source ../tc_police_scale.sh + +tc_police_get_target() +{ + local should_fail=$1; shift + local target + + target=$(devlink_resource_size_get global_policers single_rate_policers) + + if ((! should_fail)); then + echo $target + else + echo $((target + 1)) + fi +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh new file mode 100644 index 000000000000..4b96561c462f --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh @@ -0,0 +1,92 @@ +# SPDX-License-Identifier: GPL-2.0 + +TC_POLICE_NUM_NETIFS=2 + +tc_police_h1_create() +{ + simple_if_init $h1 +} + +tc_police_h1_destroy() +{ + simple_if_fini $h1 +} + +tc_police_switch_create() +{ + simple_if_init $swp1 + tc qdisc add dev $swp1 clsact +} + +tc_police_switch_destroy() +{ + tc qdisc del dev $swp1 clsact + simple_if_fini $swp1 +} + +tc_police_rules_create() +{ + local count=$1; shift + local should_fail=$1; shift + + TC_POLICE_BATCH_FILE="$(mktemp)" + + for ((i = 0; i < count; ++i)); do + cat >> $TC_POLICE_BATCH_FILE <<-EOF + filter add dev $swp1 ingress \ + prot ip \ + flower skip_sw \ + action police rate 10mbit burst 100k \ + conform-exceed drop/ok + EOF + done + + tc -b $TC_POLICE_BATCH_FILE + check_err_fail $should_fail $? "Rule insertion" +} + +__tc_police_test() +{ + local count=$1; shift + local should_fail=$1; shift + + tc_police_rules_create $count $should_fail + + offload_count=$(tc filter show dev $swp1 ingress | grep in_hw | wc -l) + ((offload_count == count)) + check_err_fail $should_fail $? "tc police offload count" +} + +tc_police_test() +{ + local count=$1; shift + local should_fail=$1; shift + + if ! tc_offload_check $TC_POLICE_NUM_NETIFS; then + check_err 1 "Could not test offloaded functionality" + return + fi + + __tc_police_test $count $should_fail +} + +tc_police_setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + vrf_prepare + + tc_police_h1_create + tc_police_switch_create +} + +tc_police_cleanup() +{ + pre_cleanup + + tc_police_switch_destroy + tc_police_h1_destroy + + vrf_cleanup +} -- cgit v1.2.3 From 46b171d7d73aedfae8070622f1798ac4b124284c Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 15 Jul 2020 11:27:33 +0300 Subject: selftests: mlxsw: Test policers' occupancy Test that policers shared by different tc filters are correctly reference counted by observing policers' occupancy via devlink-resource. Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Signed-off-by: Jakub Kicinski --- .../selftests/drivers/net/mlxsw/tc_police_occ.sh | 108 +++++++++++++++++++++ .../selftests/net/forwarding/devlink_lib.sh | 5 + 2 files changed, 113 insertions(+) create mode 100755 tools/testing/selftests/drivers/net/mlxsw/tc_police_occ.sh (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_police_occ.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_police_occ.sh new file mode 100755 index 000000000000..448b75c1545a --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/tc_police_occ.sh @@ -0,0 +1,108 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test that policers shared by different tc filters are correctly reference +# counted by observing policers' occupancy via devlink-resource. + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + tc_police_occ_test +" +NUM_NETIFS=2 +source $lib_dir/lib.sh +source $lib_dir/devlink_lib.sh + +h1_create() +{ + simple_if_init $h1 +} + +h1_destroy() +{ + simple_if_fini $h1 +} + +switch_create() +{ + simple_if_init $swp1 + tc qdisc add dev $swp1 clsact +} + +switch_destroy() +{ + tc qdisc del dev $swp1 clsact + simple_if_fini $swp1 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + vrf_prepare + + h1_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h1_destroy + + vrf_cleanup +} + +tc_police_occ_get() +{ + devlink_resource_occ_get global_policers single_rate_policers +} + +tc_police_occ_test() +{ + RET=0 + + local occ=$(tc_police_occ_get) + + tc filter add dev $swp1 ingress pref 1 handle 101 proto ip \ + flower skip_sw \ + action police rate 100mbit burst 100k conform-exceed drop/ok + (( occ + 1 == $(tc_police_occ_get) )) + check_err $? "Got occupancy $(tc_police_occ_get), expected $((occ + 1))" + + tc filter del dev $swp1 ingress pref 1 handle 101 flower + (( occ == $(tc_police_occ_get) )) + check_err $? "Got occupancy $(tc_police_occ_get), expected $occ" + + tc filter add dev $swp1 ingress pref 1 handle 101 proto ip \ + flower skip_sw \ + action police rate 100mbit burst 100k conform-exceed drop/ok \ + index 10 + tc filter add dev $swp1 ingress pref 2 handle 102 proto ip \ + flower skip_sw action police index 10 + + (( occ + 1 == $(tc_police_occ_get) )) + check_err $? "Got occupancy $(tc_police_occ_get), expected $((occ + 1))" + + tc filter del dev $swp1 ingress pref 2 handle 102 flower + (( occ + 1 == $(tc_police_occ_get) )) + check_err $? "Got occupancy $(tc_police_occ_get), expected $((occ + 1))" + + tc filter del dev $swp1 ingress pref 1 handle 101 flower + (( occ == $(tc_police_occ_get) )) + check_err $? "Got occupancy $(tc_police_occ_get), expected $occ" + + log_test "tc police occupancy" +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/devlink_lib.sh b/tools/testing/selftests/net/forwarding/devlink_lib.sh index f0e6be4c09e9..75fe24bcb9cd 100644 --- a/tools/testing/selftests/net/forwarding/devlink_lib.sh +++ b/tools/testing/selftests/net/forwarding/devlink_lib.sh @@ -98,6 +98,11 @@ devlink_resource_size_set() check_err $? "Failed setting path $path to size $size" } +devlink_resource_occ_get() +{ + devlink_resource_get "$@" | jq '.["occ"]' +} + devlink_reload() { local still_pending -- cgit v1.2.3 From 05500125021191f703d3759a7e94a37b7257d959 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 14 Jul 2020 15:56:42 +0200 Subject: selftest: Add tests for XDP programs in CPUMAP entries Similar to what have been done for DEVMAP, introduce tests to verify ability to add a XDP program to an entry in a CPUMAP. Verify CPUMAP programs can not be attached to devices as a normal XDP program, and only programs with BPF_XDP_CPUMAP attach type can be loaded in a CPUMAP. Signed-off-by: Lorenzo Bianconi Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/9c632fcea5382ea7b4578bd06b6eddf382c3550b.1594734381.git.lorenzo@kernel.org --- .../selftests/bpf/prog_tests/xdp_cpumap_attach.c | 70 ++++++++++++++++++++++ .../bpf/progs/test_xdp_with_cpumap_helpers.c | 36 +++++++++++ 2 files changed, 106 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c create mode 100644 tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c new file mode 100644 index 000000000000..0176573fe4e7 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c @@ -0,0 +1,70 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include + +#include "test_xdp_with_cpumap_helpers.skel.h" + +#define IFINDEX_LO 1 + +void test_xdp_with_cpumap_helpers(void) +{ + struct test_xdp_with_cpumap_helpers *skel; + struct bpf_prog_info info = {}; + struct bpf_cpumap_val val = { + .qsize = 192, + }; + __u32 duration = 0, idx = 0; + __u32 len = sizeof(info); + int err, prog_fd, map_fd; + + skel = test_xdp_with_cpumap_helpers__open_and_load(); + if (CHECK_FAIL(!skel)) { + perror("test_xdp_with_cpumap_helpers__open_and_load"); + return; + } + + /* can not attach program with cpumaps that allow programs + * as xdp generic + */ + prog_fd = bpf_program__fd(skel->progs.xdp_redir_prog); + err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE); + CHECK(err == 0, "Generic attach of program with 8-byte CPUMAP", + "should have failed\n"); + + prog_fd = bpf_program__fd(skel->progs.xdp_dummy_cm); + map_fd = bpf_map__fd(skel->maps.cpu_map); + err = bpf_obj_get_info_by_fd(prog_fd, &info, &len); + if (CHECK_FAIL(err)) + goto out_close; + + val.bpf_prog.fd = prog_fd; + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + CHECK(err, "Add program to cpumap entry", "err %d errno %d\n", + err, errno); + + err = bpf_map_lookup_elem(map_fd, &idx, &val); + CHECK(err, "Read cpumap entry", "err %d errno %d\n", err, errno); + CHECK(info.id != val.bpf_prog.id, "Expected program id in cpumap entry", + "expected %u read %u\n", info.id, val.bpf_prog.id); + + /* can not attach BPF_XDP_CPUMAP program to a device */ + err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE); + CHECK(err == 0, "Attach of BPF_XDP_CPUMAP program", + "should have failed\n"); + + val.qsize = 192; + val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_prog); + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + CHECK(err == 0, "Add non-BPF_XDP_CPUMAP program to cpumap entry", + "should have failed\n"); + +out_close: + test_xdp_with_cpumap_helpers__destroy(skel); +} + +void test_xdp_cpumap_attach(void) +{ + if (test__start_subtest("cpumap_with_progs")) + test_xdp_with_cpumap_helpers(); +} diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c new file mode 100644 index 000000000000..59ee4f182ff8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include + +#define IFINDEX_LO 1 + +struct { + __uint(type, BPF_MAP_TYPE_CPUMAP); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_cpumap_val)); + __uint(max_entries, 4); +} cpu_map SEC(".maps"); + +SEC("xdp_redir") +int xdp_redir_prog(struct xdp_md *ctx) +{ + return bpf_redirect_map(&cpu_map, 1, 0); +} + +SEC("xdp_dummy") +int xdp_dummy_prog(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +SEC("xdp_cpumap/dummy_cm") +int xdp_dummy_cm(struct xdp_md *ctx) +{ + if (ctx->ingress_ifindex == IFINDEX_LO) + return XDP_DROP; + + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; -- cgit v1.2.3 From e81e7a533742c30615f8b15390df6525cef96778 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Wed, 15 Jul 2020 15:41:07 -0700 Subject: selftests/bpf: Fix possible hang in sockopt_inherit Andrii reported that sockopt_inherit occasionally hangs up on 5.5 kernel [0]. This can happen if server_thread runs faster than the main thread. In that case, pthread_cond_wait will wait forever because pthread_cond_signal was executed before the main thread was blocking. Let's move pthread_mutex_lock up a bit to make sure server_thread runs strictly after the main thread goes to sleep. (Not sure why this is 5.5 specific, maybe scheduling is less deterministic? But I was able to confirm that it does indeed happen in a VM.) [0] https://lore.kernel.org/bpf/CAEf4BzY0-bVNHmCkMFPgObs=isUAyg-dFzGDY7QWYkmm7rmTSg@mail.gmail.com/ Reported-by: Andrii Nakryiko Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200715224107.3591967-1-sdf@google.com --- tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c index 8547ecbdc61f..ec281b0363b8 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c @@ -193,11 +193,10 @@ static void run_test(int cgroup_fd) if (CHECK_FAIL(server_fd < 0)) goto close_bpf_object; + pthread_mutex_lock(&server_started_mtx); if (CHECK_FAIL(pthread_create(&tid, NULL, server_thread, (void *)&server_fd))) goto close_server_fd; - - pthread_mutex_lock(&server_started_mtx); pthread_cond_wait(&server_started, &server_started_mtx); pthread_mutex_unlock(&server_started_mtx); -- cgit v1.2.3 From f7726cbea402fc92a3c27226b761a6dbc0390cac Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Fri, 17 Jul 2020 12:35:35 +0200 Subject: selftests/bpf: Add verifier tests for bpf_sk_lookup context access Exercise verifier access checks for bpf_sk_lookup context fields. Signed-off-by: Jakub Sitnicki Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200717103536.397595-15-jakub@cloudflare.com --- .../testing/selftests/bpf/verifier/ctx_sk_lookup.c | 492 +++++++++++++++++++++ 1 file changed, 492 insertions(+) create mode 100644 tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c b/tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c new file mode 100644 index 000000000000..2ad5f974451c --- /dev/null +++ b/tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c @@ -0,0 +1,492 @@ +{ + "valid 1,2,4,8-byte reads from bpf_sk_lookup", + .insns = { + /* 1-byte read from family field */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, family)), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, family) + 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, family) + 2), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, family) + 3), + /* 2-byte read from family field */ + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, family)), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, family) + 2), + /* 4-byte read from family field */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, family)), + + /* 1-byte read from protocol field */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, protocol)), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, protocol) + 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, protocol) + 2), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, protocol) + 3), + /* 2-byte read from protocol field */ + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, protocol)), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, protocol) + 2), + /* 4-byte read from protocol field */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, protocol)), + + /* 1-byte read from remote_ip4 field */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip4)), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip4) + 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip4) + 2), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip4) + 3), + /* 2-byte read from remote_ip4 field */ + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip4)), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip4) + 2), + /* 4-byte read from remote_ip4 field */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip4)), + + /* 1-byte read from remote_ip6 field */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6)), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 2), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 3), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 4), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 5), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 6), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 7), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 8), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 9), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 10), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 11), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 12), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 13), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 14), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 15), + /* 2-byte read from remote_ip6 field */ + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6)), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 2), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 4), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 6), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 8), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 10), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 12), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 14), + /* 4-byte read from remote_ip6 field */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6)), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 4), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 8), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6) + 12), + + /* 1-byte read from remote_port field */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_port)), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_port) + 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_port) + 2), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_port) + 3), + /* 2-byte read from remote_port field */ + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_port)), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_port) + 2), + /* 4-byte read from remote_port field */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_port)), + + /* 1-byte read from local_ip4 field */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip4)), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip4) + 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip4) + 2), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip4) + 3), + /* 2-byte read from local_ip4 field */ + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip4)), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip4) + 2), + /* 4-byte read from local_ip4 field */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip4)), + + /* 1-byte read from local_ip6 field */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6)), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 2), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 3), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 4), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 5), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 6), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 7), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 8), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 9), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 10), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 11), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 12), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 13), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 14), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 15), + /* 2-byte read from local_ip6 field */ + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6)), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 2), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 4), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 6), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 8), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 10), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 12), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 14), + /* 4-byte read from local_ip6 field */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6)), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 4), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 8), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6) + 12), + + /* 1-byte read from local_port field */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_port)), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_port) + 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_port) + 2), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_port) + 3), + /* 2-byte read from local_port field */ + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_port)), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_port) + 2), + /* 4-byte read from local_port field */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_port)), + + /* 8-byte read from sk field */ + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, sk)), + + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +/* invalid 8-byte reads from a 4-byte fields in bpf_sk_lookup */ +{ + "invalid 8-byte read from bpf_sk_lookup family field", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, family)), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +{ + "invalid 8-byte read from bpf_sk_lookup protocol field", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, protocol)), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +{ + "invalid 8-byte read from bpf_sk_lookup remote_ip4 field", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip4)), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +{ + "invalid 8-byte read from bpf_sk_lookup remote_ip6 field", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_ip6)), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +{ + "invalid 8-byte read from bpf_sk_lookup remote_port field", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, remote_port)), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +{ + "invalid 8-byte read from bpf_sk_lookup local_ip4 field", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip4)), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +{ + "invalid 8-byte read from bpf_sk_lookup local_ip6 field", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_ip6)), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +{ + "invalid 8-byte read from bpf_sk_lookup local_port field", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, local_port)), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +/* invalid 1,2,4-byte reads from 8-byte fields in bpf_sk_lookup */ +{ + "invalid 4-byte read from bpf_sk_lookup sk field", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, sk)), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +{ + "invalid 2-byte read from bpf_sk_lookup sk field", + .insns = { + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, sk)), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +{ + "invalid 1-byte read from bpf_sk_lookup sk field", + .insns = { + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_sk_lookup, sk)), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +/* out of bounds and unaligned reads from bpf_sk_lookup */ +{ + "invalid 4-byte read past end of bpf_sk_lookup", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + sizeof(struct bpf_sk_lookup)), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +{ + "invalid 4-byte unaligned read from bpf_sk_lookup at odd offset", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 1), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +{ + "invalid 4-byte unaligned read from bpf_sk_lookup at even offset", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 2), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +/* in-bound and out-of-bound writes to bpf_sk_lookup */ +{ + "invalid 8-byte write to bpf_sk_lookup", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0xcafe4a11U), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +{ + "invalid 4-byte write to bpf_sk_lookup", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0xcafe4a11U), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +{ + "invalid 2-byte write to bpf_sk_lookup", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0xcafe4a11U), + BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0, 0), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +{ + "invalid 1-byte write to bpf_sk_lookup", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0xcafe4a11U), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, +{ + "invalid 4-byte write past end of bpf_sk_lookup", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0xcafe4a11U), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + sizeof(struct bpf_sk_lookup)), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_LOOKUP, + .expected_attach_type = BPF_SK_LOOKUP, +}, -- cgit v1.2.3 From 0ab5539f85840d3c4e5a8a4783901c0038f8321e Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Fri, 17 Jul 2020 12:35:36 +0200 Subject: selftests/bpf: Tests for BPF_SK_LOOKUP attach point Add tests to test_progs that exercise: - attaching/detaching/querying programs to BPF_SK_LOOKUP hook, - redirecting socket lookup to a socket selected by BPF program, - failing a socket lookup on BPF program's request, - error scenarios for selecting a socket from BPF program, - accessing BPF program context, - attaching and running multiple BPF programs. Run log: bash-5.0# ./test_progs -n 70 #70/1 query lookup prog:OK #70/2 TCP IPv4 redir port:OK #70/3 TCP IPv4 redir addr:OK #70/4 TCP IPv4 redir with reuseport:OK #70/5 TCP IPv4 redir skip reuseport:OK #70/6 TCP IPv6 redir port:OK #70/7 TCP IPv6 redir addr:OK #70/8 TCP IPv4->IPv6 redir port:OK #70/9 TCP IPv6 redir with reuseport:OK #70/10 TCP IPv6 redir skip reuseport:OK #70/11 UDP IPv4 redir port:OK #70/12 UDP IPv4 redir addr:OK #70/13 UDP IPv4 redir with reuseport:OK #70/14 UDP IPv4 redir skip reuseport:OK #70/15 UDP IPv6 redir port:OK #70/16 UDP IPv6 redir addr:OK #70/17 UDP IPv4->IPv6 redir port:OK #70/18 UDP IPv6 redir and reuseport:OK #70/19 UDP IPv6 redir skip reuseport:OK #70/20 TCP IPv4 drop on lookup:OK #70/21 TCP IPv6 drop on lookup:OK #70/22 UDP IPv4 drop on lookup:OK #70/23 UDP IPv6 drop on lookup:OK #70/24 TCP IPv4 drop on reuseport:OK #70/25 TCP IPv6 drop on reuseport:OK #70/26 UDP IPv4 drop on reuseport:OK #70/27 TCP IPv6 drop on reuseport:OK #70/28 sk_assign returns EEXIST:OK #70/29 sk_assign honors F_REPLACE:OK #70/30 sk_assign accepts NULL socket:OK #70/31 access ctx->sk:OK #70/32 narrow access to ctx v4:OK #70/33 narrow access to ctx v6:OK #70/34 sk_assign rejects TCP established:OK #70/35 sk_assign rejects UDP connected:OK #70/36 multi prog - pass, pass:OK #70/37 multi prog - drop, drop:OK #70/38 multi prog - pass, drop:OK #70/39 multi prog - drop, pass:OK #70/40 multi prog - pass, redir:OK #70/41 multi prog - redir, pass:OK #70/42 multi prog - drop, redir:OK #70/43 multi prog - redir, drop:OK #70/44 multi prog - redir, redir:OK #70 sk_lookup:OK Summary: 1/44 PASSED, 0 SKIPPED, 0 FAILED Signed-off-by: Jakub Sitnicki Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200717103536.397595-16-jakub@cloudflare.com --- tools/testing/selftests/bpf/network_helpers.c | 58 +- tools/testing/selftests/bpf/network_helpers.h | 2 + tools/testing/selftests/bpf/prog_tests/sk_lookup.c | 1282 ++++++++++++++++++++ tools/testing/selftests/bpf/progs/test_sk_lookup.c | 641 ++++++++++ 4 files changed, 1960 insertions(+), 23 deletions(-) create mode 100644 tools/testing/selftests/bpf/prog_tests/sk_lookup.c create mode 100644 tools/testing/selftests/bpf/progs/test_sk_lookup.c (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index acd08715be2e..f56655690f9b 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -73,29 +73,8 @@ int start_server(int family, int type, const char *addr_str, __u16 port, socklen_t len; int fd; - if (family == AF_INET) { - struct sockaddr_in *sin = (void *)&addr; - - sin->sin_family = AF_INET; - sin->sin_port = htons(port); - if (addr_str && - inet_pton(AF_INET, addr_str, &sin->sin_addr) != 1) { - log_err("inet_pton(AF_INET, %s)", addr_str); - return -1; - } - len = sizeof(*sin); - } else { - struct sockaddr_in6 *sin6 = (void *)&addr; - - sin6->sin6_family = AF_INET6; - sin6->sin6_port = htons(port); - if (addr_str && - inet_pton(AF_INET6, addr_str, &sin6->sin6_addr) != 1) { - log_err("inet_pton(AF_INET6, %s)", addr_str); - return -1; - } - len = sizeof(*sin6); - } + if (make_sockaddr(family, addr_str, port, &addr, &len)) + return -1; fd = socket(family, type, 0); if (fd < 0) { @@ -194,3 +173,36 @@ int connect_fd_to_fd(int client_fd, int server_fd, int timeout_ms) return 0; } + +int make_sockaddr(int family, const char *addr_str, __u16 port, + struct sockaddr_storage *addr, socklen_t *len) +{ + if (family == AF_INET) { + struct sockaddr_in *sin = (void *)addr; + + sin->sin_family = AF_INET; + sin->sin_port = htons(port); + if (addr_str && + inet_pton(AF_INET, addr_str, &sin->sin_addr) != 1) { + log_err("inet_pton(AF_INET, %s)", addr_str); + return -1; + } + if (len) + *len = sizeof(*sin); + return 0; + } else if (family == AF_INET6) { + struct sockaddr_in6 *sin6 = (void *)addr; + + sin6->sin6_family = AF_INET6; + sin6->sin6_port = htons(port); + if (addr_str && + inet_pton(AF_INET6, addr_str, &sin6->sin6_addr) != 1) { + log_err("inet_pton(AF_INET6, %s)", addr_str); + return -1; + } + if (len) + *len = sizeof(*sin6); + return 0; + } + return -1; +} diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h index f580e82fda58..c3728f6667e4 100644 --- a/tools/testing/selftests/bpf/network_helpers.h +++ b/tools/testing/selftests/bpf/network_helpers.h @@ -37,5 +37,7 @@ int start_server(int family, int type, const char *addr, __u16 port, int timeout_ms); int connect_to_fd(int server_fd, int timeout_ms); int connect_fd_to_fd(int client_fd, int server_fd, int timeout_ms); +int make_sockaddr(int family, const char *addr_str, __u16 port, + struct sockaddr_storage *addr, socklen_t *len); #endif diff --git a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c new file mode 100644 index 000000000000..f1784ae4565a --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c @@ -0,0 +1,1282 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +// Copyright (c) 2020 Cloudflare +/* + * Test BPF attach point for INET socket lookup (BPF_SK_LOOKUP). + * + * Tests exercise: + * - attaching/detaching/querying programs to BPF_SK_LOOKUP hook, + * - redirecting socket lookup to a socket selected by BPF program, + * - failing a socket lookup on BPF program's request, + * - error scenarios for selecting a socket from BPF program, + * - accessing BPF program context, + * - attaching and running multiple BPF programs. + * + * Tests run in a dedicated network namespace. + */ + +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#include "test_progs.h" +#include "bpf_rlimit.h" +#include "bpf_util.h" +#include "cgroup_helpers.h" +#include "network_helpers.h" +#include "test_sk_lookup.skel.h" + +/* External (address, port) pairs the client sends packets to. */ +#define EXT_IP4 "127.0.0.1" +#define EXT_IP6 "fd00::1" +#define EXT_PORT 7007 + +/* Internal (address, port) pairs the server listens/receives at. */ +#define INT_IP4 "127.0.0.2" +#define INT_IP4_V6 "::ffff:127.0.0.2" +#define INT_IP6 "fd00::2" +#define INT_PORT 8008 + +#define IO_TIMEOUT_SEC 3 + +enum server { + SERVER_A = 0, + SERVER_B = 1, + MAX_SERVERS, +}; + +enum { + PROG1 = 0, + PROG2, +}; + +struct inet_addr { + const char *ip; + unsigned short port; +}; + +struct test { + const char *desc; + struct bpf_program *lookup_prog; + struct bpf_program *reuseport_prog; + struct bpf_map *sock_map; + int sotype; + struct inet_addr connect_to; + struct inet_addr listen_at; + enum server accept_on; +}; + +static __u32 duration; /* for CHECK macro */ + +static bool is_ipv6(const char *ip) +{ + return !!strchr(ip, ':'); +} + +static int attach_reuseport(int sock_fd, struct bpf_program *reuseport_prog) +{ + int err, prog_fd; + + prog_fd = bpf_program__fd(reuseport_prog); + if (prog_fd < 0) { + errno = -prog_fd; + return -1; + } + + err = setsockopt(sock_fd, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, + &prog_fd, sizeof(prog_fd)); + if (err) + return -1; + + return 0; +} + +static socklen_t inetaddr_len(const struct sockaddr_storage *addr) +{ + return (addr->ss_family == AF_INET ? sizeof(struct sockaddr_in) : + addr->ss_family == AF_INET6 ? sizeof(struct sockaddr_in6) : 0); +} + +static int make_socket(int sotype, const char *ip, int port, + struct sockaddr_storage *addr) +{ + struct timeval timeo = { .tv_sec = IO_TIMEOUT_SEC }; + int err, family, fd; + + family = is_ipv6(ip) ? AF_INET6 : AF_INET; + err = make_sockaddr(family, ip, port, addr, NULL); + if (CHECK(err, "make_address", "failed\n")) + return -1; + + fd = socket(addr->ss_family, sotype, 0); + if (CHECK(fd < 0, "socket", "failed\n")) { + log_err("failed to make socket"); + return -1; + } + + err = setsockopt(fd, SOL_SOCKET, SO_SNDTIMEO, &timeo, sizeof(timeo)); + if (CHECK(err, "setsockopt(SO_SNDTIMEO)", "failed\n")) { + log_err("failed to set SNDTIMEO"); + close(fd); + return -1; + } + + err = setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &timeo, sizeof(timeo)); + if (CHECK(err, "setsockopt(SO_RCVTIMEO)", "failed\n")) { + log_err("failed to set RCVTIMEO"); + close(fd); + return -1; + } + + return fd; +} + +static int make_server(int sotype, const char *ip, int port, + struct bpf_program *reuseport_prog) +{ + struct sockaddr_storage addr = {0}; + const int one = 1; + int err, fd = -1; + + fd = make_socket(sotype, ip, port, &addr); + if (fd < 0) + return -1; + + /* Enabled for UDPv6 sockets for IPv4-mapped IPv6 to work. */ + if (sotype == SOCK_DGRAM) { + err = setsockopt(fd, SOL_IP, IP_RECVORIGDSTADDR, &one, + sizeof(one)); + if (CHECK(err, "setsockopt(IP_RECVORIGDSTADDR)", "failed\n")) { + log_err("failed to enable IP_RECVORIGDSTADDR"); + goto fail; + } + } + + if (sotype == SOCK_DGRAM && addr.ss_family == AF_INET6) { + err = setsockopt(fd, SOL_IPV6, IPV6_RECVORIGDSTADDR, &one, + sizeof(one)); + if (CHECK(err, "setsockopt(IPV6_RECVORIGDSTADDR)", "failed\n")) { + log_err("failed to enable IPV6_RECVORIGDSTADDR"); + goto fail; + } + } + + if (sotype == SOCK_STREAM) { + err = setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &one, + sizeof(one)); + if (CHECK(err, "setsockopt(SO_REUSEADDR)", "failed\n")) { + log_err("failed to enable SO_REUSEADDR"); + goto fail; + } + } + + if (reuseport_prog) { + err = setsockopt(fd, SOL_SOCKET, SO_REUSEPORT, &one, + sizeof(one)); + if (CHECK(err, "setsockopt(SO_REUSEPORT)", "failed\n")) { + log_err("failed to enable SO_REUSEPORT"); + goto fail; + } + } + + err = bind(fd, (void *)&addr, inetaddr_len(&addr)); + if (CHECK(err, "bind", "failed\n")) { + log_err("failed to bind listen socket"); + goto fail; + } + + if (sotype == SOCK_STREAM) { + err = listen(fd, SOMAXCONN); + if (CHECK(err, "make_server", "listen")) { + log_err("failed to listen on port %d", port); + goto fail; + } + } + + /* Late attach reuseport prog so we can have one init path */ + if (reuseport_prog) { + err = attach_reuseport(fd, reuseport_prog); + if (CHECK(err, "attach_reuseport", "failed\n")) { + log_err("failed to attach reuseport prog"); + goto fail; + } + } + + return fd; +fail: + close(fd); + return -1; +} + +static int make_client(int sotype, const char *ip, int port) +{ + struct sockaddr_storage addr = {0}; + int err, fd; + + fd = make_socket(sotype, ip, port, &addr); + if (fd < 0) + return -1; + + err = connect(fd, (void *)&addr, inetaddr_len(&addr)); + if (CHECK(err, "make_client", "connect")) { + log_err("failed to connect client socket"); + goto fail; + } + + return fd; +fail: + close(fd); + return -1; +} + +static int send_byte(int fd) +{ + ssize_t n; + + errno = 0; + n = send(fd, "a", 1, 0); + if (CHECK(n <= 0, "send_byte", "send")) { + log_err("failed/partial send"); + return -1; + } + return 0; +} + +static int recv_byte(int fd) +{ + char buf[1]; + ssize_t n; + + n = recv(fd, buf, sizeof(buf), 0); + if (CHECK(n <= 0, "recv_byte", "recv")) { + log_err("failed/partial recv"); + return -1; + } + return 0; +} + +static int tcp_recv_send(int server_fd) +{ + char buf[1]; + int ret, fd; + ssize_t n; + + fd = accept(server_fd, NULL, NULL); + if (CHECK(fd < 0, "accept", "failed\n")) { + log_err("failed to accept"); + return -1; + } + + n = recv(fd, buf, sizeof(buf), 0); + if (CHECK(n <= 0, "recv", "failed\n")) { + log_err("failed/partial recv"); + ret = -1; + goto close; + } + + n = send(fd, buf, n, 0); + if (CHECK(n <= 0, "send", "failed\n")) { + log_err("failed/partial send"); + ret = -1; + goto close; + } + + ret = 0; +close: + close(fd); + return ret; +} + +static void v4_to_v6(struct sockaddr_storage *ss) +{ + struct sockaddr_in6 *v6 = (struct sockaddr_in6 *)ss; + struct sockaddr_in v4 = *(struct sockaddr_in *)ss; + + v6->sin6_family = AF_INET6; + v6->sin6_port = v4.sin_port; + v6->sin6_addr.s6_addr[10] = 0xff; + v6->sin6_addr.s6_addr[11] = 0xff; + memcpy(&v6->sin6_addr.s6_addr[12], &v4.sin_addr.s_addr, 4); +} + +static int udp_recv_send(int server_fd) +{ + char cmsg_buf[CMSG_SPACE(sizeof(struct sockaddr_storage))]; + struct sockaddr_storage _src_addr = { 0 }; + struct sockaddr_storage *src_addr = &_src_addr; + struct sockaddr_storage *dst_addr = NULL; + struct msghdr msg = { 0 }; + struct iovec iov = { 0 }; + struct cmsghdr *cm; + char buf[1]; + int ret, fd; + ssize_t n; + + iov.iov_base = buf; + iov.iov_len = sizeof(buf); + + msg.msg_name = src_addr; + msg.msg_namelen = sizeof(*src_addr); + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_control = cmsg_buf; + msg.msg_controllen = sizeof(cmsg_buf); + + errno = 0; + n = recvmsg(server_fd, &msg, 0); + if (CHECK(n <= 0, "recvmsg", "failed\n")) { + log_err("failed to receive"); + return -1; + } + if (CHECK(msg.msg_flags & MSG_CTRUNC, "recvmsg", "truncated cmsg\n")) + return -1; + + for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) { + if ((cm->cmsg_level == SOL_IP && + cm->cmsg_type == IP_ORIGDSTADDR) || + (cm->cmsg_level == SOL_IPV6 && + cm->cmsg_type == IPV6_ORIGDSTADDR)) { + dst_addr = (struct sockaddr_storage *)CMSG_DATA(cm); + break; + } + log_err("warning: ignored cmsg at level %d type %d", + cm->cmsg_level, cm->cmsg_type); + } + if (CHECK(!dst_addr, "recvmsg", "missing ORIGDSTADDR\n")) + return -1; + + /* Server socket bound to IPv4-mapped IPv6 address */ + if (src_addr->ss_family == AF_INET6 && + dst_addr->ss_family == AF_INET) { + v4_to_v6(dst_addr); + } + + /* Reply from original destination address. */ + fd = socket(dst_addr->ss_family, SOCK_DGRAM, 0); + if (CHECK(fd < 0, "socket", "failed\n")) { + log_err("failed to create tx socket"); + return -1; + } + + ret = bind(fd, (struct sockaddr *)dst_addr, sizeof(*dst_addr)); + if (CHECK(ret, "bind", "failed\n")) { + log_err("failed to bind tx socket"); + goto out; + } + + msg.msg_control = NULL; + msg.msg_controllen = 0; + n = sendmsg(fd, &msg, 0); + if (CHECK(n <= 0, "sendmsg", "failed\n")) { + log_err("failed to send echo reply"); + ret = -1; + goto out; + } + + ret = 0; +out: + close(fd); + return ret; +} + +static int tcp_echo_test(int client_fd, int server_fd) +{ + int err; + + err = send_byte(client_fd); + if (err) + return -1; + err = tcp_recv_send(server_fd); + if (err) + return -1; + err = recv_byte(client_fd); + if (err) + return -1; + + return 0; +} + +static int udp_echo_test(int client_fd, int server_fd) +{ + int err; + + err = send_byte(client_fd); + if (err) + return -1; + err = udp_recv_send(server_fd); + if (err) + return -1; + err = recv_byte(client_fd); + if (err) + return -1; + + return 0; +} + +static struct bpf_link *attach_lookup_prog(struct bpf_program *prog) +{ + struct bpf_link *link; + int net_fd; + + net_fd = open("/proc/self/ns/net", O_RDONLY); + if (CHECK(net_fd < 0, "open", "failed\n")) { + log_err("failed to open /proc/self/ns/net"); + return NULL; + } + + link = bpf_program__attach_netns(prog, net_fd); + if (CHECK(IS_ERR(link), "bpf_program__attach_netns", "failed\n")) { + errno = -PTR_ERR(link); + log_err("failed to attach program '%s' to netns", + bpf_program__name(prog)); + link = NULL; + } + + close(net_fd); + return link; +} + +static int update_lookup_map(struct bpf_map *map, int index, int sock_fd) +{ + int err, map_fd; + uint64_t value; + + map_fd = bpf_map__fd(map); + if (CHECK(map_fd < 0, "bpf_map__fd", "failed\n")) { + errno = -map_fd; + log_err("failed to get map FD"); + return -1; + } + + value = (uint64_t)sock_fd; + err = bpf_map_update_elem(map_fd, &index, &value, BPF_NOEXIST); + if (CHECK(err, "bpf_map_update_elem", "failed\n")) { + log_err("failed to update redir_map @ %d", index); + return -1; + } + + return 0; +} + +static __u32 link_info_prog_id(struct bpf_link *link) +{ + struct bpf_link_info info = {}; + __u32 info_len = sizeof(info); + int link_fd, err; + + link_fd = bpf_link__fd(link); + if (CHECK(link_fd < 0, "bpf_link__fd", "failed\n")) { + errno = -link_fd; + log_err("bpf_link__fd failed"); + return 0; + } + + err = bpf_obj_get_info_by_fd(link_fd, &info, &info_len); + if (CHECK(err, "bpf_obj_get_info_by_fd", "failed\n")) { + log_err("bpf_obj_get_info_by_fd"); + return 0; + } + if (CHECK(info_len != sizeof(info), "bpf_obj_get_info_by_fd", + "unexpected info len %u\n", info_len)) + return 0; + + return info.prog_id; +} + +static void query_lookup_prog(struct test_sk_lookup *skel) +{ + struct bpf_link *link[3] = {}; + __u32 attach_flags = 0; + __u32 prog_ids[3] = {}; + __u32 prog_cnt = 3; + __u32 prog_id; + int net_fd; + int err; + + net_fd = open("/proc/self/ns/net", O_RDONLY); + if (CHECK(net_fd < 0, "open", "failed\n")) { + log_err("failed to open /proc/self/ns/net"); + return; + } + + link[0] = attach_lookup_prog(skel->progs.lookup_pass); + if (!link[0]) + goto close; + link[1] = attach_lookup_prog(skel->progs.lookup_pass); + if (!link[1]) + goto detach; + link[2] = attach_lookup_prog(skel->progs.lookup_drop); + if (!link[2]) + goto detach; + + err = bpf_prog_query(net_fd, BPF_SK_LOOKUP, 0 /* query flags */, + &attach_flags, prog_ids, &prog_cnt); + if (CHECK(err, "bpf_prog_query", "failed\n")) { + log_err("failed to query lookup prog"); + goto detach; + } + + errno = 0; + if (CHECK(attach_flags != 0, "bpf_prog_query", + "wrong attach_flags on query: %u", attach_flags)) + goto detach; + if (CHECK(prog_cnt != 3, "bpf_prog_query", + "wrong program count on query: %u", prog_cnt)) + goto detach; + prog_id = link_info_prog_id(link[0]); + CHECK(prog_ids[0] != prog_id, "bpf_prog_query", + "invalid program #0 id on query: %u != %u\n", + prog_ids[0], prog_id); + prog_id = link_info_prog_id(link[1]); + CHECK(prog_ids[1] != prog_id, "bpf_prog_query", + "invalid program #1 id on query: %u != %u\n", + prog_ids[1], prog_id); + prog_id = link_info_prog_id(link[2]); + CHECK(prog_ids[2] != prog_id, "bpf_prog_query", + "invalid program #2 id on query: %u != %u\n", + prog_ids[2], prog_id); + +detach: + if (link[2]) + bpf_link__destroy(link[2]); + if (link[1]) + bpf_link__destroy(link[1]); + if (link[0]) + bpf_link__destroy(link[0]); +close: + close(net_fd); +} + +static void run_lookup_prog(const struct test *t) +{ + int client_fd, server_fds[MAX_SERVERS] = { -1 }; + struct bpf_link *lookup_link; + int i, err; + + lookup_link = attach_lookup_prog(t->lookup_prog); + if (!lookup_link) + return; + + for (i = 0; i < ARRAY_SIZE(server_fds); i++) { + server_fds[i] = make_server(t->sotype, t->listen_at.ip, + t->listen_at.port, + t->reuseport_prog); + if (server_fds[i] < 0) + goto close; + + err = update_lookup_map(t->sock_map, i, server_fds[i]); + if (err) + goto close; + + /* want just one server for non-reuseport test */ + if (!t->reuseport_prog) + break; + } + + client_fd = make_client(t->sotype, t->connect_to.ip, t->connect_to.port); + if (client_fd < 0) + goto close; + + if (t->sotype == SOCK_STREAM) + tcp_echo_test(client_fd, server_fds[t->accept_on]); + else + udp_echo_test(client_fd, server_fds[t->accept_on]); + + close(client_fd); +close: + for (i = 0; i < ARRAY_SIZE(server_fds); i++) { + if (server_fds[i] != -1) + close(server_fds[i]); + } + bpf_link__destroy(lookup_link); +} + +static void test_redirect_lookup(struct test_sk_lookup *skel) +{ + const struct test tests[] = { + { + .desc = "TCP IPv4 redir port", + .lookup_prog = skel->progs.redir_port, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_STREAM, + .connect_to = { EXT_IP4, EXT_PORT }, + .listen_at = { EXT_IP4, INT_PORT }, + }, + { + .desc = "TCP IPv4 redir addr", + .lookup_prog = skel->progs.redir_ip4, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_STREAM, + .connect_to = { EXT_IP4, EXT_PORT }, + .listen_at = { INT_IP4, EXT_PORT }, + }, + { + .desc = "TCP IPv4 redir with reuseport", + .lookup_prog = skel->progs.select_sock_a, + .reuseport_prog = skel->progs.select_sock_b, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_STREAM, + .connect_to = { EXT_IP4, EXT_PORT }, + .listen_at = { INT_IP4, INT_PORT }, + .accept_on = SERVER_B, + }, + { + .desc = "TCP IPv4 redir skip reuseport", + .lookup_prog = skel->progs.select_sock_a_no_reuseport, + .reuseport_prog = skel->progs.select_sock_b, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_STREAM, + .connect_to = { EXT_IP4, EXT_PORT }, + .listen_at = { INT_IP4, INT_PORT }, + .accept_on = SERVER_A, + }, + { + .desc = "TCP IPv6 redir port", + .lookup_prog = skel->progs.redir_port, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_STREAM, + .connect_to = { EXT_IP6, EXT_PORT }, + .listen_at = { EXT_IP6, INT_PORT }, + }, + { + .desc = "TCP IPv6 redir addr", + .lookup_prog = skel->progs.redir_ip6, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_STREAM, + .connect_to = { EXT_IP6, EXT_PORT }, + .listen_at = { INT_IP6, EXT_PORT }, + }, + { + .desc = "TCP IPv4->IPv6 redir port", + .lookup_prog = skel->progs.redir_port, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_STREAM, + .connect_to = { EXT_IP4, EXT_PORT }, + .listen_at = { INT_IP4_V6, INT_PORT }, + }, + { + .desc = "TCP IPv6 redir with reuseport", + .lookup_prog = skel->progs.select_sock_a, + .reuseport_prog = skel->progs.select_sock_b, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_STREAM, + .connect_to = { EXT_IP6, EXT_PORT }, + .listen_at = { INT_IP6, INT_PORT }, + .accept_on = SERVER_B, + }, + { + .desc = "TCP IPv6 redir skip reuseport", + .lookup_prog = skel->progs.select_sock_a_no_reuseport, + .reuseport_prog = skel->progs.select_sock_b, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_STREAM, + .connect_to = { EXT_IP6, EXT_PORT }, + .listen_at = { INT_IP6, INT_PORT }, + .accept_on = SERVER_A, + }, + { + .desc = "UDP IPv4 redir port", + .lookup_prog = skel->progs.redir_port, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_DGRAM, + .connect_to = { EXT_IP4, EXT_PORT }, + .listen_at = { EXT_IP4, INT_PORT }, + }, + { + .desc = "UDP IPv4 redir addr", + .lookup_prog = skel->progs.redir_ip4, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_DGRAM, + .connect_to = { EXT_IP4, EXT_PORT }, + .listen_at = { INT_IP4, EXT_PORT }, + }, + { + .desc = "UDP IPv4 redir with reuseport", + .lookup_prog = skel->progs.select_sock_a, + .reuseport_prog = skel->progs.select_sock_b, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_DGRAM, + .connect_to = { EXT_IP4, EXT_PORT }, + .listen_at = { INT_IP4, INT_PORT }, + .accept_on = SERVER_B, + }, + { + .desc = "UDP IPv4 redir skip reuseport", + .lookup_prog = skel->progs.select_sock_a_no_reuseport, + .reuseport_prog = skel->progs.select_sock_b, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_DGRAM, + .connect_to = { EXT_IP4, EXT_PORT }, + .listen_at = { INT_IP4, INT_PORT }, + .accept_on = SERVER_A, + }, + { + .desc = "UDP IPv6 redir port", + .lookup_prog = skel->progs.redir_port, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_DGRAM, + .connect_to = { EXT_IP6, EXT_PORT }, + .listen_at = { EXT_IP6, INT_PORT }, + }, + { + .desc = "UDP IPv6 redir addr", + .lookup_prog = skel->progs.redir_ip6, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_DGRAM, + .connect_to = { EXT_IP6, EXT_PORT }, + .listen_at = { INT_IP6, EXT_PORT }, + }, + { + .desc = "UDP IPv4->IPv6 redir port", + .lookup_prog = skel->progs.redir_port, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_DGRAM, + .listen_at = { INT_IP4_V6, INT_PORT }, + .connect_to = { EXT_IP4, EXT_PORT }, + }, + { + .desc = "UDP IPv6 redir and reuseport", + .lookup_prog = skel->progs.select_sock_a, + .reuseport_prog = skel->progs.select_sock_b, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_DGRAM, + .connect_to = { EXT_IP6, EXT_PORT }, + .listen_at = { INT_IP6, INT_PORT }, + .accept_on = SERVER_B, + }, + { + .desc = "UDP IPv6 redir skip reuseport", + .lookup_prog = skel->progs.select_sock_a_no_reuseport, + .reuseport_prog = skel->progs.select_sock_b, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_DGRAM, + .connect_to = { EXT_IP6, EXT_PORT }, + .listen_at = { INT_IP6, INT_PORT }, + .accept_on = SERVER_A, + }, + }; + const struct test *t; + + for (t = tests; t < tests + ARRAY_SIZE(tests); t++) { + if (test__start_subtest(t->desc)) + run_lookup_prog(t); + } +} + +static void drop_on_lookup(const struct test *t) +{ + struct sockaddr_storage dst = {}; + int client_fd, server_fd, err; + struct bpf_link *lookup_link; + ssize_t n; + + lookup_link = attach_lookup_prog(t->lookup_prog); + if (!lookup_link) + return; + + server_fd = make_server(t->sotype, t->listen_at.ip, t->listen_at.port, + t->reuseport_prog); + if (server_fd < 0) + goto detach; + + client_fd = make_socket(t->sotype, t->connect_to.ip, + t->connect_to.port, &dst); + if (client_fd < 0) + goto close_srv; + + err = connect(client_fd, (void *)&dst, inetaddr_len(&dst)); + if (t->sotype == SOCK_DGRAM) { + err = send_byte(client_fd); + if (err) + goto close_all; + + /* Read out asynchronous error */ + n = recv(client_fd, NULL, 0, 0); + err = n == -1; + } + if (CHECK(!err || errno != ECONNREFUSED, "connect", + "unexpected success or error\n")) + log_err("expected ECONNREFUSED on connect"); + +close_all: + close(client_fd); +close_srv: + close(server_fd); +detach: + bpf_link__destroy(lookup_link); +} + +static void test_drop_on_lookup(struct test_sk_lookup *skel) +{ + const struct test tests[] = { + { + .desc = "TCP IPv4 drop on lookup", + .lookup_prog = skel->progs.lookup_drop, + .sotype = SOCK_STREAM, + .connect_to = { EXT_IP4, EXT_PORT }, + .listen_at = { EXT_IP4, EXT_PORT }, + }, + { + .desc = "TCP IPv6 drop on lookup", + .lookup_prog = skel->progs.lookup_drop, + .sotype = SOCK_STREAM, + .connect_to = { EXT_IP6, EXT_PORT }, + .listen_at = { EXT_IP6, EXT_PORT }, + }, + { + .desc = "UDP IPv4 drop on lookup", + .lookup_prog = skel->progs.lookup_drop, + .sotype = SOCK_DGRAM, + .connect_to = { EXT_IP4, EXT_PORT }, + .listen_at = { EXT_IP4, EXT_PORT }, + }, + { + .desc = "UDP IPv6 drop on lookup", + .lookup_prog = skel->progs.lookup_drop, + .sotype = SOCK_DGRAM, + .connect_to = { EXT_IP6, EXT_PORT }, + .listen_at = { EXT_IP6, INT_PORT }, + }, + }; + const struct test *t; + + for (t = tests; t < tests + ARRAY_SIZE(tests); t++) { + if (test__start_subtest(t->desc)) + drop_on_lookup(t); + } +} + +static void drop_on_reuseport(const struct test *t) +{ + struct sockaddr_storage dst = { 0 }; + int client, server1, server2, err; + struct bpf_link *lookup_link; + ssize_t n; + + lookup_link = attach_lookup_prog(t->lookup_prog); + if (!lookup_link) + return; + + server1 = make_server(t->sotype, t->listen_at.ip, t->listen_at.port, + t->reuseport_prog); + if (server1 < 0) + goto detach; + + err = update_lookup_map(t->sock_map, SERVER_A, server1); + if (err) + goto detach; + + /* second server on destination address we should never reach */ + server2 = make_server(t->sotype, t->connect_to.ip, t->connect_to.port, + NULL /* reuseport prog */); + if (server2 < 0) + goto close_srv1; + + client = make_socket(t->sotype, t->connect_to.ip, + t->connect_to.port, &dst); + if (client < 0) + goto close_srv2; + + err = connect(client, (void *)&dst, inetaddr_len(&dst)); + if (t->sotype == SOCK_DGRAM) { + err = send_byte(client); + if (err) + goto close_all; + + /* Read out asynchronous error */ + n = recv(client, NULL, 0, 0); + err = n == -1; + } + if (CHECK(!err || errno != ECONNREFUSED, "connect", + "unexpected success or error\n")) + log_err("expected ECONNREFUSED on connect"); + +close_all: + close(client); +close_srv2: + close(server2); +close_srv1: + close(server1); +detach: + bpf_link__destroy(lookup_link); +} + +static void test_drop_on_reuseport(struct test_sk_lookup *skel) +{ + const struct test tests[] = { + { + .desc = "TCP IPv4 drop on reuseport", + .lookup_prog = skel->progs.select_sock_a, + .reuseport_prog = skel->progs.reuseport_drop, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_STREAM, + .connect_to = { EXT_IP4, EXT_PORT }, + .listen_at = { INT_IP4, INT_PORT }, + }, + { + .desc = "TCP IPv6 drop on reuseport", + .lookup_prog = skel->progs.select_sock_a, + .reuseport_prog = skel->progs.reuseport_drop, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_STREAM, + .connect_to = { EXT_IP6, EXT_PORT }, + .listen_at = { INT_IP6, INT_PORT }, + }, + { + .desc = "UDP IPv4 drop on reuseport", + .lookup_prog = skel->progs.select_sock_a, + .reuseport_prog = skel->progs.reuseport_drop, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_DGRAM, + .connect_to = { EXT_IP4, EXT_PORT }, + .listen_at = { INT_IP4, INT_PORT }, + }, + { + .desc = "TCP IPv6 drop on reuseport", + .lookup_prog = skel->progs.select_sock_a, + .reuseport_prog = skel->progs.reuseport_drop, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_STREAM, + .connect_to = { EXT_IP6, EXT_PORT }, + .listen_at = { INT_IP6, INT_PORT }, + }, + }; + const struct test *t; + + for (t = tests; t < tests + ARRAY_SIZE(tests); t++) { + if (test__start_subtest(t->desc)) + drop_on_reuseport(t); + } +} + +static void run_sk_assign(struct test_sk_lookup *skel, + struct bpf_program *lookup_prog, + const char *listen_ip, const char *connect_ip) +{ + int client_fd, peer_fd, server_fds[MAX_SERVERS] = { -1 }; + struct bpf_link *lookup_link; + int i, err; + + lookup_link = attach_lookup_prog(lookup_prog); + if (!lookup_link) + return; + + for (i = 0; i < ARRAY_SIZE(server_fds); i++) { + server_fds[i] = make_server(SOCK_STREAM, listen_ip, 0, NULL); + if (server_fds[i] < 0) + goto close_servers; + + err = update_lookup_map(skel->maps.redir_map, i, + server_fds[i]); + if (err) + goto close_servers; + } + + client_fd = make_client(SOCK_STREAM, connect_ip, EXT_PORT); + if (client_fd < 0) + goto close_servers; + + peer_fd = accept(server_fds[SERVER_B], NULL, NULL); + if (CHECK(peer_fd < 0, "accept", "failed\n")) + goto close_client; + + close(peer_fd); +close_client: + close(client_fd); +close_servers: + for (i = 0; i < ARRAY_SIZE(server_fds); i++) { + if (server_fds[i] != -1) + close(server_fds[i]); + } + bpf_link__destroy(lookup_link); +} + +static void run_sk_assign_v4(struct test_sk_lookup *skel, + struct bpf_program *lookup_prog) +{ + run_sk_assign(skel, lookup_prog, INT_IP4, EXT_IP4); +} + +static void run_sk_assign_v6(struct test_sk_lookup *skel, + struct bpf_program *lookup_prog) +{ + run_sk_assign(skel, lookup_prog, INT_IP6, EXT_IP6); +} + +static void run_sk_assign_connected(struct test_sk_lookup *skel, + int sotype) +{ + int err, client_fd, connected_fd, server_fd; + struct bpf_link *lookup_link; + + server_fd = make_server(sotype, EXT_IP4, EXT_PORT, NULL); + if (server_fd < 0) + return; + + connected_fd = make_client(sotype, EXT_IP4, EXT_PORT); + if (connected_fd < 0) + goto out_close_server; + + /* Put a connected socket in redirect map */ + err = update_lookup_map(skel->maps.redir_map, SERVER_A, connected_fd); + if (err) + goto out_close_connected; + + lookup_link = attach_lookup_prog(skel->progs.sk_assign_esocknosupport); + if (!lookup_link) + goto out_close_connected; + + /* Try to redirect TCP SYN / UDP packet to a connected socket */ + client_fd = make_client(sotype, EXT_IP4, EXT_PORT); + if (client_fd < 0) + goto out_unlink_prog; + if (sotype == SOCK_DGRAM) { + send_byte(client_fd); + recv_byte(server_fd); + } + + close(client_fd); +out_unlink_prog: + bpf_link__destroy(lookup_link); +out_close_connected: + close(connected_fd); +out_close_server: + close(server_fd); +} + +static void test_sk_assign_helper(struct test_sk_lookup *skel) +{ + if (test__start_subtest("sk_assign returns EEXIST")) + run_sk_assign_v4(skel, skel->progs.sk_assign_eexist); + if (test__start_subtest("sk_assign honors F_REPLACE")) + run_sk_assign_v4(skel, skel->progs.sk_assign_replace_flag); + if (test__start_subtest("sk_assign accepts NULL socket")) + run_sk_assign_v4(skel, skel->progs.sk_assign_null); + if (test__start_subtest("access ctx->sk")) + run_sk_assign_v4(skel, skel->progs.access_ctx_sk); + if (test__start_subtest("narrow access to ctx v4")) + run_sk_assign_v4(skel, skel->progs.ctx_narrow_access); + if (test__start_subtest("narrow access to ctx v6")) + run_sk_assign_v6(skel, skel->progs.ctx_narrow_access); + if (test__start_subtest("sk_assign rejects TCP established")) + run_sk_assign_connected(skel, SOCK_STREAM); + if (test__start_subtest("sk_assign rejects UDP connected")) + run_sk_assign_connected(skel, SOCK_DGRAM); +} + +struct test_multi_prog { + const char *desc; + struct bpf_program *prog1; + struct bpf_program *prog2; + struct bpf_map *redir_map; + struct bpf_map *run_map; + int expect_errno; + struct inet_addr listen_at; +}; + +static void run_multi_prog_lookup(const struct test_multi_prog *t) +{ + struct sockaddr_storage dst = {}; + int map_fd, server_fd, client_fd; + struct bpf_link *link1, *link2; + int prog_idx, done, err; + + map_fd = bpf_map__fd(t->run_map); + + done = 0; + prog_idx = PROG1; + err = bpf_map_update_elem(map_fd, &prog_idx, &done, BPF_ANY); + if (CHECK(err, "bpf_map_update_elem", "failed\n")) + return; + prog_idx = PROG2; + err = bpf_map_update_elem(map_fd, &prog_idx, &done, BPF_ANY); + if (CHECK(err, "bpf_map_update_elem", "failed\n")) + return; + + link1 = attach_lookup_prog(t->prog1); + if (!link1) + return; + link2 = attach_lookup_prog(t->prog2); + if (!link2) + goto out_unlink1; + + server_fd = make_server(SOCK_STREAM, t->listen_at.ip, + t->listen_at.port, NULL); + if (server_fd < 0) + goto out_unlink2; + + err = update_lookup_map(t->redir_map, SERVER_A, server_fd); + if (err) + goto out_close_server; + + client_fd = make_socket(SOCK_STREAM, EXT_IP4, EXT_PORT, &dst); + if (client_fd < 0) + goto out_close_server; + + err = connect(client_fd, (void *)&dst, inetaddr_len(&dst)); + if (CHECK(err && !t->expect_errno, "connect", + "unexpected error %d\n", errno)) + goto out_close_client; + if (CHECK(err && t->expect_errno && errno != t->expect_errno, + "connect", "unexpected error %d\n", errno)) + goto out_close_client; + + done = 0; + prog_idx = PROG1; + err = bpf_map_lookup_elem(map_fd, &prog_idx, &done); + CHECK(err, "bpf_map_lookup_elem", "failed\n"); + CHECK(!done, "bpf_map_lookup_elem", "PROG1 !done\n"); + + done = 0; + prog_idx = PROG2; + err = bpf_map_lookup_elem(map_fd, &prog_idx, &done); + CHECK(err, "bpf_map_lookup_elem", "failed\n"); + CHECK(!done, "bpf_map_lookup_elem", "PROG2 !done\n"); + +out_close_client: + close(client_fd); +out_close_server: + close(server_fd); +out_unlink2: + bpf_link__destroy(link2); +out_unlink1: + bpf_link__destroy(link1); +} + +static void test_multi_prog_lookup(struct test_sk_lookup *skel) +{ + struct test_multi_prog tests[] = { + { + .desc = "multi prog - pass, pass", + .prog1 = skel->progs.multi_prog_pass1, + .prog2 = skel->progs.multi_prog_pass2, + .listen_at = { EXT_IP4, EXT_PORT }, + }, + { + .desc = "multi prog - drop, drop", + .prog1 = skel->progs.multi_prog_drop1, + .prog2 = skel->progs.multi_prog_drop2, + .listen_at = { EXT_IP4, EXT_PORT }, + .expect_errno = ECONNREFUSED, + }, + { + .desc = "multi prog - pass, drop", + .prog1 = skel->progs.multi_prog_pass1, + .prog2 = skel->progs.multi_prog_drop2, + .listen_at = { EXT_IP4, EXT_PORT }, + .expect_errno = ECONNREFUSED, + }, + { + .desc = "multi prog - drop, pass", + .prog1 = skel->progs.multi_prog_drop1, + .prog2 = skel->progs.multi_prog_pass2, + .listen_at = { EXT_IP4, EXT_PORT }, + .expect_errno = ECONNREFUSED, + }, + { + .desc = "multi prog - pass, redir", + .prog1 = skel->progs.multi_prog_pass1, + .prog2 = skel->progs.multi_prog_redir2, + .listen_at = { INT_IP4, INT_PORT }, + }, + { + .desc = "multi prog - redir, pass", + .prog1 = skel->progs.multi_prog_redir1, + .prog2 = skel->progs.multi_prog_pass2, + .listen_at = { INT_IP4, INT_PORT }, + }, + { + .desc = "multi prog - drop, redir", + .prog1 = skel->progs.multi_prog_drop1, + .prog2 = skel->progs.multi_prog_redir2, + .listen_at = { INT_IP4, INT_PORT }, + }, + { + .desc = "multi prog - redir, drop", + .prog1 = skel->progs.multi_prog_redir1, + .prog2 = skel->progs.multi_prog_drop2, + .listen_at = { INT_IP4, INT_PORT }, + }, + { + .desc = "multi prog - redir, redir", + .prog1 = skel->progs.multi_prog_redir1, + .prog2 = skel->progs.multi_prog_redir2, + .listen_at = { INT_IP4, INT_PORT }, + }, + }; + struct test_multi_prog *t; + + for (t = tests; t < tests + ARRAY_SIZE(tests); t++) { + t->redir_map = skel->maps.redir_map; + t->run_map = skel->maps.run_map; + if (test__start_subtest(t->desc)) + run_multi_prog_lookup(t); + } +} + +static void run_tests(struct test_sk_lookup *skel) +{ + if (test__start_subtest("query lookup prog")) + query_lookup_prog(skel); + test_redirect_lookup(skel); + test_drop_on_lookup(skel); + test_drop_on_reuseport(skel); + test_sk_assign_helper(skel); + test_multi_prog_lookup(skel); +} + +static int switch_netns(void) +{ + static const char * const setup_script[] = { + "ip -6 addr add dev lo " EXT_IP6 "/128 nodad", + "ip -6 addr add dev lo " INT_IP6 "/128 nodad", + "ip link set dev lo up", + NULL, + }; + const char * const *cmd; + int err; + + err = unshare(CLONE_NEWNET); + if (CHECK(err, "unshare", "failed\n")) { + log_err("unshare(CLONE_NEWNET)"); + return -1; + } + + for (cmd = setup_script; *cmd; cmd++) { + err = system(*cmd); + if (CHECK(err, "system", "failed\n")) { + log_err("system(%s)", *cmd); + return -1; + } + } + + return 0; +} + +void test_sk_lookup(void) +{ + struct test_sk_lookup *skel; + int err; + + err = switch_netns(); + if (err) + return; + + skel = test_sk_lookup__open_and_load(); + if (CHECK(!skel, "skel open_and_load", "failed\n")) + return; + + run_tests(skel); + + test_sk_lookup__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup.c b/tools/testing/selftests/bpf/progs/test_sk_lookup.c new file mode 100644 index 000000000000..bbf8296f4d66 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sk_lookup.c @@ -0,0 +1,641 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +// Copyright (c) 2020 Cloudflare + +#include +#include +#include +#include +#include +#include + +#include +#include + +#define IP4(a, b, c, d) \ + bpf_htonl((((__u32)(a) & 0xffU) << 24) | \ + (((__u32)(b) & 0xffU) << 16) | \ + (((__u32)(c) & 0xffU) << 8) | \ + (((__u32)(d) & 0xffU) << 0)) +#define IP6(aaaa, bbbb, cccc, dddd) \ + { bpf_htonl(aaaa), bpf_htonl(bbbb), bpf_htonl(cccc), bpf_htonl(dddd) } + +#define MAX_SOCKS 32 + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, MAX_SOCKS); + __type(key, __u32); + __type(value, __u64); +} redir_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 2); + __type(key, int); + __type(value, int); +} run_map SEC(".maps"); + +enum { + PROG1 = 0, + PROG2, +}; + +enum { + SERVER_A = 0, + SERVER_B, +}; + +/* Addressable key/value constants for convenience */ +static const int KEY_PROG1 = PROG1; +static const int KEY_PROG2 = PROG2; +static const int PROG_DONE = 1; + +static const __u32 KEY_SERVER_A = SERVER_A; +static const __u32 KEY_SERVER_B = SERVER_B; + +static const __u16 DST_PORT = 7007; /* Host byte order */ +static const __u32 DST_IP4 = IP4(127, 0, 0, 1); +static const __u32 DST_IP6[] = IP6(0xfd000000, 0x0, 0x0, 0x00000001); + +SEC("sk_lookup/lookup_pass") +int lookup_pass(struct bpf_sk_lookup *ctx) +{ + return SK_PASS; +} + +SEC("sk_lookup/lookup_drop") +int lookup_drop(struct bpf_sk_lookup *ctx) +{ + return SK_DROP; +} + +SEC("sk_reuseport/reuse_pass") +int reuseport_pass(struct sk_reuseport_md *ctx) +{ + return SK_PASS; +} + +SEC("sk_reuseport/reuse_drop") +int reuseport_drop(struct sk_reuseport_md *ctx) +{ + return SK_DROP; +} + +/* Redirect packets destined for port DST_PORT to socket at redir_map[0]. */ +SEC("sk_lookup/redir_port") +int redir_port(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk; + int err; + + if (ctx->local_port != DST_PORT) + return SK_PASS; + + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A); + if (!sk) + return SK_PASS; + + err = bpf_sk_assign(ctx, sk, 0); + bpf_sk_release(sk); + return err ? SK_DROP : SK_PASS; +} + +/* Redirect packets destined for DST_IP4 address to socket at redir_map[0]. */ +SEC("sk_lookup/redir_ip4") +int redir_ip4(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk; + int err; + + if (ctx->family != AF_INET) + return SK_PASS; + if (ctx->local_port != DST_PORT) + return SK_PASS; + if (ctx->local_ip4 != DST_IP4) + return SK_PASS; + + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A); + if (!sk) + return SK_PASS; + + err = bpf_sk_assign(ctx, sk, 0); + bpf_sk_release(sk); + return err ? SK_DROP : SK_PASS; +} + +/* Redirect packets destined for DST_IP6 address to socket at redir_map[0]. */ +SEC("sk_lookup/redir_ip6") +int redir_ip6(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk; + int err; + + if (ctx->family != AF_INET6) + return SK_PASS; + if (ctx->local_port != DST_PORT) + return SK_PASS; + if (ctx->local_ip6[0] != DST_IP6[0] || + ctx->local_ip6[1] != DST_IP6[1] || + ctx->local_ip6[2] != DST_IP6[2] || + ctx->local_ip6[3] != DST_IP6[3]) + return SK_PASS; + + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A); + if (!sk) + return SK_PASS; + + err = bpf_sk_assign(ctx, sk, 0); + bpf_sk_release(sk); + return err ? SK_DROP : SK_PASS; +} + +SEC("sk_lookup/select_sock_a") +int select_sock_a(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk; + int err; + + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A); + if (!sk) + return SK_PASS; + + err = bpf_sk_assign(ctx, sk, 0); + bpf_sk_release(sk); + return err ? SK_DROP : SK_PASS; +} + +SEC("sk_lookup/select_sock_a_no_reuseport") +int select_sock_a_no_reuseport(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk; + int err; + + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A); + if (!sk) + return SK_DROP; + + err = bpf_sk_assign(ctx, sk, BPF_SK_LOOKUP_F_NO_REUSEPORT); + bpf_sk_release(sk); + return err ? SK_DROP : SK_PASS; +} + +SEC("sk_reuseport/select_sock_b") +int select_sock_b(struct sk_reuseport_md *ctx) +{ + __u32 key = KEY_SERVER_B; + int err; + + err = bpf_sk_select_reuseport(ctx, &redir_map, &key, 0); + return err ? SK_DROP : SK_PASS; +} + +/* Check that bpf_sk_assign() returns -EEXIST if socket already selected. */ +SEC("sk_lookup/sk_assign_eexist") +int sk_assign_eexist(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk; + int err, ret; + + ret = SK_DROP; + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_B); + if (!sk) + goto out; + err = bpf_sk_assign(ctx, sk, 0); + if (err) + goto out; + bpf_sk_release(sk); + + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A); + if (!sk) + goto out; + err = bpf_sk_assign(ctx, sk, 0); + if (err != -EEXIST) { + bpf_printk("sk_assign returned %d, expected %d\n", + err, -EEXIST); + goto out; + } + + ret = SK_PASS; /* Success, redirect to KEY_SERVER_B */ +out: + if (sk) + bpf_sk_release(sk); + return ret; +} + +/* Check that bpf_sk_assign(BPF_SK_LOOKUP_F_REPLACE) can override selection. */ +SEC("sk_lookup/sk_assign_replace_flag") +int sk_assign_replace_flag(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk; + int err, ret; + + ret = SK_DROP; + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A); + if (!sk) + goto out; + err = bpf_sk_assign(ctx, sk, 0); + if (err) + goto out; + bpf_sk_release(sk); + + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_B); + if (!sk) + goto out; + err = bpf_sk_assign(ctx, sk, BPF_SK_LOOKUP_F_REPLACE); + if (err) { + bpf_printk("sk_assign returned %d, expected 0\n", err); + goto out; + } + + ret = SK_PASS; /* Success, redirect to KEY_SERVER_B */ +out: + if (sk) + bpf_sk_release(sk); + return ret; +} + +/* Check that bpf_sk_assign(sk=NULL) is accepted. */ +SEC("sk_lookup/sk_assign_null") +int sk_assign_null(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk = NULL; + int err, ret; + + ret = SK_DROP; + + err = bpf_sk_assign(ctx, NULL, 0); + if (err) { + bpf_printk("sk_assign returned %d, expected 0\n", err); + goto out; + } + + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_B); + if (!sk) + goto out; + err = bpf_sk_assign(ctx, sk, BPF_SK_LOOKUP_F_REPLACE); + if (err) { + bpf_printk("sk_assign returned %d, expected 0\n", err); + goto out; + } + + if (ctx->sk != sk) + goto out; + err = bpf_sk_assign(ctx, NULL, 0); + if (err != -EEXIST) + goto out; + err = bpf_sk_assign(ctx, NULL, BPF_SK_LOOKUP_F_REPLACE); + if (err) + goto out; + err = bpf_sk_assign(ctx, sk, BPF_SK_LOOKUP_F_REPLACE); + if (err) + goto out; + + ret = SK_PASS; /* Success, redirect to KEY_SERVER_B */ +out: + if (sk) + bpf_sk_release(sk); + return ret; +} + +/* Check that selected sk is accessible through context. */ +SEC("sk_lookup/access_ctx_sk") +int access_ctx_sk(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk1 = NULL, *sk2 = NULL; + int err, ret; + + ret = SK_DROP; + + /* Try accessing unassigned (NULL) ctx->sk field */ + if (ctx->sk && ctx->sk->family != AF_INET) + goto out; + + /* Assign a value to ctx->sk */ + sk1 = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A); + if (!sk1) + goto out; + err = bpf_sk_assign(ctx, sk1, 0); + if (err) + goto out; + if (ctx->sk != sk1) + goto out; + + /* Access ctx->sk fields */ + if (ctx->sk->family != AF_INET || + ctx->sk->type != SOCK_STREAM || + ctx->sk->state != BPF_TCP_LISTEN) + goto out; + + /* Reset selection */ + err = bpf_sk_assign(ctx, NULL, BPF_SK_LOOKUP_F_REPLACE); + if (err) + goto out; + if (ctx->sk) + goto out; + + /* Assign another socket */ + sk2 = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_B); + if (!sk2) + goto out; + err = bpf_sk_assign(ctx, sk2, BPF_SK_LOOKUP_F_REPLACE); + if (err) + goto out; + if (ctx->sk != sk2) + goto out; + + /* Access reassigned ctx->sk fields */ + if (ctx->sk->family != AF_INET || + ctx->sk->type != SOCK_STREAM || + ctx->sk->state != BPF_TCP_LISTEN) + goto out; + + ret = SK_PASS; /* Success, redirect to KEY_SERVER_B */ +out: + if (sk1) + bpf_sk_release(sk1); + if (sk2) + bpf_sk_release(sk2); + return ret; +} + +/* Check narrow loads from ctx fields that support them. + * + * Narrow loads of size >= target field size from a non-zero offset + * are not covered because they give bogus results, that is the + * verifier ignores the offset. + */ +SEC("sk_lookup/ctx_narrow_access") +int ctx_narrow_access(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk; + int err, family; + __u16 *half; + __u8 *byte; + bool v4; + + v4 = (ctx->family == AF_INET); + + /* Narrow loads from family field */ + byte = (__u8 *)&ctx->family; + half = (__u16 *)&ctx->family; + if (byte[0] != (v4 ? AF_INET : AF_INET6) || + byte[1] != 0 || byte[2] != 0 || byte[3] != 0) + return SK_DROP; + if (half[0] != (v4 ? AF_INET : AF_INET6)) + return SK_DROP; + + byte = (__u8 *)&ctx->protocol; + if (byte[0] != IPPROTO_TCP || + byte[1] != 0 || byte[2] != 0 || byte[3] != 0) + return SK_DROP; + half = (__u16 *)&ctx->protocol; + if (half[0] != IPPROTO_TCP) + return SK_DROP; + + /* Narrow loads from remote_port field. Expect non-0 value. */ + byte = (__u8 *)&ctx->remote_port; + if (byte[0] == 0 && byte[1] == 0 && byte[2] == 0 && byte[3] == 0) + return SK_DROP; + half = (__u16 *)&ctx->remote_port; + if (half[0] == 0) + return SK_DROP; + + /* Narrow loads from local_port field. Expect DST_PORT. */ + byte = (__u8 *)&ctx->local_port; + if (byte[0] != ((DST_PORT >> 0) & 0xff) || + byte[1] != ((DST_PORT >> 8) & 0xff) || + byte[2] != 0 || byte[3] != 0) + return SK_DROP; + half = (__u16 *)&ctx->local_port; + if (half[0] != DST_PORT) + return SK_DROP; + + /* Narrow loads from IPv4 fields */ + if (v4) { + /* Expect non-0.0.0.0 in remote_ip4 */ + byte = (__u8 *)&ctx->remote_ip4; + if (byte[0] == 0 && byte[1] == 0 && + byte[2] == 0 && byte[3] == 0) + return SK_DROP; + half = (__u16 *)&ctx->remote_ip4; + if (half[0] == 0 && half[1] == 0) + return SK_DROP; + + /* Expect DST_IP4 in local_ip4 */ + byte = (__u8 *)&ctx->local_ip4; + if (byte[0] != ((DST_IP4 >> 0) & 0xff) || + byte[1] != ((DST_IP4 >> 8) & 0xff) || + byte[2] != ((DST_IP4 >> 16) & 0xff) || + byte[3] != ((DST_IP4 >> 24) & 0xff)) + return SK_DROP; + half = (__u16 *)&ctx->local_ip4; + if (half[0] != ((DST_IP4 >> 0) & 0xffff) || + half[1] != ((DST_IP4 >> 16) & 0xffff)) + return SK_DROP; + } else { + /* Expect 0.0.0.0 IPs when family != AF_INET */ + byte = (__u8 *)&ctx->remote_ip4; + if (byte[0] != 0 || byte[1] != 0 && + byte[2] != 0 || byte[3] != 0) + return SK_DROP; + half = (__u16 *)&ctx->remote_ip4; + if (half[0] != 0 || half[1] != 0) + return SK_DROP; + + byte = (__u8 *)&ctx->local_ip4; + if (byte[0] != 0 || byte[1] != 0 && + byte[2] != 0 || byte[3] != 0) + return SK_DROP; + half = (__u16 *)&ctx->local_ip4; + if (half[0] != 0 || half[1] != 0) + return SK_DROP; + } + + /* Narrow loads from IPv6 fields */ + if (!v4) { + /* Expenct non-:: IP in remote_ip6 */ + byte = (__u8 *)&ctx->remote_ip6; + if (byte[0] == 0 && byte[1] == 0 && + byte[2] == 0 && byte[3] == 0 && + byte[4] == 0 && byte[5] == 0 && + byte[6] == 0 && byte[7] == 0 && + byte[8] == 0 && byte[9] == 0 && + byte[10] == 0 && byte[11] == 0 && + byte[12] == 0 && byte[13] == 0 && + byte[14] == 0 && byte[15] == 0) + return SK_DROP; + half = (__u16 *)&ctx->remote_ip6; + if (half[0] == 0 && half[1] == 0 && + half[2] == 0 && half[3] == 0 && + half[4] == 0 && half[5] == 0 && + half[6] == 0 && half[7] == 0) + return SK_DROP; + + /* Expect DST_IP6 in local_ip6 */ + byte = (__u8 *)&ctx->local_ip6; + if (byte[0] != ((DST_IP6[0] >> 0) & 0xff) || + byte[1] != ((DST_IP6[0] >> 8) & 0xff) || + byte[2] != ((DST_IP6[0] >> 16) & 0xff) || + byte[3] != ((DST_IP6[0] >> 24) & 0xff) || + byte[4] != ((DST_IP6[1] >> 0) & 0xff) || + byte[5] != ((DST_IP6[1] >> 8) & 0xff) || + byte[6] != ((DST_IP6[1] >> 16) & 0xff) || + byte[7] != ((DST_IP6[1] >> 24) & 0xff) || + byte[8] != ((DST_IP6[2] >> 0) & 0xff) || + byte[9] != ((DST_IP6[2] >> 8) & 0xff) || + byte[10] != ((DST_IP6[2] >> 16) & 0xff) || + byte[11] != ((DST_IP6[2] >> 24) & 0xff) || + byte[12] != ((DST_IP6[3] >> 0) & 0xff) || + byte[13] != ((DST_IP6[3] >> 8) & 0xff) || + byte[14] != ((DST_IP6[3] >> 16) & 0xff) || + byte[15] != ((DST_IP6[3] >> 24) & 0xff)) + return SK_DROP; + half = (__u16 *)&ctx->local_ip6; + if (half[0] != ((DST_IP6[0] >> 0) & 0xffff) || + half[1] != ((DST_IP6[0] >> 16) & 0xffff) || + half[2] != ((DST_IP6[1] >> 0) & 0xffff) || + half[3] != ((DST_IP6[1] >> 16) & 0xffff) || + half[4] != ((DST_IP6[2] >> 0) & 0xffff) || + half[5] != ((DST_IP6[2] >> 16) & 0xffff) || + half[6] != ((DST_IP6[3] >> 0) & 0xffff) || + half[7] != ((DST_IP6[3] >> 16) & 0xffff)) + return SK_DROP; + } else { + /* Expect :: IPs when family != AF_INET6 */ + byte = (__u8 *)&ctx->remote_ip6; + if (byte[0] != 0 || byte[1] != 0 || + byte[2] != 0 || byte[3] != 0 || + byte[4] != 0 || byte[5] != 0 || + byte[6] != 0 || byte[7] != 0 || + byte[8] != 0 || byte[9] != 0 || + byte[10] != 0 || byte[11] != 0 || + byte[12] != 0 || byte[13] != 0 || + byte[14] != 0 || byte[15] != 0) + return SK_DROP; + half = (__u16 *)&ctx->remote_ip6; + if (half[0] != 0 || half[1] != 0 || + half[2] != 0 || half[3] != 0 || + half[4] != 0 || half[5] != 0 || + half[6] != 0 || half[7] != 0) + return SK_DROP; + + byte = (__u8 *)&ctx->local_ip6; + if (byte[0] != 0 || byte[1] != 0 || + byte[2] != 0 || byte[3] != 0 || + byte[4] != 0 || byte[5] != 0 || + byte[6] != 0 || byte[7] != 0 || + byte[8] != 0 || byte[9] != 0 || + byte[10] != 0 || byte[11] != 0 || + byte[12] != 0 || byte[13] != 0 || + byte[14] != 0 || byte[15] != 0) + return SK_DROP; + half = (__u16 *)&ctx->local_ip6; + if (half[0] != 0 || half[1] != 0 || + half[2] != 0 || half[3] != 0 || + half[4] != 0 || half[5] != 0 || + half[6] != 0 || half[7] != 0) + return SK_DROP; + } + + /* Success, redirect to KEY_SERVER_B */ + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_B); + if (sk) { + bpf_sk_assign(ctx, sk, 0); + bpf_sk_release(sk); + } + return SK_PASS; +} + +/* Check that sk_assign rejects SERVER_A socket with -ESOCKNOSUPPORT */ +SEC("sk_lookup/sk_assign_esocknosupport") +int sk_assign_esocknosupport(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk; + int err, ret; + + ret = SK_DROP; + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A); + if (!sk) + goto out; + + err = bpf_sk_assign(ctx, sk, 0); + if (err != -ESOCKTNOSUPPORT) { + bpf_printk("sk_assign returned %d, expected %d\n", + err, -ESOCKTNOSUPPORT); + goto out; + } + + ret = SK_PASS; /* Success, pass to regular lookup */ +out: + if (sk) + bpf_sk_release(sk); + return ret; +} + +SEC("sk_lookup/multi_prog_pass1") +int multi_prog_pass1(struct bpf_sk_lookup *ctx) +{ + bpf_map_update_elem(&run_map, &KEY_PROG1, &PROG_DONE, BPF_ANY); + return SK_PASS; +} + +SEC("sk_lookup/multi_prog_pass2") +int multi_prog_pass2(struct bpf_sk_lookup *ctx) +{ + bpf_map_update_elem(&run_map, &KEY_PROG2, &PROG_DONE, BPF_ANY); + return SK_PASS; +} + +SEC("sk_lookup/multi_prog_drop1") +int multi_prog_drop1(struct bpf_sk_lookup *ctx) +{ + bpf_map_update_elem(&run_map, &KEY_PROG1, &PROG_DONE, BPF_ANY); + return SK_DROP; +} + +SEC("sk_lookup/multi_prog_drop2") +int multi_prog_drop2(struct bpf_sk_lookup *ctx) +{ + bpf_map_update_elem(&run_map, &KEY_PROG2, &PROG_DONE, BPF_ANY); + return SK_DROP; +} + +static __always_inline int select_server_a(struct bpf_sk_lookup *ctx) +{ + struct bpf_sock *sk; + int err; + + sk = bpf_map_lookup_elem(&redir_map, &KEY_SERVER_A); + if (!sk) + return SK_DROP; + + err = bpf_sk_assign(ctx, sk, 0); + bpf_sk_release(sk); + if (err) + return SK_DROP; + + return SK_PASS; +} + +SEC("sk_lookup/multi_prog_redir1") +int multi_prog_redir1(struct bpf_sk_lookup *ctx) +{ + int ret; + + ret = select_server_a(ctx); + bpf_map_update_elem(&run_map, &KEY_PROG1, &PROG_DONE, BPF_ANY); + return SK_PASS; +} + +SEC("sk_lookup/multi_prog_redir2") +int multi_prog_redir2(struct bpf_sk_lookup *ctx) +{ + int ret; + + ret = select_server_a(ctx); + bpf_map_update_elem(&run_map, &KEY_PROG2, &PROG_DONE, BPF_ANY); + return SK_PASS; +} + +char _license[] SEC("license") = "Dual BSD/GPL"; +__u32 _version SEC("version") = 1; -- cgit v1.2.3 From 4a09a981002bafdac1decf4116c77bf8f5496326 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 20 Jul 2020 20:55:58 +0300 Subject: testptp: promote 'perout' variable to int64_t Since 'perout' holds the nanosecond value of the signal's period, it should be a 64-bit value. Current assumption is that it cannot be larger than 1 second. Signed-off-by: Vladimir Oltean Acked-by: Richard Cochran Signed-off-by: David S. Miller --- tools/testing/selftests/ptp/testptp.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/ptp/testptp.c b/tools/testing/selftests/ptp/testptp.c index da7a9dda9490..edc1e50768c2 100644 --- a/tools/testing/selftests/ptp/testptp.c +++ b/tools/testing/selftests/ptp/testptp.c @@ -35,6 +35,8 @@ #define CLOCK_INVALID -1 #endif +#define NSEC_PER_SEC 1000000000LL + /* clock_adjtime is not available in GLIBC < 2.14 */ #if !__GLIBC_PREREQ(2, 14) #include @@ -169,7 +171,6 @@ int main(int argc, char *argv[]) int list_pins = 0; int pct_offset = 0; int n_samples = 0; - int perout = -1; int pin_index = -1, pin_func; int pps = -1; int seconds = 0; @@ -177,6 +178,7 @@ int main(int argc, char *argv[]) int64_t t1, t2, tp; int64_t interval, offset; + int64_t perout = -1; progname = strrchr(argv[0], '/'); progname = progname ? 1+progname : argv[0]; @@ -215,7 +217,7 @@ int main(int argc, char *argv[]) } break; case 'p': - perout = atoi(optarg); + perout = atoll(optarg); break; case 'P': pps = atoi(optarg); @@ -400,8 +402,8 @@ int main(int argc, char *argv[]) perout_request.index = index; perout_request.start.sec = ts.tv_sec + 2; perout_request.start.nsec = 0; - perout_request.period.sec = 0; - perout_request.period.nsec = perout; + perout_request.period.sec = perout / NSEC_PER_SEC; + perout_request.period.nsec = perout % NSEC_PER_SEC; if (ioctl(fd, PTP_PEROUT_REQUEST, &perout_request)) { perror("PTP_PEROUT_REQUEST"); } else { -- cgit v1.2.3 From 7570ebe0410a1df1c9a44071c18685842d84a7e1 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 20 Jul 2020 20:55:59 +0300 Subject: testptp: add new options for perout phase and pulse width Extend the example program for PTP ancillary functionality with the ability to configure not only the periodic output's period (frequency), but also the phase and duty cycle (pulse width) which were newly introduced. The ioctl level also needs to be updated to the new PTP_PEROUT_REQUEST2, since the original PTP_PEROUT_REQUEST doesn't support this functionality. For an in-tree testing program, not having explicit backwards compatibility is fine, as it should always be tested with the current kernel headers and sources. Tested with an oscilloscope on the felix switch PHC: echo '2 0' > /sys/class/ptp/ptp1/pins/switch_1588_dat0 ./testptp -d /dev/ptp1 -p 1000000000 -w 100000000 -H 1000 -i 0 Signed-off-by: Vladimir Oltean Acked-by: Richard Cochran Signed-off-by: David S. Miller --- tools/testing/selftests/ptp/testptp.c | 41 +++++++++++++++++++++++++++++++---- 1 file changed, 37 insertions(+), 4 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/ptp/testptp.c b/tools/testing/selftests/ptp/testptp.c index edc1e50768c2..f7911aaeb007 100644 --- a/tools/testing/selftests/ptp/testptp.c +++ b/tools/testing/selftests/ptp/testptp.c @@ -134,6 +134,8 @@ static void usage(char *progname) " 1 - external time stamp\n" " 2 - periodic output\n" " -p val enable output with a period of 'val' nanoseconds\n" + " -H val set output phase to 'val' nanoseconds (requires -p)\n" + " -w val set output pulse width to 'val' nanoseconds (requires -p)\n" " -P val enable or disable (val=1|0) the system clock PPS\n" " -s set the ptp clock time from the system time\n" " -S set the system time from the ptp clock time\n" @@ -178,11 +180,13 @@ int main(int argc, char *argv[]) int64_t t1, t2, tp; int64_t interval, offset; + int64_t perout_phase = -1; + int64_t pulsewidth = -1; int64_t perout = -1; progname = strrchr(argv[0], '/'); progname = progname ? 1+progname : argv[0]; - while (EOF != (c = getopt(argc, argv, "cd:e:f:ghi:k:lL:p:P:sSt:T:z"))) { + while (EOF != (c = getopt(argc, argv, "cd:e:f:ghH:i:k:lL:p:P:sSt:T:w:z"))) { switch (c) { case 'c': capabilities = 1; @@ -199,6 +203,9 @@ int main(int argc, char *argv[]) case 'g': gettime = 1; break; + case 'H': + perout_phase = atoll(optarg); + break; case 'i': index = atoi(optarg); break; @@ -235,6 +242,9 @@ int main(int argc, char *argv[]) settime = 3; seconds = atoi(optarg); break; + case 'w': + pulsewidth = atoi(optarg); + break; case 'z': flagtest = 1; break; @@ -393,6 +403,16 @@ int main(int argc, char *argv[]) } } + if (pulsewidth >= 0 && perout < 0) { + puts("-w can only be specified together with -p"); + return -1; + } + + if (perout_phase >= 0 && perout < 0) { + puts("-H can only be specified together with -p"); + return -1; + } + if (perout >= 0) { if (clock_gettime(clkid, &ts)) { perror("clock_gettime"); @@ -400,11 +420,24 @@ int main(int argc, char *argv[]) } memset(&perout_request, 0, sizeof(perout_request)); perout_request.index = index; - perout_request.start.sec = ts.tv_sec + 2; - perout_request.start.nsec = 0; perout_request.period.sec = perout / NSEC_PER_SEC; perout_request.period.nsec = perout % NSEC_PER_SEC; - if (ioctl(fd, PTP_PEROUT_REQUEST, &perout_request)) { + perout_request.flags = 0; + if (pulsewidth >= 0) { + perout_request.flags |= PTP_PEROUT_DUTY_CYCLE; + perout_request.on.sec = pulsewidth / NSEC_PER_SEC; + perout_request.on.nsec = pulsewidth % NSEC_PER_SEC; + } + if (perout_phase >= 0) { + perout_request.flags |= PTP_PEROUT_PHASE; + perout_request.phase.sec = perout_phase / NSEC_PER_SEC; + perout_request.phase.nsec = perout_phase % NSEC_PER_SEC; + } else { + perout_request.start.sec = ts.tv_sec + 2; + perout_request.start.nsec = 0; + } + + if (ioctl(fd, PTP_PEROUT_REQUEST2, &perout_request)) { perror("PTP_PEROUT_REQUEST"); } else { puts("periodic output request okay"); -- cgit v1.2.3 From 2b9843fbe15276a98cae74d5818dd55600e19052 Mon Sep 17 00:00:00 2001 From: Briana Oursler Date: Fri, 17 Jul 2020 14:54:39 -0700 Subject: tc-testing: Add tdc to kselftests Add tdc to existing kselftest infrastructure so that it can be run with existing kselftests. TDC now generates objects in objdir/kselftest without cluttering main objdir, leaves source directory clean, and installs correctly in kselftest_install, properly adding itself to run_kselftest.sh script. Add tc-testing as a target of selftests/Makefile. Create tdc.sh to run tdc.py targets with correct arguments. To support single target from selftest/Makefile, combine tc-testing/bpf/Makefile and tc-testing/Makefile. Move action.c up a directory to tc-testing/. Tested with: make O=/tmp/{objdir} TARGETS="tc-testing" kselftest cd /tmp/{objdir} cd kselftest cd tc-testing ./tdc.sh make -C tools/testing/selftests/ TARGETS=tc-testing run_tests make TARGETS="tc-testing" kselftest cd tools/testing/selftests ./kselftest_install.sh /tmp/exampledir My VM doesn't run all the kselftests so I commented out all except my target and net/pmtu.sh then: cd /tmp/exampledir && ./run_kselftest.sh Co-developed-by: Davide Caratti Signed-off-by: Davide Caratti Signed-off-by: Briana Oursler Signed-off-by: David S. Miller --- tools/testing/selftests/Makefile | 1 + tools/testing/selftests/tc-testing/Makefile | 33 ++++++++++++++++++++++++ tools/testing/selftests/tc-testing/action.c | 23 +++++++++++++++++ tools/testing/selftests/tc-testing/bpf/Makefile | 30 --------------------- tools/testing/selftests/tc-testing/bpf/action.c | 23 ----------------- tools/testing/selftests/tc-testing/tdc.sh | 5 ++++ tools/testing/selftests/tc-testing/tdc_config.py | 2 +- 7 files changed, 63 insertions(+), 54 deletions(-) create mode 100644 tools/testing/selftests/tc-testing/Makefile create mode 100644 tools/testing/selftests/tc-testing/action.c delete mode 100644 tools/testing/selftests/tc-testing/bpf/Makefile delete mode 100644 tools/testing/selftests/tc-testing/bpf/action.c create mode 100755 tools/testing/selftests/tc-testing/tdc.sh (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 1195bd85af38..f4522e0a2cab 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -54,6 +54,7 @@ TARGETS += splice TARGETS += static_keys TARGETS += sync TARGETS += sysctl +TARGETS += tc-testing TARGETS += timens ifneq (1, $(quicktest)) TARGETS += timers diff --git a/tools/testing/selftests/tc-testing/Makefile b/tools/testing/selftests/tc-testing/Makefile new file mode 100644 index 000000000000..91fee5c43274 --- /dev/null +++ b/tools/testing/selftests/tc-testing/Makefile @@ -0,0 +1,33 @@ +# SPDX-License-Identifier: GPL-2.0 + +top_srcdir = $(abspath ../../../..) +APIDIR := $(top_scrdir)/include/uapi +TEST_GEN_FILES = action.o + +KSFT_KHDR_INSTALL := 1 +include ../lib.mk + +CLANG ?= clang +LLC ?= llc +PROBE := $(shell $(LLC) -march=bpf -mcpu=probe -filetype=null /dev/null 2>&1) + +ifeq ($(PROBE),) + CPU ?= probe +else + CPU ?= generic +endif + +CLANG_SYS_INCLUDES := $(shell $(CLANG) -v -E - &1 \ + | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') + +CLANG_FLAGS = -I. -I$(APIDIR) \ + $(CLANG_SYS_INCLUDES) \ + -Wno-compare-distinct-pointer-types + +$(OUTPUT)/%.o: %.c + $(CLANG) $(CLANG_FLAGS) \ + -O2 -target bpf -emit-llvm -c $< -o - | \ + $(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@ + +TEST_PROGS += ./tdc.sh +TEST_FILES := tdc*.py Tdc*.py plugins plugin-lib tc-tests diff --git a/tools/testing/selftests/tc-testing/action.c b/tools/testing/selftests/tc-testing/action.c new file mode 100644 index 000000000000..c32b99b80e19 --- /dev/null +++ b/tools/testing/selftests/tc-testing/action.c @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 + * Copyright (c) 2018 Davide Caratti, Red Hat inc. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ + +#include +#include + +__attribute__((section("action-ok"),used)) int action_ok(struct __sk_buff *s) +{ + return TC_ACT_OK; +} + +__attribute__((section("action-ko"),used)) int action_ko(struct __sk_buff *s) +{ + s->data = 0x0; + return TC_ACT_OK; +} + +char _license[] __attribute__((section("license"),used)) = "GPL"; diff --git a/tools/testing/selftests/tc-testing/bpf/Makefile b/tools/testing/selftests/tc-testing/bpf/Makefile deleted file mode 100644 index be5a5e542804..000000000000 --- a/tools/testing/selftests/tc-testing/bpf/Makefile +++ /dev/null @@ -1,30 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 - -APIDIR := ../../../../include/uapi -TEST_GEN_FILES = action.o - -top_srcdir = ../../../../.. -KSFT_KHDR_INSTALL := 1 -include ../../lib.mk - -CLANG ?= clang -LLC ?= llc -PROBE := $(shell $(LLC) -march=bpf -mcpu=probe -filetype=null /dev/null 2>&1) - -ifeq ($(PROBE),) - CPU ?= probe -else - CPU ?= generic -endif - -CLANG_SYS_INCLUDES := $(shell $(CLANG) -v -E - &1 \ - | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') - -CLANG_FLAGS = -I. -I$(APIDIR) \ - $(CLANG_SYS_INCLUDES) \ - -Wno-compare-distinct-pointer-types - -$(OUTPUT)/%.o: %.c - $(CLANG) $(CLANG_FLAGS) \ - -O2 -target bpf -emit-llvm -c $< -o - | \ - $(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@ diff --git a/tools/testing/selftests/tc-testing/bpf/action.c b/tools/testing/selftests/tc-testing/bpf/action.c deleted file mode 100644 index c32b99b80e19..000000000000 --- a/tools/testing/selftests/tc-testing/bpf/action.c +++ /dev/null @@ -1,23 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 - * Copyright (c) 2018 Davide Caratti, Red Hat inc. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of version 2 of the GNU General Public - * License as published by the Free Software Foundation. - */ - -#include -#include - -__attribute__((section("action-ok"),used)) int action_ok(struct __sk_buff *s) -{ - return TC_ACT_OK; -} - -__attribute__((section("action-ko"),used)) int action_ko(struct __sk_buff *s) -{ - s->data = 0x0; - return TC_ACT_OK; -} - -char _license[] __attribute__((section("license"),used)) = "GPL"; diff --git a/tools/testing/selftests/tc-testing/tdc.sh b/tools/testing/selftests/tc-testing/tdc.sh new file mode 100755 index 000000000000..7fe38c76db44 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tdc.sh @@ -0,0 +1,5 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +./tdc.py -c actions --nobuildebpf +./tdc.py -c qdisc diff --git a/tools/testing/selftests/tc-testing/tdc_config.py b/tools/testing/selftests/tc-testing/tdc_config.py index 080709cc4297..cd4a27ee1466 100644 --- a/tools/testing/selftests/tc-testing/tdc_config.py +++ b/tools/testing/selftests/tc-testing/tdc_config.py @@ -24,7 +24,7 @@ NAMES = { # Name of the namespace to use 'NS': 'tcut', # Directory containing eBPF test programs - 'EBPFDIR': './bpf' + 'EBPFDIR': './' } -- cgit v1.2.3 From 2ea485980734500d41e4530f038d94a21e2b3b34 Mon Sep 17 00:00:00 2001 From: Ilya Leoshkevich Date: Fri, 17 Jul 2020 18:53:22 +0200 Subject: selftests: bpf: test_kmod.sh: Fix running out of srctree When running out of srctree, relative path to lib/test_bpf.ko is different than when running in srctree. Check $building_out_of_srctree environment variable and use a different relative path if needed. Signed-off-by: Ilya Leoshkevich Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200717165326.6786-2-iii@linux.ibm.com --- tools/testing/selftests/bpf/test_kmod.sh | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/test_kmod.sh b/tools/testing/selftests/bpf/test_kmod.sh index 9df0d2ac45f8..4f6444bcd53f 100755 --- a/tools/testing/selftests/bpf/test_kmod.sh +++ b/tools/testing/selftests/bpf/test_kmod.sh @@ -10,7 +10,13 @@ if [ "$(id -u)" != "0" ]; then exit $ksft_skip fi -SRC_TREE=../../../../ +if [ "$building_out_of_srctree" ]; then + # We are in linux-build/kselftest/bpf + OUTPUT=../../ +else + # We are in linux/tools/testing/selftests/bpf + OUTPUT=../../../../ +fi test_run() { @@ -19,8 +25,8 @@ test_run() echo "[ JIT enabled:$1 hardened:$2 ]" dmesg -C - if [ -f ${SRC_TREE}/lib/test_bpf.ko ]; then - insmod ${SRC_TREE}/lib/test_bpf.ko 2> /dev/null + if [ -f ${OUTPUT}/lib/test_bpf.ko ]; then + insmod ${OUTPUT}/lib/test_bpf.ko 2> /dev/null if [ $? -ne 0 ]; then rc=1 fi -- cgit v1.2.3 From 6bd557275ad5a1adaff5082f4e24218ba344e0c0 Mon Sep 17 00:00:00 2001 From: Ilya Leoshkevich Date: Mon, 20 Jul 2020 12:18:10 +0200 Subject: selftests/bpf: Fix test_lwt_seg6local.sh hangs OpenBSD netcat (Debian patchlevel 1.195-2) does not seem to react to SIGINT for whatever reason, causing prefix.pl to hang after test_lwt_seg6local.sh exits due to netcat inheriting test_lwt_seg6local.sh's file descriptors. Fix by using SIGTERM instead. Signed-off-by: Ilya Leoshkevich Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200720101810.84299-1-iii@linux.ibm.com --- tools/testing/selftests/bpf/test_lwt_seg6local.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/test_lwt_seg6local.sh b/tools/testing/selftests/bpf/test_lwt_seg6local.sh index 785eabf2a593..5620919fde9e 100755 --- a/tools/testing/selftests/bpf/test_lwt_seg6local.sh +++ b/tools/testing/selftests/bpf/test_lwt_seg6local.sh @@ -140,7 +140,7 @@ ip netns exec ns6 sysctl net.ipv6.conf.veth10.seg6_enabled=1 > /dev/null ip netns exec ns6 nc -l -6 -u -d 7330 > $TMP_FILE & ip netns exec ns1 bash -c "echo 'foobar' | nc -w0 -6 -u -p 2121 -s fb00::1 fb00::6 7330" sleep 5 # wait enough time to ensure the UDP datagram arrived to the last segment -kill -INT $! +kill -TERM $! if [[ $(< $TMP_FILE) != "foobar" ]]; then exit 1 -- cgit v1.2.3 From e4d9c2320716ea0e9ef59f503ddd8f253a642ddd Mon Sep 17 00:00:00 2001 From: Ilya Leoshkevich Date: Mon, 20 Jul 2020 13:48:06 +0200 Subject: samples/bpf, selftests/bpf: Use bpf_probe_read_kernel A handful of samples and selftests fail to build on s390, because after commit 0ebeea8ca8a4 ("bpf: Restrict bpf_probe_read{, str}() only to archs where they work") bpf_probe_read is not available anymore. Fix by using bpf_probe_read_kernel. Signed-off-by: Ilya Leoshkevich Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200720114806.88823-1-iii@linux.ibm.com --- samples/bpf/offwaketime_kern.c | 7 ++++++- samples/bpf/test_overhead_kprobe_kern.c | 12 +++++++++--- samples/bpf/tracex1_kern.c | 9 +++++++-- samples/bpf/tracex5_kern.c | 4 ++-- tools/bpf/bpftool/skeleton/pid_iter.bpf.c | 3 ++- tools/testing/selftests/bpf/progs/bpf_iter_netlink.c | 6 +++--- tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c | 2 +- tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c | 2 +- tools/testing/selftests/bpf/progs/bpf_iter_udp4.c | 2 +- tools/testing/selftests/bpf/progs/bpf_iter_udp6.c | 2 +- 10 files changed, 33 insertions(+), 16 deletions(-) (limited to 'tools/testing/selftests') diff --git a/samples/bpf/offwaketime_kern.c b/samples/bpf/offwaketime_kern.c index d459f73412a4..e74ee1cd4b9c 100644 --- a/samples/bpf/offwaketime_kern.c +++ b/samples/bpf/offwaketime_kern.c @@ -12,7 +12,12 @@ #include #include -#define _(P) ({typeof(P) val; bpf_probe_read(&val, sizeof(val), &P); val;}) +#define _(P) \ + ({ \ + typeof(P) val; \ + bpf_probe_read_kernel(&val, sizeof(val), &(P)); \ + val; \ + }) #define MINBLOCK_US 1 diff --git a/samples/bpf/test_overhead_kprobe_kern.c b/samples/bpf/test_overhead_kprobe_kern.c index 8b811c29dc79..f6d593e47037 100644 --- a/samples/bpf/test_overhead_kprobe_kern.c +++ b/samples/bpf/test_overhead_kprobe_kern.c @@ -10,7 +10,12 @@ #include #include -#define _(P) ({typeof(P) val = 0; bpf_probe_read(&val, sizeof(val), &P); val;}) +#define _(P) \ + ({ \ + typeof(P) val = 0; \ + bpf_probe_read_kernel(&val, sizeof(val), &(P)); \ + val; \ + }) SEC("kprobe/__set_task_comm") int prog(struct pt_regs *ctx) @@ -25,8 +30,9 @@ int prog(struct pt_regs *ctx) tsk = (void *)PT_REGS_PARM1(ctx); pid = _(tsk->pid); - bpf_probe_read(oldcomm, sizeof(oldcomm), &tsk->comm); - bpf_probe_read(newcomm, sizeof(newcomm), (void *)PT_REGS_PARM2(ctx)); + bpf_probe_read_kernel(oldcomm, sizeof(oldcomm), &tsk->comm); + bpf_probe_read_kernel(newcomm, sizeof(newcomm), + (void *)PT_REGS_PARM2(ctx)); signal = _(tsk->signal); oom_score_adj = _(signal->oom_score_adj); return 0; diff --git a/samples/bpf/tracex1_kern.c b/samples/bpf/tracex1_kern.c index 8e2610e14475..3f4599c9a202 100644 --- a/samples/bpf/tracex1_kern.c +++ b/samples/bpf/tracex1_kern.c @@ -11,7 +11,12 @@ #include #include -#define _(P) ({typeof(P) val = 0; bpf_probe_read(&val, sizeof(val), &P); val;}) +#define _(P) \ + ({ \ + typeof(P) val = 0; \ + bpf_probe_read_kernel(&val, sizeof(val), &(P)); \ + val; \ + }) /* kprobe is NOT a stable ABI * kernel functions can be removed, renamed or completely change semantics. @@ -34,7 +39,7 @@ int bpf_prog1(struct pt_regs *ctx) dev = _(skb->dev); len = _(skb->len); - bpf_probe_read(devname, sizeof(devname), dev->name); + bpf_probe_read_kernel(devname, sizeof(devname), dev->name); if (devname[0] == 'l' && devname[1] == 'o') { char fmt[] = "skb %p len %d\n"; diff --git a/samples/bpf/tracex5_kern.c b/samples/bpf/tracex5_kern.c index 32b49e8ab6bd..64a1f7550d7e 100644 --- a/samples/bpf/tracex5_kern.c +++ b/samples/bpf/tracex5_kern.c @@ -47,7 +47,7 @@ PROG(SYS__NR_write)(struct pt_regs *ctx) { struct seccomp_data sd; - bpf_probe_read(&sd, sizeof(sd), (void *)PT_REGS_PARM2(ctx)); + bpf_probe_read_kernel(&sd, sizeof(sd), (void *)PT_REGS_PARM2(ctx)); if (sd.args[2] == 512) { char fmt[] = "write(fd=%d, buf=%p, size=%d)\n"; bpf_trace_printk(fmt, sizeof(fmt), @@ -60,7 +60,7 @@ PROG(SYS__NR_read)(struct pt_regs *ctx) { struct seccomp_data sd; - bpf_probe_read(&sd, sizeof(sd), (void *)PT_REGS_PARM2(ctx)); + bpf_probe_read_kernel(&sd, sizeof(sd), (void *)PT_REGS_PARM2(ctx)); if (sd.args[2] > 128 && sd.args[2] <= 1024) { char fmt[] = "read(fd=%d, buf=%p, size=%d)\n"; bpf_trace_printk(fmt, sizeof(fmt), diff --git a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c index 8468a608911e..d9b420972934 100644 --- a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c +++ b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c @@ -71,7 +71,8 @@ int iter(struct bpf_iter__task_file *ctx) e.pid = task->tgid; e.id = get_obj_id(file->private_data, obj_type); - bpf_probe_read(&e.comm, sizeof(e.comm), task->group_leader->comm); + bpf_probe_read_kernel(&e.comm, sizeof(e.comm), + task->group_leader->comm); bpf_seq_write(ctx->meta->seq, &e, sizeof(e)); return 0; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c index 7de98a68599a..95989f4c99b5 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c @@ -36,10 +36,10 @@ int dump_netlink(struct bpf_iter__netlink *ctx) if (!nlk->groups) { group = 0; } else { - /* FIXME: temporary use bpf_probe_read here, needs + /* FIXME: temporary use bpf_probe_read_kernel here, needs * verifier support to do direct access. */ - bpf_probe_read(&group, sizeof(group), &nlk->groups[0]); + bpf_probe_read_kernel(&group, sizeof(group), &nlk->groups[0]); } BPF_SEQ_PRINTF(seq, "%-10u %08x %-8d %-8d %-5d %-8d ", nlk->portid, (u32)group, @@ -56,7 +56,7 @@ int dump_netlink(struct bpf_iter__netlink *ctx) * with current verifier. */ inode = SOCK_INODE(sk); - bpf_probe_read(&ino, sizeof(ino), &inode->i_ino); + bpf_probe_read_kernel(&ino, sizeof(ino), &inode->i_ino); } BPF_SEQ_PRINTF(seq, "%-8u %-8lu\n", s->sk_drops.counter, ino); diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c b/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c index 30fd587cb325..54380c5e1069 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c @@ -57,7 +57,7 @@ static long sock_i_ino(const struct sock *sk) return 0; inode = &container_of(sk_socket, struct socket_alloc, socket)->vfs_inode; - bpf_probe_read(&ino, sizeof(ino), &inode->i_ino); + bpf_probe_read_kernel(&ino, sizeof(ino), &inode->i_ino); return ino; } diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c b/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c index 10dec4392031..b4fbddfa4e10 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c @@ -57,7 +57,7 @@ static long sock_i_ino(const struct sock *sk) return 0; inode = &container_of(sk_socket, struct socket_alloc, socket)->vfs_inode; - bpf_probe_read(&ino, sizeof(ino), &inode->i_ino); + bpf_probe_read_kernel(&ino, sizeof(ino), &inode->i_ino); return ino; } diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c b/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c index 7053784575e4..f258583afbbd 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c @@ -18,7 +18,7 @@ static long sock_i_ino(const struct sock *sk) return 0; inode = &container_of(sk_socket, struct socket_alloc, socket)->vfs_inode; - bpf_probe_read(&ino, sizeof(ino), &inode->i_ino); + bpf_probe_read_kernel(&ino, sizeof(ino), &inode->i_ino); return ino; } diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c b/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c index c1175a6ecf43..65f93bb03f0f 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c @@ -25,7 +25,7 @@ static long sock_i_ino(const struct sock *sk) return 0; inode = &container_of(sk_socket, struct socket_alloc, socket)->vfs_inode; - bpf_probe_read(&ino, sizeof(ino), &inode->i_ino); + bpf_probe_read_kernel(&ino, sizeof(ino), &inode->i_ino); return ino; } -- cgit v1.2.3 From d8dfe5bfe856c0c72b1750322dbfcad402e73373 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Mon, 20 Jul 2020 09:33:59 -0700 Subject: tools/bpf: Sync btf_ids.h to tools Sync kernel header btf_ids.h to tools directory. Also define macro CONFIG_DEBUG_INFO_BTF before including btf_ids.h in prog_tests/resolve_btfids.c since non-stub definitions for BTF_ID_LIST etc. macros are defined under CONFIG_DEBUG_INFO_BTF. This prevented test_progs from failing. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200720163359.1393079-1-yhs@fb.com --- tools/include/linux/btf_ids.h | 11 ++++++++++- tools/testing/selftests/bpf/prog_tests/resolve_btfids.c | 1 + 2 files changed, 11 insertions(+), 1 deletion(-) (limited to 'tools/testing/selftests') diff --git a/tools/include/linux/btf_ids.h b/tools/include/linux/btf_ids.h index fe019774f8a7..1cdb56950ffe 100644 --- a/tools/include/linux/btf_ids.h +++ b/tools/include/linux/btf_ids.h @@ -3,6 +3,8 @@ #ifndef _LINUX_BTF_IDS_H #define _LINUX_BTF_IDS_H +#ifdef CONFIG_DEBUG_INFO_BTF + #include /* for __PASTE */ /* @@ -21,7 +23,7 @@ asm( \ ".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ ".local " #symbol " ; \n" \ -".type " #symbol ", @object; \n" \ +".type " #symbol ", STT_OBJECT; \n" \ ".size " #symbol ", 4; \n" \ #symbol ": \n" \ ".zero 4 \n" \ @@ -83,5 +85,12 @@ asm( \ ".zero 4 \n" \ ".popsection; \n"); +#else + +#define BTF_ID_LIST(name) static u32 name[5]; +#define BTF_ID(prefix, name) +#define BTF_ID_UNUSED + +#endif /* CONFIG_DEBUG_INFO_BTF */ #endif diff --git a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c index 403be6f36cba..22d83bba4e91 100644 --- a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c +++ b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c @@ -6,6 +6,7 @@ #include #include #include +#define CONFIG_DEBUG_INFO_BTF #include #include "test_progs.h" -- cgit v1.2.3 From 0f12e584b241285cf60a6227f3771fa444cfcf76 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Mon, 20 Jul 2020 09:34:01 -0700 Subject: bpf: Add BTF_ID_LIST_GLOBAL in btf_ids.h Existing BTF_ID_LIST used a local static variable to store btf_ids. This patch provided a new macro BTF_ID_LIST_GLOBAL to store btf_ids in a global variable which can be shared among multiple files. The existing BTF_ID_LIST is still retained. Two reasons. First, BTF_ID_LIST is also used to build btf_ids for helper arguments which typically is an array of 5. Since typically different helpers have different signature, it makes little sense to share them. Second, some current computed btf_ids are indeed local. If later those btf_ids are shared between different files, they can use BTF_ID_LIST_GLOBAL then. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Jiri Olsa Link: https://lore.kernel.org/bpf/20200720163401.1393159-1-yhs@fb.com --- include/linux/btf_ids.h | 10 +++++-- tools/include/linux/btf_ids.h | 10 +++++-- .../selftests/bpf/prog_tests/resolve_btfids.c | 33 ++++++++++++++++------ 3 files changed, 39 insertions(+), 14 deletions(-) (limited to 'tools/testing/selftests') diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 1cdb56950ffe..77ab45baa095 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -57,17 +57,20 @@ asm( \ * .zero 4 * */ -#define __BTF_ID_LIST(name) \ +#define __BTF_ID_LIST(name, scope) \ asm( \ ".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ -".local " #name "; \n" \ +"." #scope " " #name "; \n" \ #name ":; \n" \ ".popsection; \n"); \ #define BTF_ID_LIST(name) \ -__BTF_ID_LIST(name) \ +__BTF_ID_LIST(name, local) \ extern u32 name[]; +#define BTF_ID_LIST_GLOBAL(name) \ +__BTF_ID_LIST(name, globl) + /* * The BTF_ID_UNUSED macro defines 4 zero bytes. * It's used when we want to define 'unused' entry @@ -90,6 +93,7 @@ asm( \ #define BTF_ID_LIST(name) static u32 name[5]; #define BTF_ID(prefix, name) #define BTF_ID_UNUSED +#define BTF_ID_LIST_GLOBAL(name) u32 name[1]; #endif /* CONFIG_DEBUG_INFO_BTF */ diff --git a/tools/include/linux/btf_ids.h b/tools/include/linux/btf_ids.h index 1cdb56950ffe..77ab45baa095 100644 --- a/tools/include/linux/btf_ids.h +++ b/tools/include/linux/btf_ids.h @@ -57,17 +57,20 @@ asm( \ * .zero 4 * */ -#define __BTF_ID_LIST(name) \ +#define __BTF_ID_LIST(name, scope) \ asm( \ ".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ -".local " #name "; \n" \ +"." #scope " " #name "; \n" \ #name ":; \n" \ ".popsection; \n"); \ #define BTF_ID_LIST(name) \ -__BTF_ID_LIST(name) \ +__BTF_ID_LIST(name, local) \ extern u32 name[]; +#define BTF_ID_LIST_GLOBAL(name) \ +__BTF_ID_LIST(name, globl) + /* * The BTF_ID_UNUSED macro defines 4 zero bytes. * It's used when we want to define 'unused' entry @@ -90,6 +93,7 @@ asm( \ #define BTF_ID_LIST(name) static u32 name[5]; #define BTF_ID(prefix, name) #define BTF_ID_UNUSED +#define BTF_ID_LIST_GLOBAL(name) u32 name[1]; #endif /* CONFIG_DEBUG_INFO_BTF */ diff --git a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c index 22d83bba4e91..3b127cab4864 100644 --- a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c +++ b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c @@ -28,7 +28,17 @@ struct symbol test_symbols[] = { { "func", BTF_KIND_FUNC, -1 }, }; -BTF_ID_LIST(test_list) +BTF_ID_LIST(test_list_local) +BTF_ID_UNUSED +BTF_ID(typedef, S) +BTF_ID(typedef, T) +BTF_ID(typedef, U) +BTF_ID(struct, S) +BTF_ID(union, U) +BTF_ID(func, func) + +extern __u32 test_list_global[]; +BTF_ID_LIST_GLOBAL(test_list_global) BTF_ID_UNUSED BTF_ID(typedef, S) BTF_ID(typedef, T) @@ -94,18 +104,25 @@ static int resolve_symbols(void) int test_resolve_btfids(void) { - unsigned int i; + __u32 *test_list, *test_lists[] = { test_list_local, test_list_global }; + unsigned int i, j; int ret = 0; if (resolve_symbols()) return -1; - /* Check BTF_ID_LIST(test_list) IDs */ - for (i = 0; i < ARRAY_SIZE(test_symbols) && !ret; i++) { - ret = CHECK(test_list[i] != test_symbols[i].id, - "id_check", - "wrong ID for %s (%d != %d)\n", test_symbols[i].name, - test_list[i], test_symbols[i].id); + /* Check BTF_ID_LIST(test_list_local) and + * BTF_ID_LIST_GLOBAL(test_list_global) IDs + */ + for (j = 0; j < ARRAY_SIZE(test_lists); j++) { + test_list = test_lists[j]; + for (i = 0; i < ARRAY_SIZE(test_symbols) && !ret; i++) { + ret = CHECK(test_list[i] != test_symbols[i].id, + "id_check", + "wrong ID for %s (%d != %d)\n", + test_symbols[i].name, + test_list[i], test_symbols[i].id); + } } return ret; -- cgit v1.2.3 From 1b6687e31a2df9fbdb12d25c1d1d372777bf96a8 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 23 Jul 2020 17:23:09 -0600 Subject: vrf: Handle CONFIG_SYSCTL not set Randy reported compile failure when CONFIG_SYSCTL is not set/enabled: ERROR: modpost: "sysctl_vals" [drivers/net/vrf.ko] undefined! Fix by splitting out the sysctl init and cleanup into helpers that can be set to do nothing when CONFIG_SYSCTL is disabled. In addition, move vrf_strict_mode and vrf_strict_mode_change to above vrf_shared_table_handler (code move only) and wrap all of it in the ifdef CONFIG_SYSCTL. Update the strict mode tests to check for the existence of the /proc/sys entry. Fixes: 33306f1aaf82 ("vrf: add sysctl parameter for strict mode") Cc: Andrea Mayer Reported-by: Randy Dunlap Signed-off-by: David Ahern Acked-by: Randy Dunlap # build-tested Signed-off-by: David S. Miller --- drivers/net/vrf.c | 138 ++++++++++++--------- .../testing/selftests/net/vrf_strict_mode_test.sh | 6 + 2 files changed, 83 insertions(+), 61 deletions(-) (limited to 'tools/testing/selftests') diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 46599606ff10..60c1aadece89 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -260,52 +260,6 @@ static void vrf_map_unlock(struct vrf_map *vmap) __releases(&vmap->vmap_lock) spin_unlock(&vmap->vmap_lock); } -static bool vrf_strict_mode(struct vrf_map *vmap) -{ - bool strict_mode; - - vrf_map_lock(vmap); - strict_mode = vmap->strict_mode; - vrf_map_unlock(vmap); - - return strict_mode; -} - -static int vrf_strict_mode_change(struct vrf_map *vmap, bool new_mode) -{ - bool *cur_mode; - int res = 0; - - vrf_map_lock(vmap); - - cur_mode = &vmap->strict_mode; - if (*cur_mode == new_mode) - goto unlock; - - if (*cur_mode) { - /* disable strict mode */ - *cur_mode = false; - } else { - if (vmap->shared_tables) { - /* we cannot allow strict_mode because there are some - * vrfs that share one or more tables. - */ - res = -EBUSY; - goto unlock; - } - - /* no tables are shared among vrfs, so we can go back - * to 1:1 association between a vrf with its table. - */ - *cur_mode = true; - } - -unlock: - vrf_map_unlock(vmap); - - return res; -} - /* called with rtnl lock held */ static int vrf_map_register_dev(struct net_device *dev, struct netlink_ext_ack *extack) @@ -1790,6 +1744,53 @@ static int vrf_map_init(struct vrf_map *vmap) return 0; } +#ifdef CONFIG_SYSCTL +static bool vrf_strict_mode(struct vrf_map *vmap) +{ + bool strict_mode; + + vrf_map_lock(vmap); + strict_mode = vmap->strict_mode; + vrf_map_unlock(vmap); + + return strict_mode; +} + +static int vrf_strict_mode_change(struct vrf_map *vmap, bool new_mode) +{ + bool *cur_mode; + int res = 0; + + vrf_map_lock(vmap); + + cur_mode = &vmap->strict_mode; + if (*cur_mode == new_mode) + goto unlock; + + if (*cur_mode) { + /* disable strict mode */ + *cur_mode = false; + } else { + if (vmap->shared_tables) { + /* we cannot allow strict_mode because there are some + * vrfs that share one or more tables. + */ + res = -EBUSY; + goto unlock; + } + + /* no tables are shared among vrfs, so we can go back + * to 1:1 association between a vrf with its table. + */ + *cur_mode = true; + } + +unlock: + vrf_map_unlock(vmap); + + return res; +} + static int vrf_shared_table_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -1830,15 +1831,9 @@ static const struct ctl_table vrf_table[] = { { }, }; -/* Initialize per network namespace state */ -static int __net_init vrf_netns_init(struct net *net) +static int vrf_netns_init_sysctl(struct net *net, struct netns_vrf *nn_vrf) { - struct netns_vrf *nn_vrf = net_generic(net, vrf_net_id); struct ctl_table *table; - int res; - - nn_vrf->add_fib_rules = true; - vrf_map_init(&nn_vrf->vmap); table = kmemdup(vrf_table, sizeof(vrf_table), GFP_KERNEL); if (!table) @@ -1849,19 +1844,14 @@ static int __net_init vrf_netns_init(struct net *net) nn_vrf->ctl_hdr = register_net_sysctl(net, "net/vrf", table); if (!nn_vrf->ctl_hdr) { - res = -ENOMEM; - goto free_table; + kfree(table); + return -ENOMEM; } return 0; - -free_table: - kfree(table); - - return res; } -static void __net_exit vrf_netns_exit(struct net *net) +static void vrf_netns_exit_sysctl(struct net *net) { struct netns_vrf *nn_vrf = net_generic(net, vrf_net_id); struct ctl_table *table; @@ -1870,6 +1860,32 @@ static void __net_exit vrf_netns_exit(struct net *net) unregister_net_sysctl_table(nn_vrf->ctl_hdr); kfree(table); } +#else +static int vrf_netns_init_sysctl(struct net *net, struct netns_vrf *nn_vrf) +{ + return 0; +} + +static void vrf_netns_exit_sysctl(struct net *net) +{ +} +#endif + +/* Initialize per network namespace state */ +static int __net_init vrf_netns_init(struct net *net) +{ + struct netns_vrf *nn_vrf = net_generic(net, vrf_net_id); + + nn_vrf->add_fib_rules = true; + vrf_map_init(&nn_vrf->vmap); + + return vrf_netns_init_sysctl(net, nn_vrf); +} + +static void __net_exit vrf_netns_exit(struct net *net) +{ + vrf_netns_exit_sysctl(net); +} static struct pernet_operations vrf_net_ops __net_initdata = { .init = vrf_netns_init, diff --git a/tools/testing/selftests/net/vrf_strict_mode_test.sh b/tools/testing/selftests/net/vrf_strict_mode_test.sh index 5274f4a1fba1..18b982d611de 100755 --- a/tools/testing/selftests/net/vrf_strict_mode_test.sh +++ b/tools/testing/selftests/net/vrf_strict_mode_test.sh @@ -379,6 +379,12 @@ if [ ! -x "$(command -v ip)" ]; then exit 0 fi +modprobe vrf &>/dev/null +if [ ! -e /proc/sys/net/vrf/strict_mode ]; then + echo "SKIP: vrf sysctl does not exist" + exit 0 +fi + cleanup &> /dev/null setup -- cgit v1.2.3 From 86176a1821a1237ad163d312ba0f2d7598757894 Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Wed, 22 Jul 2020 18:17:20 +0200 Subject: selftests/bpf: Test BPF socket lookup and reuseport with connections Cover the case when BPF socket lookup returns a socket that belongs to a reuseport group, and the reuseport group contains connected UDP sockets. Ensure that the presence of connected UDP sockets in reuseport group does not affect the socket lookup result. Socket selected by reuseport should always be used as result in such case. Signed-off-by: Jakub Sitnicki Signed-off-by: Alexei Starovoitov Acked-by: Kuniyuki Iwashima Link: https://lore.kernel.org/bpf/20200722161720.940831-3-jakub@cloudflare.com --- tools/testing/selftests/bpf/prog_tests/sk_lookup.c | 54 +++++++++++++++++++++- 1 file changed, 53 insertions(+), 1 deletion(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c index f1784ae4565a..9bbd2b2b7630 100644 --- a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c +++ b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c @@ -74,6 +74,7 @@ struct test { struct inet_addr connect_to; struct inet_addr listen_at; enum server accept_on; + bool reuseport_has_conns; /* Add a connected socket to reuseport group */ }; static __u32 duration; /* for CHECK macro */ @@ -559,7 +560,8 @@ close: static void run_lookup_prog(const struct test *t) { - int client_fd, server_fds[MAX_SERVERS] = { -1 }; + int server_fds[MAX_SERVERS] = { -1 }; + int client_fd, reuse_conn_fd = -1; struct bpf_link *lookup_link; int i, err; @@ -583,6 +585,32 @@ static void run_lookup_prog(const struct test *t) break; } + /* Regular UDP socket lookup with reuseport behaves + * differently when reuseport group contains connected + * sockets. Check that adding a connected UDP socket to the + * reuseport group does not affect how reuseport works with + * BPF socket lookup. + */ + if (t->reuseport_has_conns) { + struct sockaddr_storage addr = {}; + socklen_t len = sizeof(addr); + + /* Add an extra socket to reuseport group */ + reuse_conn_fd = make_server(t->sotype, t->listen_at.ip, + t->listen_at.port, + t->reuseport_prog); + if (reuse_conn_fd < 0) + goto close; + + /* Connect the extra socket to itself */ + err = getsockname(reuse_conn_fd, (void *)&addr, &len); + if (CHECK(err, "getsockname", "errno %d\n", errno)) + goto close; + err = connect(reuse_conn_fd, (void *)&addr, len); + if (CHECK(err, "connect", "errno %d\n", errno)) + goto close; + } + client_fd = make_client(t->sotype, t->connect_to.ip, t->connect_to.port); if (client_fd < 0) goto close; @@ -594,6 +622,8 @@ static void run_lookup_prog(const struct test *t) close(client_fd); close: + if (reuse_conn_fd != -1) + close(reuse_conn_fd); for (i = 0; i < ARRAY_SIZE(server_fds); i++) { if (server_fds[i] != -1) close(server_fds[i]); @@ -710,6 +740,17 @@ static void test_redirect_lookup(struct test_sk_lookup *skel) .listen_at = { INT_IP4, INT_PORT }, .accept_on = SERVER_B, }, + { + .desc = "UDP IPv4 redir and reuseport with conns", + .lookup_prog = skel->progs.select_sock_a, + .reuseport_prog = skel->progs.select_sock_b, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_DGRAM, + .connect_to = { EXT_IP4, EXT_PORT }, + .listen_at = { INT_IP4, INT_PORT }, + .accept_on = SERVER_B, + .reuseport_has_conns = true, + }, { .desc = "UDP IPv4 redir skip reuseport", .lookup_prog = skel->progs.select_sock_a_no_reuseport, @@ -754,6 +795,17 @@ static void test_redirect_lookup(struct test_sk_lookup *skel) .listen_at = { INT_IP6, INT_PORT }, .accept_on = SERVER_B, }, + { + .desc = "UDP IPv6 redir and reuseport with conns", + .lookup_prog = skel->progs.select_sock_a, + .reuseport_prog = skel->progs.select_sock_b, + .sock_map = skel->maps.redir_map, + .sotype = SOCK_DGRAM, + .connect_to = { EXT_IP6, EXT_PORT }, + .listen_at = { INT_IP6, INT_PORT }, + .accept_on = SERVER_B, + .reuseport_has_conns = true, + }, { .desc = "UDP IPv6 redir skip reuseport", .lookup_prog = skel->progs.select_sock_a_no_reuseport, -- cgit v1.2.3 From 2a7c2fff7dd6e87634e47ddb2d2c7f272708dbbf Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 23 Jul 2020 11:41:20 -0700 Subject: selftests/bpf: Add test for bpf hash map iterators Two subtests are added. $ ./test_progs -n 4 ... #4/18 bpf_hash_map:OK #4/19 bpf_percpu_hash_map:OK ... Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200723184120.590916-1-yhs@fb.com --- tools/testing/selftests/bpf/prog_tests/bpf_iter.c | 187 +++++++++++++++++++++ .../selftests/bpf/progs/bpf_iter_bpf_hash_map.c | 100 +++++++++++ .../bpf/progs/bpf_iter_bpf_percpu_hash_map.c | 50 ++++++ 3 files changed, 337 insertions(+) create mode 100644 tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c create mode 100644 tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_hash_map.c (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index fed42755416d..72790b600c62 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -15,6 +15,8 @@ #include "bpf_iter_test_kern2.skel.h" #include "bpf_iter_test_kern3.skel.h" #include "bpf_iter_test_kern4.skel.h" +#include "bpf_iter_bpf_hash_map.skel.h" +#include "bpf_iter_bpf_percpu_hash_map.skel.h" static int duration; @@ -455,6 +457,187 @@ out: bpf_iter_test_kern4__destroy(skel); } +static void test_bpf_hash_map(void) +{ + __u32 expected_key_a = 0, expected_key_b = 0, expected_key_c = 0; + DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts); + struct bpf_iter_bpf_hash_map *skel; + int err, i, len, map_fd, iter_fd; + __u64 val, expected_val = 0; + struct bpf_link *link; + struct key_t { + int a; + int b; + int c; + } key; + char buf[64]; + + skel = bpf_iter_bpf_hash_map__open(); + if (CHECK(!skel, "bpf_iter_bpf_hash_map__open", + "skeleton open failed\n")) + return; + + skel->bss->in_test_mode = true; + + err = bpf_iter_bpf_hash_map__load(skel); + if (CHECK(!skel, "bpf_iter_bpf_hash_map__load", + "skeleton load failed\n")) + goto out; + + /* iterator with hashmap2 and hashmap3 should fail */ + opts.map_fd = bpf_map__fd(skel->maps.hashmap2); + link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts); + if (CHECK(!IS_ERR(link), "attach_iter", + "attach_iter for hashmap2 unexpected succeeded\n")) + goto out; + + opts.map_fd = bpf_map__fd(skel->maps.hashmap3); + link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts); + if (CHECK(!IS_ERR(link), "attach_iter", + "attach_iter for hashmap3 unexpected succeeded\n")) + goto out; + + /* hashmap1 should be good, update map values here */ + map_fd = bpf_map__fd(skel->maps.hashmap1); + for (i = 0; i < bpf_map__max_entries(skel->maps.hashmap1); i++) { + key.a = i + 1; + key.b = i + 2; + key.c = i + 3; + val = i + 4; + expected_key_a += key.a; + expected_key_b += key.b; + expected_key_c += key.c; + expected_val += val; + + err = bpf_map_update_elem(map_fd, &key, &val, BPF_ANY); + if (CHECK(err, "map_update", "map_update failed\n")) + goto out; + } + + opts.map_fd = map_fd; + link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts); + if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n")) + goto out; + + iter_fd = bpf_iter_create(bpf_link__fd(link)); + if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n")) + goto free_link; + + /* do some tests */ + while ((len = read(iter_fd, buf, sizeof(buf))) > 0) + ; + if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno))) + goto close_iter; + + /* test results */ + if (CHECK(skel->bss->key_sum_a != expected_key_a, + "key_sum_a", "got %u expected %u\n", + skel->bss->key_sum_a, expected_key_a)) + goto close_iter; + if (CHECK(skel->bss->key_sum_b != expected_key_b, + "key_sum_b", "got %u expected %u\n", + skel->bss->key_sum_b, expected_key_b)) + goto close_iter; + if (CHECK(skel->bss->val_sum != expected_val, + "val_sum", "got %llu expected %llu\n", + skel->bss->val_sum, expected_val)) + goto close_iter; + +close_iter: + close(iter_fd); +free_link: + bpf_link__destroy(link); +out: + bpf_iter_bpf_hash_map__destroy(skel); +} + +static void test_bpf_percpu_hash_map(void) +{ + __u32 expected_key_a = 0, expected_key_b = 0, expected_key_c = 0; + DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts); + struct bpf_iter_bpf_percpu_hash_map *skel; + int err, i, j, len, map_fd, iter_fd; + __u32 expected_val = 0; + struct bpf_link *link; + struct key_t { + int a; + int b; + int c; + } key; + char buf[64]; + void *val; + + val = malloc(8 * bpf_num_possible_cpus()); + + skel = bpf_iter_bpf_percpu_hash_map__open(); + if (CHECK(!skel, "bpf_iter_bpf_percpu_hash_map__open", + "skeleton open failed\n")) + return; + + skel->rodata->num_cpus = bpf_num_possible_cpus(); + + err = bpf_iter_bpf_percpu_hash_map__load(skel); + if (CHECK(!skel, "bpf_iter_bpf_percpu_hash_map__load", + "skeleton load failed\n")) + goto out; + + /* update map values here */ + map_fd = bpf_map__fd(skel->maps.hashmap1); + for (i = 0; i < bpf_map__max_entries(skel->maps.hashmap1); i++) { + key.a = i + 1; + key.b = i + 2; + key.c = i + 3; + expected_key_a += key.a; + expected_key_b += key.b; + expected_key_c += key.c; + + for (j = 0; j < bpf_num_possible_cpus(); j++) { + *(__u32 *)(val + j * 8) = i + j; + expected_val += i + j; + } + + err = bpf_map_update_elem(map_fd, &key, val, BPF_ANY); + if (CHECK(err, "map_update", "map_update failed\n")) + goto out; + } + + opts.map_fd = map_fd; + link = bpf_program__attach_iter(skel->progs.dump_bpf_percpu_hash_map, &opts); + if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n")) + goto out; + + iter_fd = bpf_iter_create(bpf_link__fd(link)); + if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n")) + goto free_link; + + /* do some tests */ + while ((len = read(iter_fd, buf, sizeof(buf))) > 0) + ; + if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno))) + goto close_iter; + + /* test results */ + if (CHECK(skel->bss->key_sum_a != expected_key_a, + "key_sum_a", "got %u expected %u\n", + skel->bss->key_sum_a, expected_key_a)) + goto close_iter; + if (CHECK(skel->bss->key_sum_b != expected_key_b, + "key_sum_b", "got %u expected %u\n", + skel->bss->key_sum_b, expected_key_b)) + goto close_iter; + if (CHECK(skel->bss->val_sum != expected_val, + "val_sum", "got %u expected %u\n", + skel->bss->val_sum, expected_val)) + goto close_iter; + +close_iter: + close(iter_fd); +free_link: + bpf_link__destroy(link); +out: + bpf_iter_bpf_percpu_hash_map__destroy(skel); +} + void test_bpf_iter(void) { if (test__start_subtest("btf_id_or_null")) @@ -491,4 +674,8 @@ void test_bpf_iter(void) test_overflow(true, false); if (test__start_subtest("prog-ret-1")) test_overflow(false, true); + if (test__start_subtest("bpf_hash_map")) + test_bpf_hash_map(); + if (test__start_subtest("bpf_percpu_hash_map")) + test_bpf_percpu_hash_map(); } diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c new file mode 100644 index 000000000000..07ddbfdbcab7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include +#include + +char _license[] SEC("license") = "GPL"; + +struct key_t { + int a; + int b; + int c; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 3); + __type(key, struct key_t); + __type(value, __u64); +} hashmap1 SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 3); + __type(key, __u64); + __type(value, __u64); +} hashmap2 SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 3); + __type(key, struct key_t); + __type(value, __u32); +} hashmap3 SEC(".maps"); + +/* will set before prog run */ +bool in_test_mode = 0; + +/* will collect results during prog run */ +__u32 key_sum_a = 0, key_sum_b = 0, key_sum_c = 0; +__u64 val_sum = 0; + +SEC("iter/bpf_map_elem") +int dump_bpf_hash_map(struct bpf_iter__bpf_map_elem *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + __u32 seq_num = ctx->meta->seq_num; + struct bpf_map *map = ctx->map; + struct key_t *key = ctx->key; + __u64 *val = ctx->value; + + if (in_test_mode) { + /* test mode is used by selftests to + * test functionality of bpf_hash_map iter. + * + * the above hashmap1 will have correct size + * and will be accepted, hashmap2 and hashmap3 + * should be rejected due to smaller key/value + * size. + */ + if (key == (void *)0 || val == (void *)0) + return 0; + + key_sum_a += key->a; + key_sum_b += key->b; + key_sum_c += key->c; + val_sum += *val; + return 0; + } + + /* non-test mode, the map is prepared with the + * below bpftool command sequence: + * bpftool map create /sys/fs/bpf/m1 type hash \ + * key 12 value 8 entries 3 name map1 + * bpftool map update id 77 key 0 0 0 1 0 0 0 0 0 0 0 1 \ + * value 0 0 0 1 0 0 0 1 + * bpftool map update id 77 key 0 0 0 1 0 0 0 0 0 0 0 2 \ + * value 0 0 0 1 0 0 0 2 + * The bpftool iter command line: + * bpftool iter pin ./bpf_iter_bpf_hash_map.o /sys/fs/bpf/p1 \ + * map id 77 + * The below output will be: + * map dump starts + * 77: (1000000 0 2000000) (200000001000000) + * 77: (1000000 0 1000000) (100000001000000) + * map dump ends + */ + if (seq_num == 0) + BPF_SEQ_PRINTF(seq, "map dump starts\n"); + + if (key == (void *)0 || val == (void *)0) { + BPF_SEQ_PRINTF(seq, "map dump ends\n"); + return 0; + } + + BPF_SEQ_PRINTF(seq, "%d: (%x %d %x) (%llx)\n", map->id, + key->a, key->b, key->c, *val); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_hash_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_hash_map.c new file mode 100644 index 000000000000..feaaa2b89c57 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_hash_map.c @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include +#include + +char _license[] SEC("license") = "GPL"; + +struct key_t { + int a; + int b; + int c; +}; + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __uint(max_entries, 3); + __type(key, struct key_t); + __type(value, __u32); +} hashmap1 SEC(".maps"); + +/* will set before prog run */ +volatile const __u32 num_cpus = 0; + +/* will collect results during prog run */ +__u32 key_sum_a = 0, key_sum_b = 0, key_sum_c = 0; +__u32 val_sum = 0; + +SEC("iter/bpf_map_elem") +int dump_bpf_percpu_hash_map(struct bpf_iter__bpf_map_elem *ctx) +{ + struct key_t *key = ctx->key; + void *pptr = ctx->value; + __u32 step; + int i; + + if (key == (void *)0 || pptr == (void *)0) + return 0; + + key_sum_a += key->a; + key_sum_b += key->b; + key_sum_c += key->c; + + step = 8; + for (i = 0; i < num_cpus; i++) { + val_sum += *(__u32 *)pptr; + pptr += step; + } + return 0; +} -- cgit v1.2.3 From 60dd49ea65390986a665c462da704927e861e67e Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 23 Jul 2020 11:41:21 -0700 Subject: selftests/bpf: Add test for bpf array map iterators Two subtests are added. $ ./test_progs -n 4 ... #4/20 bpf_array_map:OK #4/21 bpf_percpu_array_map:OK ... The bpf_array_map subtest also tested bpf program changing array element values and send key/value to user space through bpf_seq_write() interface. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200723184121.591367-1-yhs@fb.com --- tools/testing/selftests/bpf/prog_tests/bpf_iter.c | 161 +++++++++++++++++++++ .../selftests/bpf/progs/bpf_iter_bpf_array_map.c | 40 +++++ .../bpf/progs/bpf_iter_bpf_percpu_array_map.c | 46 ++++++ 3 files changed, 247 insertions(+) create mode 100644 tools/testing/selftests/bpf/progs/bpf_iter_bpf_array_map.c create mode 100644 tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_array_map.c (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index 72790b600c62..4a02b2222a6d 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -17,6 +17,8 @@ #include "bpf_iter_test_kern4.skel.h" #include "bpf_iter_bpf_hash_map.skel.h" #include "bpf_iter_bpf_percpu_hash_map.skel.h" +#include "bpf_iter_bpf_array_map.skel.h" +#include "bpf_iter_bpf_percpu_array_map.skel.h" static int duration; @@ -638,6 +640,161 @@ out: bpf_iter_bpf_percpu_hash_map__destroy(skel); } +static void test_bpf_array_map(void) +{ + __u64 val, expected_val = 0, res_first_val, first_val = 0; + DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts); + __u32 expected_key = 0, res_first_key; + struct bpf_iter_bpf_array_map *skel; + int err, i, map_fd, iter_fd; + struct bpf_link *link; + char buf[64] = {}; + int len, start; + + skel = bpf_iter_bpf_array_map__open_and_load(); + if (CHECK(!skel, "bpf_iter_bpf_array_map__open_and_load", + "skeleton open_and_load failed\n")) + return; + + map_fd = bpf_map__fd(skel->maps.arraymap1); + for (i = 0; i < bpf_map__max_entries(skel->maps.arraymap1); i++) { + val = i + 4; + expected_key += i; + expected_val += val; + + if (i == 0) + first_val = val; + + err = bpf_map_update_elem(map_fd, &i, &val, BPF_ANY); + if (CHECK(err, "map_update", "map_update failed\n")) + goto out; + } + + opts.map_fd = map_fd; + link = bpf_program__attach_iter(skel->progs.dump_bpf_array_map, &opts); + if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n")) + goto out; + + iter_fd = bpf_iter_create(bpf_link__fd(link)); + if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n")) + goto free_link; + + /* do some tests */ + start = 0; + while ((len = read(iter_fd, buf + start, sizeof(buf) - start)) > 0) + start += len; + if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno))) + goto close_iter; + + /* test results */ + res_first_key = *(__u32 *)buf; + res_first_val = *(__u64 *)(buf + sizeof(__u32)); + if (CHECK(res_first_key != 0 || res_first_val != first_val, + "bpf_seq_write", + "seq_write failure: first key %u vs expected 0, " + " first value %llu vs expected %llu\n", + res_first_key, res_first_val, first_val)) + goto close_iter; + + if (CHECK(skel->bss->key_sum != expected_key, + "key_sum", "got %u expected %u\n", + skel->bss->key_sum, expected_key)) + goto close_iter; + if (CHECK(skel->bss->val_sum != expected_val, + "val_sum", "got %llu expected %llu\n", + skel->bss->val_sum, expected_val)) + goto close_iter; + + for (i = 0; i < bpf_map__max_entries(skel->maps.arraymap1); i++) { + err = bpf_map_lookup_elem(map_fd, &i, &val); + if (CHECK(err, "map_lookup", "map_lookup failed\n")) + goto out; + if (CHECK(i != val, "invalid_val", + "got value %llu expected %u\n", val, i)) + goto out; + } + +close_iter: + close(iter_fd); +free_link: + bpf_link__destroy(link); +out: + bpf_iter_bpf_array_map__destroy(skel); +} + +static void test_bpf_percpu_array_map(void) +{ + DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts); + struct bpf_iter_bpf_percpu_array_map *skel; + __u32 expected_key = 0, expected_val = 0; + int err, i, j, map_fd, iter_fd; + struct bpf_link *link; + char buf[64]; + void *val; + int len; + + val = malloc(8 * bpf_num_possible_cpus()); + + skel = bpf_iter_bpf_percpu_array_map__open(); + if (CHECK(!skel, "bpf_iter_bpf_percpu_array_map__open", + "skeleton open failed\n")) + return; + + skel->rodata->num_cpus = bpf_num_possible_cpus(); + + err = bpf_iter_bpf_percpu_array_map__load(skel); + if (CHECK(!skel, "bpf_iter_bpf_percpu_array_map__load", + "skeleton load failed\n")) + goto out; + + /* update map values here */ + map_fd = bpf_map__fd(skel->maps.arraymap1); + for (i = 0; i < bpf_map__max_entries(skel->maps.arraymap1); i++) { + expected_key += i; + + for (j = 0; j < bpf_num_possible_cpus(); j++) { + *(__u32 *)(val + j * 8) = i + j; + expected_val += i + j; + } + + err = bpf_map_update_elem(map_fd, &i, val, BPF_ANY); + if (CHECK(err, "map_update", "map_update failed\n")) + goto out; + } + + opts.map_fd = map_fd; + link = bpf_program__attach_iter(skel->progs.dump_bpf_percpu_array_map, &opts); + if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n")) + goto out; + + iter_fd = bpf_iter_create(bpf_link__fd(link)); + if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n")) + goto free_link; + + /* do some tests */ + while ((len = read(iter_fd, buf, sizeof(buf))) > 0) + ; + if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno))) + goto close_iter; + + /* test results */ + if (CHECK(skel->bss->key_sum != expected_key, + "key_sum", "got %u expected %u\n", + skel->bss->key_sum, expected_key)) + goto close_iter; + if (CHECK(skel->bss->val_sum != expected_val, + "val_sum", "got %u expected %u\n", + skel->bss->val_sum, expected_val)) + goto close_iter; + +close_iter: + close(iter_fd); +free_link: + bpf_link__destroy(link); +out: + bpf_iter_bpf_percpu_array_map__destroy(skel); +} + void test_bpf_iter(void) { if (test__start_subtest("btf_id_or_null")) @@ -678,4 +835,8 @@ void test_bpf_iter(void) test_bpf_hash_map(); if (test__start_subtest("bpf_percpu_hash_map")) test_bpf_percpu_hash_map(); + if (test__start_subtest("bpf_array_map")) + test_bpf_array_map(); + if (test__start_subtest("bpf_percpu_array_map")) + test_bpf_percpu_array_map(); } diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_array_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_array_map.c new file mode 100644 index 000000000000..6286023fd62b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_array_map.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include +#include + +char _license[] SEC("license") = "GPL"; + +struct key_t { + int a; + int b; + int c; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 3); + __type(key, __u32); + __type(value, __u64); +} arraymap1 SEC(".maps"); + +__u32 key_sum = 0; +__u64 val_sum = 0; + +SEC("iter/bpf_map_elem") +int dump_bpf_array_map(struct bpf_iter__bpf_map_elem *ctx) +{ + __u32 *key = ctx->key; + __u64 *val = ctx->value; + + if (key == (void *)0 || val == (void *)0) + return 0; + + bpf_seq_write(ctx->meta->seq, key, sizeof(__u32)); + bpf_seq_write(ctx->meta->seq, val, sizeof(__u64)); + key_sum += *key; + val_sum += *val; + *val = *key; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_array_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_array_map.c new file mode 100644 index 000000000000..85fa710fad90 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_array_map.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include +#include + +char _license[] SEC("license") = "GPL"; + +struct key_t { + int a; + int b; + int c; +}; + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, 3); + __type(key, __u32); + __type(value, __u32); +} arraymap1 SEC(".maps"); + +/* will set before prog run */ +volatile const __u32 num_cpus = 0; + +__u32 key_sum = 0, val_sum = 0; + +SEC("iter/bpf_map_elem") +int dump_bpf_percpu_array_map(struct bpf_iter__bpf_map_elem *ctx) +{ + __u32 *key = ctx->key; + void *pptr = ctx->value; + __u32 step; + int i; + + if (key == (void *)0 || pptr == (void *)0) + return 0; + + key_sum += *key; + + step = 8; + for (i = 0; i < num_cpus; i++) { + val_sum += *(__u32 *)pptr; + pptr += step; + } + return 0; +} -- cgit v1.2.3 From 3b1c420bd882115eb7a3d2335cc00d7b9974eb0b Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 23 Jul 2020 11:41:22 -0700 Subject: selftests/bpf: Add a test for bpf sk_storage_map iterator Added one test for bpf sk_storage_map_iterator. $ ./test_progs -n 4 ... #4/22 bpf_sk_storage_map:OK ... Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200723184122.591591-1-yhs@fb.com --- tools/testing/selftests/bpf/prog_tests/bpf_iter.c | 72 ++++++++++++++++++++++ .../bpf/progs/bpf_iter_bpf_sk_storage_map.c | 34 ++++++++++ 2 files changed, 106 insertions(+) create mode 100644 tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_map.c (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index 4a02b2222a6d..ffbbeb9fa268 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -19,6 +19,7 @@ #include "bpf_iter_bpf_percpu_hash_map.skel.h" #include "bpf_iter_bpf_array_map.skel.h" #include "bpf_iter_bpf_percpu_array_map.skel.h" +#include "bpf_iter_bpf_sk_storage_map.skel.h" static int duration; @@ -795,6 +796,75 @@ out: bpf_iter_bpf_percpu_array_map__destroy(skel); } +static void test_bpf_sk_storage_map(void) +{ + DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts); + int err, i, len, map_fd, iter_fd, num_sockets; + struct bpf_iter_bpf_sk_storage_map *skel; + int sock_fd[3] = {-1, -1, -1}; + __u32 val, expected_val = 0; + struct bpf_link *link; + char buf[64]; + + skel = bpf_iter_bpf_sk_storage_map__open_and_load(); + if (CHECK(!skel, "bpf_iter_bpf_sk_storage_map__open_and_load", + "skeleton open_and_load failed\n")) + return; + + map_fd = bpf_map__fd(skel->maps.sk_stg_map); + num_sockets = ARRAY_SIZE(sock_fd); + for (i = 0; i < num_sockets; i++) { + sock_fd[i] = socket(AF_INET6, SOCK_STREAM, 0); + if (CHECK(sock_fd[i] < 0, "socket", "errno: %d\n", errno)) + goto out; + + val = i + 1; + expected_val += val; + + err = bpf_map_update_elem(map_fd, &sock_fd[i], &val, + BPF_NOEXIST); + if (CHECK(err, "map_update", "map_update failed\n")) + goto out; + } + + opts.map_fd = map_fd; + link = bpf_program__attach_iter(skel->progs.dump_bpf_sk_storage_map, &opts); + if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n")) + goto out; + + iter_fd = bpf_iter_create(bpf_link__fd(link)); + if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n")) + goto free_link; + + /* do some tests */ + while ((len = read(iter_fd, buf, sizeof(buf))) > 0) + ; + if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno))) + goto close_iter; + + /* test results */ + if (CHECK(skel->bss->ipv6_sk_count != num_sockets, + "ipv6_sk_count", "got %u expected %u\n", + skel->bss->ipv6_sk_count, num_sockets)) + goto close_iter; + + if (CHECK(skel->bss->val_sum != expected_val, + "val_sum", "got %u expected %u\n", + skel->bss->val_sum, expected_val)) + goto close_iter; + +close_iter: + close(iter_fd); +free_link: + bpf_link__destroy(link); +out: + for (i = 0; i < num_sockets; i++) { + if (sock_fd[i] >= 0) + close(sock_fd[i]); + } + bpf_iter_bpf_sk_storage_map__destroy(skel); +} + void test_bpf_iter(void) { if (test__start_subtest("btf_id_or_null")) @@ -839,4 +909,6 @@ void test_bpf_iter(void) test_bpf_array_map(); if (test__start_subtest("bpf_percpu_array_map")) test_bpf_percpu_array_map(); + if (test__start_subtest("bpf_sk_storage_map")) + test_bpf_sk_storage_map(); } diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_map.c new file mode 100644 index 000000000000..6b70ccaba301 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_map.c @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include "bpf_tracing_net.h" +#include +#include + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, int); +} sk_stg_map SEC(".maps"); + +__u32 val_sum = 0; +__u32 ipv6_sk_count = 0; + +SEC("iter/bpf_sk_storage_map") +int dump_bpf_sk_storage_map(struct bpf_iter__bpf_sk_storage_map *ctx) +{ + struct sock *sk = ctx->sk; + __u32 *val = ctx->value; + + if (sk == (void *)0 || val == (void *)0) + return 0; + + if (sk->sk_family == AF_INET6) + ipv6_sk_count++; + + val_sum += *val; + return 0; +} -- cgit v1.2.3 From 9efcc4ad7a15ea50550c53fbf62457c309216051 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 23 Jul 2020 11:41:24 -0700 Subject: selftests/bpf: Add a test for out of bound rdonly buf access If the bpf program contains out of bound access w.r.t. a particular map key/value size, the verification will be still okay, e.g., it will be accepted by verifier. But it will be rejected during link_create time. A test is added here to ensure link_create failure did happen if out of bound access happened. $ ./test_progs -n 4 ... #4/23 rdonly-buf-out-of-bound:OK ... Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200723184124.591700-1-yhs@fb.com --- tools/testing/selftests/bpf/prog_tests/bpf_iter.c | 22 ++++++++++++++ .../selftests/bpf/progs/bpf_iter_test_kern5.c | 35 ++++++++++++++++++++++ 2 files changed, 57 insertions(+) create mode 100644 tools/testing/selftests/bpf/progs/bpf_iter_test_kern5.c (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index ffbbeb9fa268..d95de80b1851 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -20,6 +20,7 @@ #include "bpf_iter_bpf_array_map.skel.h" #include "bpf_iter_bpf_percpu_array_map.skel.h" #include "bpf_iter_bpf_sk_storage_map.skel.h" +#include "bpf_iter_test_kern5.skel.h" static int duration; @@ -865,6 +866,25 @@ out: bpf_iter_bpf_sk_storage_map__destroy(skel); } +static void test_rdonly_buf_out_of_bound(void) +{ + DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts); + struct bpf_iter_test_kern5 *skel; + struct bpf_link *link; + + skel = bpf_iter_test_kern5__open_and_load(); + if (CHECK(!skel, "bpf_iter_test_kern5__open_and_load", + "skeleton open_and_load failed\n")) + return; + + opts.map_fd = bpf_map__fd(skel->maps.hashmap1); + link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts); + if (CHECK(!IS_ERR(link), "attach_iter", "unexpected success\n")) + bpf_link__destroy(link); + + bpf_iter_test_kern5__destroy(skel); +} + void test_bpf_iter(void) { if (test__start_subtest("btf_id_or_null")) @@ -911,4 +931,6 @@ void test_bpf_iter(void) test_bpf_percpu_array_map(); if (test__start_subtest("bpf_sk_storage_map")) test_bpf_sk_storage_map(); + if (test__start_subtest("rdonly-buf-out-of-bound")) + test_rdonly_buf_out_of_bound(); } diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern5.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern5.c new file mode 100644 index 000000000000..e3a7575e81d2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern5.c @@ -0,0 +1,35 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include +#include + +char _license[] SEC("license") = "GPL"; + +struct key_t { + int a; + int b; + int c; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 3); + __type(key, struct key_t); + __type(value, __u64); +} hashmap1 SEC(".maps"); + +__u32 key_sum = 0; + +SEC("iter/bpf_map_elem") +int dump_bpf_hash_map(struct bpf_iter__bpf_map_elem *ctx) +{ + void *key = ctx->key; + + if (key == (void *)0) + return 0; + + /* out of bound access w.r.t. hashmap1 */ + key_sum += *(__u32 *)(key + sizeof(struct key_t)); + return 0; +} -- cgit v1.2.3 From 1da4864c2b20f81afbb18b2a0b914d0c776331fc Mon Sep 17 00:00:00 2001 From: Song Liu Date: Thu, 23 Jul 2020 11:06:47 -0700 Subject: selftests/bpf: Add callchain_stackid This tests new helper function bpf_get_stackid_pe and bpf_get_stack_pe. These two helpers have different implementation for perf_event with PEB entries. Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200723180648.1429892-5-songliubraving@fb.com --- .../selftests/bpf/prog_tests/perf_event_stackmap.c | 116 +++++++++++++++++++++ .../selftests/bpf/progs/perf_event_stackmap.c | 59 +++++++++++ 2 files changed, 175 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/perf_event_stackmap.c create mode 100644 tools/testing/selftests/bpf/progs/perf_event_stackmap.c (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/perf_event_stackmap.c b/tools/testing/selftests/bpf/prog_tests/perf_event_stackmap.c new file mode 100644 index 000000000000..72c3690844fb --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/perf_event_stackmap.c @@ -0,0 +1,116 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook +#define _GNU_SOURCE +#include +#include +#include +#include "perf_event_stackmap.skel.h" + +#ifndef noinline +#define noinline __attribute__((noinline)) +#endif + +noinline int func_1(void) +{ + static int val = 1; + + val += 1; + + usleep(100); + return val; +} + +noinline int func_2(void) +{ + return func_1(); +} + +noinline int func_3(void) +{ + return func_2(); +} + +noinline int func_4(void) +{ + return func_3(); +} + +noinline int func_5(void) +{ + return func_4(); +} + +noinline int func_6(void) +{ + int i, val = 1; + + for (i = 0; i < 100; i++) + val += func_5(); + + return val; +} + +void test_perf_event_stackmap(void) +{ + struct perf_event_attr attr = { + /* .type = PERF_TYPE_SOFTWARE, */ + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + .precise_ip = 2, + .sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_BRANCH_STACK | + PERF_SAMPLE_CALLCHAIN, + .branch_sample_type = PERF_SAMPLE_BRANCH_USER | + PERF_SAMPLE_BRANCH_NO_FLAGS | + PERF_SAMPLE_BRANCH_NO_CYCLES | + PERF_SAMPLE_BRANCH_CALL_STACK, + .sample_period = 5000, + .size = sizeof(struct perf_event_attr), + }; + struct perf_event_stackmap *skel; + __u32 duration = 0; + cpu_set_t cpu_set; + int pmu_fd, err; + + skel = perf_event_stackmap__open(); + + if (CHECK(!skel, "skel_open", "skeleton open failed\n")) + return; + + err = perf_event_stackmap__load(skel); + if (CHECK(err, "skel_load", "skeleton load failed: %d\n", err)) + goto cleanup; + + CPU_ZERO(&cpu_set); + CPU_SET(0, &cpu_set); + err = pthread_setaffinity_np(pthread_self(), sizeof(cpu_set), &cpu_set); + if (CHECK(err, "set_affinity", "err %d, errno %d\n", err, errno)) + goto cleanup; + + pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */, + 0 /* cpu 0 */, -1 /* group id */, + 0 /* flags */); + if (pmu_fd < 0) { + printf("%s:SKIP:cpu doesn't support the event\n", __func__); + test__skip(); + goto cleanup; + } + + skel->links.oncpu = bpf_program__attach_perf_event(skel->progs.oncpu, + pmu_fd); + if (CHECK(IS_ERR(skel->links.oncpu), "attach_perf_event", + "err %ld\n", PTR_ERR(skel->links.oncpu))) { + close(pmu_fd); + goto cleanup; + } + + /* create kernel and user stack traces for testing */ + func_6(); + + CHECK(skel->data->stackid_kernel != 2, "get_stackid_kernel", "failed\n"); + CHECK(skel->data->stackid_user != 2, "get_stackid_user", "failed\n"); + CHECK(skel->data->stack_kernel != 2, "get_stack_kernel", "failed\n"); + CHECK(skel->data->stack_user != 2, "get_stack_user", "failed\n"); + +cleanup: + perf_event_stackmap__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/progs/perf_event_stackmap.c b/tools/testing/selftests/bpf/progs/perf_event_stackmap.c new file mode 100644 index 000000000000..25467d13c356 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/perf_event_stackmap.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook +#include "vmlinux.h" +#include + +#ifndef PERF_MAX_STACK_DEPTH +#define PERF_MAX_STACK_DEPTH 127 +#endif + +typedef __u64 stack_trace_t[PERF_MAX_STACK_DEPTH]; +struct { + __uint(type, BPF_MAP_TYPE_STACK_TRACE); + __uint(max_entries, 16384); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(stack_trace_t)); +} stackmap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, stack_trace_t); +} stackdata_map SEC(".maps"); + +long stackid_kernel = 1; +long stackid_user = 1; +long stack_kernel = 1; +long stack_user = 1; + +SEC("perf_event") +int oncpu(void *ctx) +{ + stack_trace_t *trace; + __u32 key = 0; + long val; + + val = bpf_get_stackid(ctx, &stackmap, 0); + if (val > 0) + stackid_kernel = 2; + val = bpf_get_stackid(ctx, &stackmap, BPF_F_USER_STACK); + if (val > 0) + stackid_user = 2; + + trace = bpf_map_lookup_elem(&stackdata_map, &key); + if (!trace) + return 0; + + val = bpf_get_stack(ctx, trace, sizeof(stack_trace_t), 0); + if (val > 0) + stack_kernel = 2; + + val = bpf_get_stack(ctx, trace, sizeof(stack_trace_t), BPF_F_USER_STACK); + if (val > 0) + stack_user = 2; + + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; -- cgit v1.2.3 From 346938e9380cc0b2ad8e2566389cdc570386fe22 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Thu, 23 Jul 2020 11:06:48 -0700 Subject: selftests/bpf: Add get_stackid_cannot_attach This test confirms that BPF program that calls bpf_get_stackid() cannot attach to perf_event with precise_ip > 0 but not PERF_SAMPLE_CALLCHAIN; and cannot attach if the perf_event has exclude_callchain_kernel. Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200723180648.1429892-6-songliubraving@fb.com --- .../bpf/prog_tests/get_stackid_cannot_attach.c | 91 ++++++++++++++++++++++ 1 file changed, 91 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c b/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c new file mode 100644 index 000000000000..d884b2ed5bc5 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook +#include +#include "test_stacktrace_build_id.skel.h" + +void test_get_stackid_cannot_attach(void) +{ + struct perf_event_attr attr = { + /* .type = PERF_TYPE_SOFTWARE, */ + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + .precise_ip = 1, + .sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_BRANCH_STACK, + .branch_sample_type = PERF_SAMPLE_BRANCH_USER | + PERF_SAMPLE_BRANCH_NO_FLAGS | + PERF_SAMPLE_BRANCH_NO_CYCLES | + PERF_SAMPLE_BRANCH_CALL_STACK, + .sample_period = 5000, + .size = sizeof(struct perf_event_attr), + }; + struct test_stacktrace_build_id *skel; + __u32 duration = 0; + int pmu_fd, err; + + skel = test_stacktrace_build_id__open(); + if (CHECK(!skel, "skel_open", "skeleton open failed\n")) + return; + + /* override program type */ + bpf_program__set_perf_event(skel->progs.oncpu); + + err = test_stacktrace_build_id__load(skel); + if (CHECK(err, "skel_load", "skeleton load failed: %d\n", err)) + goto cleanup; + + pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */, + 0 /* cpu 0 */, -1 /* group id */, + 0 /* flags */); + if (pmu_fd < 0 && (errno == ENOENT || errno == EOPNOTSUPP)) { + printf("%s:SKIP:cannot open PERF_COUNT_HW_CPU_CYCLES with precise_ip > 0\n", + __func__); + test__skip(); + goto cleanup; + } + if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n", + pmu_fd, errno)) + goto cleanup; + + skel->links.oncpu = bpf_program__attach_perf_event(skel->progs.oncpu, + pmu_fd); + CHECK(!IS_ERR(skel->links.oncpu), "attach_perf_event_no_callchain", + "should have failed\n"); + close(pmu_fd); + + /* add PERF_SAMPLE_CALLCHAIN, attach should succeed */ + attr.sample_type |= PERF_SAMPLE_CALLCHAIN; + + pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */, + 0 /* cpu 0 */, -1 /* group id */, + 0 /* flags */); + + if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n", + pmu_fd, errno)) + goto cleanup; + + skel->links.oncpu = bpf_program__attach_perf_event(skel->progs.oncpu, + pmu_fd); + CHECK(IS_ERR(skel->links.oncpu), "attach_perf_event_callchain", + "err: %ld\n", PTR_ERR(skel->links.oncpu)); + close(pmu_fd); + + /* add exclude_callchain_kernel, attach should fail */ + attr.exclude_callchain_kernel = 1; + + pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */, + 0 /* cpu 0 */, -1 /* group id */, + 0 /* flags */); + + if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n", + pmu_fd, errno)) + goto cleanup; + + skel->links.oncpu = bpf_program__attach_perf_event(skel->progs.oncpu, + pmu_fd); + CHECK(!IS_ERR(skel->links.oncpu), "attach_perf_event_exclude_callchain_kernel", + "should have failed\n"); + close(pmu_fd); + +cleanup: + test_stacktrace_build_id__destroy(skel); +} -- cgit v1.2.3 From d4a89c1eb81431479664029bcdec593dbf23385f Mon Sep 17 00:00:00 2001 From: YiFei Zhu Date: Thu, 23 Jul 2020 23:47:41 -0500 Subject: selftests/bpf: Add test for CGROUP_STORAGE map on multiple attaches This test creates a parent cgroup, and a child of that cgroup. It attaches a cgroup_skb/egress program that simply counts packets, to a global variable (ARRAY map), and to a CGROUP_STORAGE map. The program is first attached to the parent cgroup only, then to parent and child. The test cases sends a message within the child cgroup, and because the program is inherited across parent / child cgroups, it will trigger the egress program for both the parent and child, if they exist. The program, when looking up a CGROUP_STORAGE map, uses the cgroup and attach type of the attachment parameters; therefore, both attaches uses different cgroup storages. We assert that all packet counts returns what we expects. Signed-off-by: YiFei Zhu Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/5a20206afa4606144691c7caa0d1b997cd60dec0.1595565795.git.zhuyifei@google.com --- .../selftests/bpf/prog_tests/cg_storage_multi.c | 161 +++++++++++++++++++++ .../bpf/progs/cg_storage_multi_egress_only.c | 30 ++++ 2 files changed, 191 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c create mode 100644 tools/testing/selftests/bpf/progs/cg_storage_multi_egress_only.c (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c b/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c new file mode 100644 index 000000000000..e90e0547d759 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c @@ -0,0 +1,161 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright 2020 Google LLC. + */ + +#include +#include +#include + +#include "cg_storage_multi_egress_only.skel.h" + +#define PARENT_CGROUP "/cgroup_storage" +#define CHILD_CGROUP "/cgroup_storage/child" + +static int duration; + +static bool assert_storage(struct bpf_map *map, const char *cgroup_path, + __u32 expected) +{ + struct bpf_cgroup_storage_key key = {0}; + __u32 value; + int map_fd; + + map_fd = bpf_map__fd(map); + + key.cgroup_inode_id = get_cgroup_id(cgroup_path); + key.attach_type = BPF_CGROUP_INET_EGRESS; + if (CHECK(bpf_map_lookup_elem(map_fd, &key, &value) < 0, + "map-lookup", "errno %d", errno)) + return true; + if (CHECK(value != expected, + "assert-storage", "got %u expected %u", value, expected)) + return true; + + return false; +} + +static bool assert_storage_noexist(struct bpf_map *map, const char *cgroup_path) +{ + struct bpf_cgroup_storage_key key = {0}; + __u32 value; + int map_fd; + + map_fd = bpf_map__fd(map); + + key.cgroup_inode_id = get_cgroup_id(cgroup_path); + key.attach_type = BPF_CGROUP_INET_EGRESS; + if (CHECK(bpf_map_lookup_elem(map_fd, &key, &value) == 0, + "map-lookup", "succeeded, expected ENOENT")) + return true; + if (CHECK(errno != ENOENT, + "map-lookup", "errno %d, expected ENOENT", errno)) + return true; + + return false; +} + +static bool connect_send(const char *cgroup_path) +{ + bool res = true; + int server_fd = -1, client_fd = -1; + + if (join_cgroup(cgroup_path)) + goto out_clean; + + server_fd = start_server(AF_INET, SOCK_DGRAM, NULL, 0, 0); + if (server_fd < 0) + goto out_clean; + + client_fd = connect_to_fd(server_fd, 0); + if (client_fd < 0) + goto out_clean; + + if (send(client_fd, "message", strlen("message"), 0) < 0) + goto out_clean; + + res = false; + +out_clean: + close(client_fd); + close(server_fd); + return res; +} + +static void test_egress_only(int parent_cgroup_fd, int child_cgroup_fd) +{ + struct cg_storage_multi_egress_only *obj; + struct bpf_link *parent_link = NULL, *child_link = NULL; + bool err; + + obj = cg_storage_multi_egress_only__open_and_load(); + if (CHECK(!obj, "skel-load", "errno %d", errno)) + return; + + /* Attach to parent cgroup, trigger packet from child. + * Assert that there is only one run and in that run the storage is + * parent cgroup's storage. + * Also assert that child cgroup's storage does not exist + */ + parent_link = bpf_program__attach_cgroup(obj->progs.egress, + parent_cgroup_fd); + if (CHECK(IS_ERR(parent_link), "parent-cg-attach", + "err %ld", PTR_ERR(parent_link))) + goto close_bpf_object; + err = connect_send(CHILD_CGROUP); + if (CHECK(err, "first-connect-send", "errno %d", errno)) + goto close_bpf_object; + if (CHECK(obj->bss->invocations != 1, + "first-invoke", "invocations=%d", obj->bss->invocations)) + goto close_bpf_object; + if (assert_storage(obj->maps.cgroup_storage, PARENT_CGROUP, 1)) + goto close_bpf_object; + if (assert_storage_noexist(obj->maps.cgroup_storage, CHILD_CGROUP)) + goto close_bpf_object; + + /* Attach to parent and child cgroup, trigger packet from child. + * Assert that there are two additional runs, one that run with parent + * cgroup's storage and one with child cgroup's storage. + */ + child_link = bpf_program__attach_cgroup(obj->progs.egress, + child_cgroup_fd); + if (CHECK(IS_ERR(child_link), "child-cg-attach", + "err %ld", PTR_ERR(child_link))) + goto close_bpf_object; + err = connect_send(CHILD_CGROUP); + if (CHECK(err, "second-connect-send", "errno %d", errno)) + goto close_bpf_object; + if (CHECK(obj->bss->invocations != 3, + "second-invoke", "invocations=%d", obj->bss->invocations)) + goto close_bpf_object; + if (assert_storage(obj->maps.cgroup_storage, PARENT_CGROUP, 2)) + goto close_bpf_object; + if (assert_storage(obj->maps.cgroup_storage, CHILD_CGROUP, 1)) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(parent_link); + bpf_link__destroy(child_link); + + cg_storage_multi_egress_only__destroy(obj); +} + +void test_cg_storage_multi(void) +{ + int parent_cgroup_fd = -1, child_cgroup_fd = -1; + + parent_cgroup_fd = test__join_cgroup(PARENT_CGROUP); + if (CHECK(parent_cgroup_fd < 0, "cg-create-parent", "errno %d", errno)) + goto close_cgroup_fd; + child_cgroup_fd = create_and_get_cgroup(CHILD_CGROUP); + if (CHECK(child_cgroup_fd < 0, "cg-create-child", "errno %d", errno)) + goto close_cgroup_fd; + + if (test__start_subtest("egress_only")) + test_egress_only(parent_cgroup_fd, child_cgroup_fd); + +close_cgroup_fd: + close(child_cgroup_fd); + close(parent_cgroup_fd); +} diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi_egress_only.c b/tools/testing/selftests/bpf/progs/cg_storage_multi_egress_only.c new file mode 100644 index 000000000000..ec0165d07105 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cg_storage_multi_egress_only.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright 2020 Google LLC. + */ + +#include +#include +#include +#include +#include + +struct { + __uint(type, BPF_MAP_TYPE_CGROUP_STORAGE); + __type(key, struct bpf_cgroup_storage_key); + __type(value, __u32); +} cgroup_storage SEC(".maps"); + +__u32 invocations = 0; + +SEC("cgroup_skb/egress") +int egress(struct __sk_buff *skb) +{ + __u32 *ptr_cg_storage = bpf_get_local_storage(&cgroup_storage, 0); + + __sync_fetch_and_add(ptr_cg_storage, 1); + __sync_fetch_and_add(&invocations, 1); + + return 1; +} -- cgit v1.2.3 From 9e5bd1f7633bc1c3c8b25496eedfeced6d2675ff Mon Sep 17 00:00:00 2001 From: YiFei Zhu Date: Thu, 23 Jul 2020 23:47:42 -0500 Subject: selftests/bpf: Test CGROUP_STORAGE map can't be used by multiple progs The current assumption is that the lifetime of a cgroup storage is tied to the program's attachment. The storage is created in cgroup_bpf_attach, and released upon cgroup_bpf_detach and cgroup_bpf_release. Because the current semantics is that each attachment gets a completely independent cgroup storage, and you can have multiple programs attached to the same (cgroup, attach type) pair, the key of the CGROUP_STORAGE map, looking up the map with this pair could yield multiple storages, and that is not permitted. Therefore, the kernel verifier checks that two programs cannot share the same CGROUP_STORAGE map, even if they have different expected attach types, considering that the actual attach type does not always have to be equal to the expected attach type. The test creates a CGROUP_STORAGE map and make it shared across two different programs, one cgroup_skb/egress and one /ingress. It asserts that the two programs cannot be both loaded, due to verifier failure from the above reason. Signed-off-by: YiFei Zhu Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/30a6b0da67ae6b0296c4d511bfb19c5f3d035916.1595565795.git.zhuyifei@google.com --- .../selftests/bpf/prog_tests/cg_storage_multi.c | 43 +++++++++++++++++---- .../testing/selftests/bpf/progs/cg_storage_multi.h | 13 +++++++ .../bpf/progs/cg_storage_multi_egress_ingress.c | 45 ++++++++++++++++++++++ .../bpf/progs/cg_storage_multi_egress_only.c | 9 +++-- 4 files changed, 99 insertions(+), 11 deletions(-) create mode 100644 tools/testing/selftests/bpf/progs/cg_storage_multi.h create mode 100644 tools/testing/selftests/bpf/progs/cg_storage_multi_egress_ingress.c (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c b/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c index e90e0547d759..1c7653423698 100644 --- a/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c @@ -8,7 +8,10 @@ #include #include +#include "progs/cg_storage_multi.h" + #include "cg_storage_multi_egress_only.skel.h" +#include "cg_storage_multi_egress_ingress.skel.h" #define PARENT_CGROUP "/cgroup_storage" #define CHILD_CGROUP "/cgroup_storage/child" @@ -16,10 +19,10 @@ static int duration; static bool assert_storage(struct bpf_map *map, const char *cgroup_path, - __u32 expected) + struct cgroup_value *expected) { struct bpf_cgroup_storage_key key = {0}; - __u32 value; + struct cgroup_value value; int map_fd; map_fd = bpf_map__fd(map); @@ -29,8 +32,8 @@ static bool assert_storage(struct bpf_map *map, const char *cgroup_path, if (CHECK(bpf_map_lookup_elem(map_fd, &key, &value) < 0, "map-lookup", "errno %d", errno)) return true; - if (CHECK(value != expected, - "assert-storage", "got %u expected %u", value, expected)) + if (CHECK(memcmp(&value, expected, sizeof(struct cgroup_value)), + "assert-storage", "storages differ")) return true; return false; @@ -39,7 +42,7 @@ static bool assert_storage(struct bpf_map *map, const char *cgroup_path, static bool assert_storage_noexist(struct bpf_map *map, const char *cgroup_path) { struct bpf_cgroup_storage_key key = {0}; - __u32 value; + struct cgroup_value value; int map_fd; map_fd = bpf_map__fd(map); @@ -86,6 +89,7 @@ out_clean: static void test_egress_only(int parent_cgroup_fd, int child_cgroup_fd) { struct cg_storage_multi_egress_only *obj; + struct cgroup_value expected_cgroup_value; struct bpf_link *parent_link = NULL, *child_link = NULL; bool err; @@ -109,7 +113,9 @@ static void test_egress_only(int parent_cgroup_fd, int child_cgroup_fd) if (CHECK(obj->bss->invocations != 1, "first-invoke", "invocations=%d", obj->bss->invocations)) goto close_bpf_object; - if (assert_storage(obj->maps.cgroup_storage, PARENT_CGROUP, 1)) + expected_cgroup_value = (struct cgroup_value) { .egress_pkts = 1 }; + if (assert_storage(obj->maps.cgroup_storage, + PARENT_CGROUP, &expected_cgroup_value)) goto close_bpf_object; if (assert_storage_noexist(obj->maps.cgroup_storage, CHILD_CGROUP)) goto close_bpf_object; @@ -129,9 +135,13 @@ static void test_egress_only(int parent_cgroup_fd, int child_cgroup_fd) if (CHECK(obj->bss->invocations != 3, "second-invoke", "invocations=%d", obj->bss->invocations)) goto close_bpf_object; - if (assert_storage(obj->maps.cgroup_storage, PARENT_CGROUP, 2)) + expected_cgroup_value = (struct cgroup_value) { .egress_pkts = 2 }; + if (assert_storage(obj->maps.cgroup_storage, + PARENT_CGROUP, &expected_cgroup_value)) goto close_bpf_object; - if (assert_storage(obj->maps.cgroup_storage, CHILD_CGROUP, 1)) + expected_cgroup_value = (struct cgroup_value) { .egress_pkts = 1 }; + if (assert_storage(obj->maps.cgroup_storage, + CHILD_CGROUP, &expected_cgroup_value)) goto close_bpf_object; close_bpf_object: @@ -141,6 +151,20 @@ close_bpf_object: cg_storage_multi_egress_only__destroy(obj); } +static void test_egress_ingress(int parent_cgroup_fd, int child_cgroup_fd) +{ + struct cg_storage_multi_egress_ingress *obj; + + /* Cannot load both programs due to verifier failure: + * "only one cgroup storage of each type is allowed" + */ + obj = cg_storage_multi_egress_ingress__open_and_load(); + CHECK(obj || errno != EBUSY, + "skel-load", "errno %d, expected EBUSY", errno); + + cg_storage_multi_egress_ingress__destroy(obj); +} + void test_cg_storage_multi(void) { int parent_cgroup_fd = -1, child_cgroup_fd = -1; @@ -155,6 +179,9 @@ void test_cg_storage_multi(void) if (test__start_subtest("egress_only")) test_egress_only(parent_cgroup_fd, child_cgroup_fd); + if (test__start_subtest("egress_ingress")) + test_egress_ingress(parent_cgroup_fd, child_cgroup_fd); + close_cgroup_fd: close(child_cgroup_fd); close(parent_cgroup_fd); diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi.h b/tools/testing/selftests/bpf/progs/cg_storage_multi.h new file mode 100644 index 000000000000..a0778fe7857a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cg_storage_multi.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __PROGS_CG_STORAGE_MULTI_H +#define __PROGS_CG_STORAGE_MULTI_H + +#include + +struct cgroup_value { + __u32 egress_pkts; + __u32 ingress_pkts; +}; + +#endif diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi_egress_ingress.c b/tools/testing/selftests/bpf/progs/cg_storage_multi_egress_ingress.c new file mode 100644 index 000000000000..9ce386899365 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cg_storage_multi_egress_ingress.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright 2020 Google LLC. + */ + +#include +#include +#include +#include +#include + +#include "progs/cg_storage_multi.h" + +struct { + __uint(type, BPF_MAP_TYPE_CGROUP_STORAGE); + __type(key, struct bpf_cgroup_storage_key); + __type(value, struct cgroup_value); +} cgroup_storage SEC(".maps"); + +__u32 invocations = 0; + +SEC("cgroup_skb/egress") +int egress(struct __sk_buff *skb) +{ + struct cgroup_value *ptr_cg_storage = + bpf_get_local_storage(&cgroup_storage, 0); + + __sync_fetch_and_add(&ptr_cg_storage->egress_pkts, 1); + __sync_fetch_and_add(&invocations, 1); + + return 1; +} + +SEC("cgroup_skb/ingress") +int ingress(struct __sk_buff *skb) +{ + struct cgroup_value *ptr_cg_storage = + bpf_get_local_storage(&cgroup_storage, 0); + + __sync_fetch_and_add(&ptr_cg_storage->ingress_pkts, 1); + __sync_fetch_and_add(&invocations, 1); + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi_egress_only.c b/tools/testing/selftests/bpf/progs/cg_storage_multi_egress_only.c index ec0165d07105..44ad46b33539 100644 --- a/tools/testing/selftests/bpf/progs/cg_storage_multi_egress_only.c +++ b/tools/testing/selftests/bpf/progs/cg_storage_multi_egress_only.c @@ -10,10 +10,12 @@ #include #include +#include "progs/cg_storage_multi.h" + struct { __uint(type, BPF_MAP_TYPE_CGROUP_STORAGE); __type(key, struct bpf_cgroup_storage_key); - __type(value, __u32); + __type(value, struct cgroup_value); } cgroup_storage SEC(".maps"); __u32 invocations = 0; @@ -21,9 +23,10 @@ __u32 invocations = 0; SEC("cgroup_skb/egress") int egress(struct __sk_buff *skb) { - __u32 *ptr_cg_storage = bpf_get_local_storage(&cgroup_storage, 0); + struct cgroup_value *ptr_cg_storage = + bpf_get_local_storage(&cgroup_storage, 0); - __sync_fetch_and_add(ptr_cg_storage, 1); + __sync_fetch_and_add(&ptr_cg_storage->egress_pkts, 1); __sync_fetch_and_add(&invocations, 1); return 1; -- cgit v1.2.3 From 3573f384014f51fd5289df0e8369b63ae7fdc244 Mon Sep 17 00:00:00 2001 From: YiFei Zhu Date: Thu, 23 Jul 2020 23:47:44 -0500 Subject: selftests/bpf: Test CGROUP_STORAGE behavior on shared egress + ingress This mirrors the original egress-only test. The cgroup_storage is now extended to have two packet counters, one for egress and one for ingress. We also extend to have two egress programs to test that egress will always share with other egress origrams in the same cgroup. The behavior of the counters are exactly the same as the original egress-only test. The test is split into two, one "isolated" test that when the key type is struct bpf_cgroup_storage_key, which contains the attach type, programs of different attach types will see different storages. The other, "shared" test that when the key type is u64, programs of different attach types will see the same storage if they are attached to the same cgroup. Signed-off-by: YiFei Zhu Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/c756f5f1521227b8e6e90a453299dda722d7324d.1595565795.git.zhuyifei@google.com --- .../selftests/bpf/prog_tests/cg_storage_multi.c | 265 +++++++++++++++++++-- .../bpf/progs/cg_storage_multi_egress_ingress.c | 45 ---- .../bpf/progs/cg_storage_multi_isolated.c | 57 +++++ .../selftests/bpf/progs/cg_storage_multi_shared.c | 57 +++++ 4 files changed, 354 insertions(+), 70 deletions(-) delete mode 100644 tools/testing/selftests/bpf/progs/cg_storage_multi_egress_ingress.c create mode 100644 tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c create mode 100644 tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c b/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c index 1c7653423698..c67d8c076a34 100644 --- a/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c @@ -11,25 +11,23 @@ #include "progs/cg_storage_multi.h" #include "cg_storage_multi_egress_only.skel.h" -#include "cg_storage_multi_egress_ingress.skel.h" +#include "cg_storage_multi_isolated.skel.h" +#include "cg_storage_multi_shared.skel.h" #define PARENT_CGROUP "/cgroup_storage" #define CHILD_CGROUP "/cgroup_storage/child" static int duration; -static bool assert_storage(struct bpf_map *map, const char *cgroup_path, +static bool assert_storage(struct bpf_map *map, const void *key, struct cgroup_value *expected) { - struct bpf_cgroup_storage_key key = {0}; struct cgroup_value value; int map_fd; map_fd = bpf_map__fd(map); - key.cgroup_inode_id = get_cgroup_id(cgroup_path); - key.attach_type = BPF_CGROUP_INET_EGRESS; - if (CHECK(bpf_map_lookup_elem(map_fd, &key, &value) < 0, + if (CHECK(bpf_map_lookup_elem(map_fd, key, &value) < 0, "map-lookup", "errno %d", errno)) return true; if (CHECK(memcmp(&value, expected, sizeof(struct cgroup_value)), @@ -39,17 +37,14 @@ static bool assert_storage(struct bpf_map *map, const char *cgroup_path, return false; } -static bool assert_storage_noexist(struct bpf_map *map, const char *cgroup_path) +static bool assert_storage_noexist(struct bpf_map *map, const void *key) { - struct bpf_cgroup_storage_key key = {0}; struct cgroup_value value; int map_fd; map_fd = bpf_map__fd(map); - key.cgroup_inode_id = get_cgroup_id(cgroup_path); - key.attach_type = BPF_CGROUP_INET_EGRESS; - if (CHECK(bpf_map_lookup_elem(map_fd, &key, &value) == 0, + if (CHECK(bpf_map_lookup_elem(map_fd, key, &value) == 0, "map-lookup", "succeeded, expected ENOENT")) return true; if (CHECK(errno != ENOENT, @@ -90,9 +85,12 @@ static void test_egress_only(int parent_cgroup_fd, int child_cgroup_fd) { struct cg_storage_multi_egress_only *obj; struct cgroup_value expected_cgroup_value; + struct bpf_cgroup_storage_key key; struct bpf_link *parent_link = NULL, *child_link = NULL; bool err; + key.attach_type = BPF_CGROUP_INET_EGRESS; + obj = cg_storage_multi_egress_only__open_and_load(); if (CHECK(!obj, "skel-load", "errno %d", errno)) return; @@ -113,11 +111,13 @@ static void test_egress_only(int parent_cgroup_fd, int child_cgroup_fd) if (CHECK(obj->bss->invocations != 1, "first-invoke", "invocations=%d", obj->bss->invocations)) goto close_bpf_object; + key.cgroup_inode_id = get_cgroup_id(PARENT_CGROUP); expected_cgroup_value = (struct cgroup_value) { .egress_pkts = 1 }; if (assert_storage(obj->maps.cgroup_storage, - PARENT_CGROUP, &expected_cgroup_value)) + &key, &expected_cgroup_value)) goto close_bpf_object; - if (assert_storage_noexist(obj->maps.cgroup_storage, CHILD_CGROUP)) + key.cgroup_inode_id = get_cgroup_id(CHILD_CGROUP); + if (assert_storage_noexist(obj->maps.cgroup_storage, &key)) goto close_bpf_object; /* Attach to parent and child cgroup, trigger packet from child. @@ -135,13 +135,15 @@ static void test_egress_only(int parent_cgroup_fd, int child_cgroup_fd) if (CHECK(obj->bss->invocations != 3, "second-invoke", "invocations=%d", obj->bss->invocations)) goto close_bpf_object; + key.cgroup_inode_id = get_cgroup_id(PARENT_CGROUP); expected_cgroup_value = (struct cgroup_value) { .egress_pkts = 2 }; if (assert_storage(obj->maps.cgroup_storage, - PARENT_CGROUP, &expected_cgroup_value)) + &key, &expected_cgroup_value)) goto close_bpf_object; + key.cgroup_inode_id = get_cgroup_id(CHILD_CGROUP); expected_cgroup_value = (struct cgroup_value) { .egress_pkts = 1 }; if (assert_storage(obj->maps.cgroup_storage, - CHILD_CGROUP, &expected_cgroup_value)) + &key, &expected_cgroup_value)) goto close_bpf_object; close_bpf_object: @@ -151,18 +153,228 @@ close_bpf_object: cg_storage_multi_egress_only__destroy(obj); } -static void test_egress_ingress(int parent_cgroup_fd, int child_cgroup_fd) +static void test_isolated(int parent_cgroup_fd, int child_cgroup_fd) { - struct cg_storage_multi_egress_ingress *obj; + struct cg_storage_multi_isolated *obj; + struct cgroup_value expected_cgroup_value; + struct bpf_cgroup_storage_key key; + struct bpf_link *parent_egress1_link = NULL, *parent_egress2_link = NULL; + struct bpf_link *child_egress1_link = NULL, *child_egress2_link = NULL; + struct bpf_link *parent_ingress_link = NULL, *child_ingress_link = NULL; + bool err; - /* Cannot load both programs due to verifier failure: - * "only one cgroup storage of each type is allowed" + obj = cg_storage_multi_isolated__open_and_load(); + if (CHECK(!obj, "skel-load", "errno %d", errno)) + return; + + /* Attach to parent cgroup, trigger packet from child. + * Assert that there is three runs, two with parent cgroup egress and + * one with parent cgroup ingress, stored in separate parent storages. + * Also assert that child cgroup's storages does not exist */ - obj = cg_storage_multi_egress_ingress__open_and_load(); - CHECK(obj || errno != EBUSY, - "skel-load", "errno %d, expected EBUSY", errno); + parent_egress1_link = bpf_program__attach_cgroup(obj->progs.egress1, + parent_cgroup_fd); + if (CHECK(IS_ERR(parent_egress1_link), "parent-egress1-cg-attach", + "err %ld", PTR_ERR(parent_egress1_link))) + goto close_bpf_object; + parent_egress2_link = bpf_program__attach_cgroup(obj->progs.egress2, + parent_cgroup_fd); + if (CHECK(IS_ERR(parent_egress2_link), "parent-egress2-cg-attach", + "err %ld", PTR_ERR(parent_egress2_link))) + goto close_bpf_object; + parent_ingress_link = bpf_program__attach_cgroup(obj->progs.ingress, + parent_cgroup_fd); + if (CHECK(IS_ERR(parent_ingress_link), "parent-ingress-cg-attach", + "err %ld", PTR_ERR(parent_ingress_link))) + goto close_bpf_object; + err = connect_send(CHILD_CGROUP); + if (CHECK(err, "first-connect-send", "errno %d", errno)) + goto close_bpf_object; + if (CHECK(obj->bss->invocations != 3, + "first-invoke", "invocations=%d", obj->bss->invocations)) + goto close_bpf_object; + key.cgroup_inode_id = get_cgroup_id(PARENT_CGROUP); + key.attach_type = BPF_CGROUP_INET_EGRESS; + expected_cgroup_value = (struct cgroup_value) { .egress_pkts = 2 }; + if (assert_storage(obj->maps.cgroup_storage, + &key, &expected_cgroup_value)) + goto close_bpf_object; + key.attach_type = BPF_CGROUP_INET_INGRESS; + expected_cgroup_value = (struct cgroup_value) { .ingress_pkts = 1 }; + if (assert_storage(obj->maps.cgroup_storage, + &key, &expected_cgroup_value)) + goto close_bpf_object; + key.cgroup_inode_id = get_cgroup_id(CHILD_CGROUP); + key.attach_type = BPF_CGROUP_INET_EGRESS; + if (assert_storage_noexist(obj->maps.cgroup_storage, &key)) + goto close_bpf_object; + key.attach_type = BPF_CGROUP_INET_INGRESS; + if (assert_storage_noexist(obj->maps.cgroup_storage, &key)) + goto close_bpf_object; - cg_storage_multi_egress_ingress__destroy(obj); + /* Attach to parent and child cgroup, trigger packet from child. + * Assert that there is six additional runs, parent cgroup egresses and + * ingress, child cgroup egresses and ingress. + * Assert that egree and ingress storages are separate. + */ + child_egress1_link = bpf_program__attach_cgroup(obj->progs.egress1, + child_cgroup_fd); + if (CHECK(IS_ERR(child_egress1_link), "child-egress1-cg-attach", + "err %ld", PTR_ERR(child_egress1_link))) + goto close_bpf_object; + child_egress2_link = bpf_program__attach_cgroup(obj->progs.egress2, + child_cgroup_fd); + if (CHECK(IS_ERR(child_egress2_link), "child-egress2-cg-attach", + "err %ld", PTR_ERR(child_egress2_link))) + goto close_bpf_object; + child_ingress_link = bpf_program__attach_cgroup(obj->progs.ingress, + child_cgroup_fd); + if (CHECK(IS_ERR(child_ingress_link), "child-ingress-cg-attach", + "err %ld", PTR_ERR(child_ingress_link))) + goto close_bpf_object; + err = connect_send(CHILD_CGROUP); + if (CHECK(err, "second-connect-send", "errno %d", errno)) + goto close_bpf_object; + if (CHECK(obj->bss->invocations != 9, + "second-invoke", "invocations=%d", obj->bss->invocations)) + goto close_bpf_object; + key.cgroup_inode_id = get_cgroup_id(PARENT_CGROUP); + key.attach_type = BPF_CGROUP_INET_EGRESS; + expected_cgroup_value = (struct cgroup_value) { .egress_pkts = 4 }; + if (assert_storage(obj->maps.cgroup_storage, + &key, &expected_cgroup_value)) + goto close_bpf_object; + key.attach_type = BPF_CGROUP_INET_INGRESS; + expected_cgroup_value = (struct cgroup_value) { .ingress_pkts = 2 }; + if (assert_storage(obj->maps.cgroup_storage, + &key, &expected_cgroup_value)) + goto close_bpf_object; + key.cgroup_inode_id = get_cgroup_id(CHILD_CGROUP); + key.attach_type = BPF_CGROUP_INET_EGRESS; + expected_cgroup_value = (struct cgroup_value) { .egress_pkts = 2 }; + if (assert_storage(obj->maps.cgroup_storage, + &key, &expected_cgroup_value)) + goto close_bpf_object; + key.attach_type = BPF_CGROUP_INET_INGRESS; + expected_cgroup_value = (struct cgroup_value) { .ingress_pkts = 1 }; + if (assert_storage(obj->maps.cgroup_storage, + &key, &expected_cgroup_value)) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(parent_egress1_link); + bpf_link__destroy(parent_egress2_link); + bpf_link__destroy(parent_ingress_link); + bpf_link__destroy(child_egress1_link); + bpf_link__destroy(child_egress2_link); + bpf_link__destroy(child_ingress_link); + + cg_storage_multi_isolated__destroy(obj); +} + +static void test_shared(int parent_cgroup_fd, int child_cgroup_fd) +{ + struct cg_storage_multi_shared *obj; + struct cgroup_value expected_cgroup_value; + __u64 key; + struct bpf_link *parent_egress1_link = NULL, *parent_egress2_link = NULL; + struct bpf_link *child_egress1_link = NULL, *child_egress2_link = NULL; + struct bpf_link *parent_ingress_link = NULL, *child_ingress_link = NULL; + bool err; + + obj = cg_storage_multi_shared__open_and_load(); + if (CHECK(!obj, "skel-load", "errno %d", errno)) + return; + + /* Attach to parent cgroup, trigger packet from child. + * Assert that there is three runs, two with parent cgroup egress and + * one with parent cgroup ingress. + * Also assert that child cgroup's storage does not exist + */ + parent_egress1_link = bpf_program__attach_cgroup(obj->progs.egress1, + parent_cgroup_fd); + if (CHECK(IS_ERR(parent_egress1_link), "parent-egress1-cg-attach", + "err %ld", PTR_ERR(parent_egress1_link))) + goto close_bpf_object; + parent_egress2_link = bpf_program__attach_cgroup(obj->progs.egress2, + parent_cgroup_fd); + if (CHECK(IS_ERR(parent_egress2_link), "parent-egress2-cg-attach", + "err %ld", PTR_ERR(parent_egress2_link))) + goto close_bpf_object; + parent_ingress_link = bpf_program__attach_cgroup(obj->progs.ingress, + parent_cgroup_fd); + if (CHECK(IS_ERR(parent_ingress_link), "parent-ingress-cg-attach", + "err %ld", PTR_ERR(parent_ingress_link))) + goto close_bpf_object; + err = connect_send(CHILD_CGROUP); + if (CHECK(err, "first-connect-send", "errno %d", errno)) + goto close_bpf_object; + if (CHECK(obj->bss->invocations != 3, + "first-invoke", "invocations=%d", obj->bss->invocations)) + goto close_bpf_object; + key = get_cgroup_id(PARENT_CGROUP); + expected_cgroup_value = (struct cgroup_value) { + .egress_pkts = 2, + .ingress_pkts = 1, + }; + if (assert_storage(obj->maps.cgroup_storage, + &key, &expected_cgroup_value)) + goto close_bpf_object; + key = get_cgroup_id(CHILD_CGROUP); + if (assert_storage_noexist(obj->maps.cgroup_storage, &key)) + goto close_bpf_object; + + /* Attach to parent and child cgroup, trigger packet from child. + * Assert that there is six additional runs, parent cgroup egresses and + * ingress, child cgroup egresses and ingress. + */ + child_egress1_link = bpf_program__attach_cgroup(obj->progs.egress1, + child_cgroup_fd); + if (CHECK(IS_ERR(child_egress1_link), "child-egress1-cg-attach", + "err %ld", PTR_ERR(child_egress1_link))) + goto close_bpf_object; + child_egress2_link = bpf_program__attach_cgroup(obj->progs.egress2, + child_cgroup_fd); + if (CHECK(IS_ERR(child_egress2_link), "child-egress2-cg-attach", + "err %ld", PTR_ERR(child_egress2_link))) + goto close_bpf_object; + child_ingress_link = bpf_program__attach_cgroup(obj->progs.ingress, + child_cgroup_fd); + if (CHECK(IS_ERR(child_ingress_link), "child-ingress-cg-attach", + "err %ld", PTR_ERR(child_ingress_link))) + goto close_bpf_object; + err = connect_send(CHILD_CGROUP); + if (CHECK(err, "second-connect-send", "errno %d", errno)) + goto close_bpf_object; + if (CHECK(obj->bss->invocations != 9, + "second-invoke", "invocations=%d", obj->bss->invocations)) + goto close_bpf_object; + key = get_cgroup_id(PARENT_CGROUP); + expected_cgroup_value = (struct cgroup_value) { + .egress_pkts = 4, + .ingress_pkts = 2, + }; + if (assert_storage(obj->maps.cgroup_storage, + &key, &expected_cgroup_value)) + goto close_bpf_object; + key = get_cgroup_id(CHILD_CGROUP); + expected_cgroup_value = (struct cgroup_value) { + .egress_pkts = 2, + .ingress_pkts = 1, + }; + if (assert_storage(obj->maps.cgroup_storage, + &key, &expected_cgroup_value)) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(parent_egress1_link); + bpf_link__destroy(parent_egress2_link); + bpf_link__destroy(parent_ingress_link); + bpf_link__destroy(child_egress1_link); + bpf_link__destroy(child_egress2_link); + bpf_link__destroy(child_ingress_link); + + cg_storage_multi_shared__destroy(obj); } void test_cg_storage_multi(void) @@ -179,8 +391,11 @@ void test_cg_storage_multi(void) if (test__start_subtest("egress_only")) test_egress_only(parent_cgroup_fd, child_cgroup_fd); - if (test__start_subtest("egress_ingress")) - test_egress_ingress(parent_cgroup_fd, child_cgroup_fd); + if (test__start_subtest("isolated")) + test_isolated(parent_cgroup_fd, child_cgroup_fd); + + if (test__start_subtest("shared")) + test_shared(parent_cgroup_fd, child_cgroup_fd); close_cgroup_fd: close(child_cgroup_fd); diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi_egress_ingress.c b/tools/testing/selftests/bpf/progs/cg_storage_multi_egress_ingress.c deleted file mode 100644 index 9ce386899365..000000000000 --- a/tools/testing/selftests/bpf/progs/cg_storage_multi_egress_ingress.c +++ /dev/null @@ -1,45 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only - -/* - * Copyright 2020 Google LLC. - */ - -#include -#include -#include -#include -#include - -#include "progs/cg_storage_multi.h" - -struct { - __uint(type, BPF_MAP_TYPE_CGROUP_STORAGE); - __type(key, struct bpf_cgroup_storage_key); - __type(value, struct cgroup_value); -} cgroup_storage SEC(".maps"); - -__u32 invocations = 0; - -SEC("cgroup_skb/egress") -int egress(struct __sk_buff *skb) -{ - struct cgroup_value *ptr_cg_storage = - bpf_get_local_storage(&cgroup_storage, 0); - - __sync_fetch_and_add(&ptr_cg_storage->egress_pkts, 1); - __sync_fetch_and_add(&invocations, 1); - - return 1; -} - -SEC("cgroup_skb/ingress") -int ingress(struct __sk_buff *skb) -{ - struct cgroup_value *ptr_cg_storage = - bpf_get_local_storage(&cgroup_storage, 0); - - __sync_fetch_and_add(&ptr_cg_storage->ingress_pkts, 1); - __sync_fetch_and_add(&invocations, 1); - - return 1; -} diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c b/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c new file mode 100644 index 000000000000..a25373002055 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright 2020 Google LLC. + */ + +#include +#include +#include +#include +#include + +#include "progs/cg_storage_multi.h" + +struct { + __uint(type, BPF_MAP_TYPE_CGROUP_STORAGE); + __type(key, struct bpf_cgroup_storage_key); + __type(value, struct cgroup_value); +} cgroup_storage SEC(".maps"); + +__u32 invocations = 0; + +SEC("cgroup_skb/egress/1") +int egress1(struct __sk_buff *skb) +{ + struct cgroup_value *ptr_cg_storage = + bpf_get_local_storage(&cgroup_storage, 0); + + __sync_fetch_and_add(&ptr_cg_storage->egress_pkts, 1); + __sync_fetch_and_add(&invocations, 1); + + return 1; +} + +SEC("cgroup_skb/egress/2") +int egress2(struct __sk_buff *skb) +{ + struct cgroup_value *ptr_cg_storage = + bpf_get_local_storage(&cgroup_storage, 0); + + __sync_fetch_and_add(&ptr_cg_storage->egress_pkts, 1); + __sync_fetch_and_add(&invocations, 1); + + return 1; +} + +SEC("cgroup_skb/ingress") +int ingress(struct __sk_buff *skb) +{ + struct cgroup_value *ptr_cg_storage = + bpf_get_local_storage(&cgroup_storage, 0); + + __sync_fetch_and_add(&ptr_cg_storage->ingress_pkts, 1); + __sync_fetch_and_add(&invocations, 1); + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c b/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c new file mode 100644 index 000000000000..a149f33bc533 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright 2020 Google LLC. + */ + +#include +#include +#include +#include +#include + +#include "progs/cg_storage_multi.h" + +struct { + __uint(type, BPF_MAP_TYPE_CGROUP_STORAGE); + __type(key, __u64); + __type(value, struct cgroup_value); +} cgroup_storage SEC(".maps"); + +__u32 invocations = 0; + +SEC("cgroup_skb/egress/1") +int egress1(struct __sk_buff *skb) +{ + struct cgroup_value *ptr_cg_storage = + bpf_get_local_storage(&cgroup_storage, 0); + + __sync_fetch_and_add(&ptr_cg_storage->egress_pkts, 1); + __sync_fetch_and_add(&invocations, 1); + + return 1; +} + +SEC("cgroup_skb/egress/2") +int egress2(struct __sk_buff *skb) +{ + struct cgroup_value *ptr_cg_storage = + bpf_get_local_storage(&cgroup_storage, 0); + + __sync_fetch_and_add(&ptr_cg_storage->egress_pkts, 1); + __sync_fetch_and_add(&invocations, 1); + + return 1; +} + +SEC("cgroup_skb/ingress") +int ingress(struct __sk_buff *skb) +{ + struct cgroup_value *ptr_cg_storage = + bpf_get_local_storage(&cgroup_storage, 0); + + __sync_fetch_and_add(&ptr_cg_storage->ingress_pkts, 1); + __sync_fetch_and_add(&invocations, 1); + + return 1; +} -- cgit v1.2.3 From dc8698cac7aada9b61a612cb819341d84591163e Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 21 Jul 2020 23:46:00 -0700 Subject: libbpf: Add support for BPF XDP link Sync UAPI header and add support for using bpf_link-based XDP attachment. Make xdp/ prog type set expected attach type. Kernel didn't enforce attach_type for XDP programs before, so there is no backwards compatiblity issues there. Also fix section_names selftest to recognize that xdp prog types now have expected attach type. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200722064603.3350758-8-andriin@fb.com --- tools/include/uapi/linux/bpf.h | 10 +++++++++- tools/lib/bpf/libbpf.c | 9 ++++++++- tools/lib/bpf/libbpf.h | 2 ++ tools/lib/bpf/libbpf.map | 1 + tools/testing/selftests/bpf/prog_tests/section_names.c | 2 +- 5 files changed, 21 insertions(+), 3 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 828c2f6438f2..e1ba4ae6a916 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -230,6 +230,7 @@ enum bpf_attach_type { BPF_CGROUP_INET_SOCK_RELEASE, BPF_XDP_CPUMAP, BPF_SK_LOOKUP, + BPF_XDP, __MAX_BPF_ATTACH_TYPE }; @@ -242,6 +243,7 @@ enum bpf_link_type { BPF_LINK_TYPE_CGROUP = 3, BPF_LINK_TYPE_ITER = 4, BPF_LINK_TYPE_NETNS = 5, + BPF_LINK_TYPE_XDP = 6, MAX_BPF_LINK_TYPE, }; @@ -614,7 +616,10 @@ union bpf_attr { struct { /* struct used by BPF_LINK_CREATE command */ __u32 prog_fd; /* eBPF program to attach */ - __u32 target_fd; /* object to attach to */ + union { + __u32 target_fd; /* object to attach to */ + __u32 target_ifindex; /* target ifindex */ + }; __u32 attach_type; /* attach type */ __u32 flags; /* extra flags */ } link_create; @@ -4064,6 +4069,9 @@ struct bpf_link_info { __u32 netns_ino; __u32 attach_type; } netns; + struct { + __u32 ifindex; + } xdp; }; } __attribute__((aligned(8))); diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index e51479d60285..54830d603fee 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -6915,7 +6915,8 @@ static const struct bpf_sec_def section_defs[] = { BPF_XDP_DEVMAP), BPF_EAPROG_SEC("xdp_cpumap/", BPF_PROG_TYPE_XDP, BPF_XDP_CPUMAP), - BPF_PROG_SEC("xdp", BPF_PROG_TYPE_XDP), + BPF_EAPROG_SEC("xdp", BPF_PROG_TYPE_XDP, + BPF_XDP), BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT), BPF_PROG_SEC("lwt_in", BPF_PROG_TYPE_LWT_IN), BPF_PROG_SEC("lwt_out", BPF_PROG_TYPE_LWT_OUT), @@ -8281,6 +8282,12 @@ bpf_program__attach_netns(struct bpf_program *prog, int netns_fd) return bpf_program__attach_fd(prog, netns_fd, "netns"); } +struct bpf_link *bpf_program__attach_xdp(struct bpf_program *prog, int ifindex) +{ + /* target_fd/target_ifindex use the same field in LINK_CREATE */ + return bpf_program__attach_fd(prog, ifindex, "xdp"); +} + struct bpf_link * bpf_program__attach_iter(struct bpf_program *prog, const struct bpf_iter_attach_opts *opts) diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index c6813791fa7e..9924385462ab 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -257,6 +257,8 @@ LIBBPF_API struct bpf_link * bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd); LIBBPF_API struct bpf_link * bpf_program__attach_netns(struct bpf_program *prog, int netns_fd); +LIBBPF_API struct bpf_link * +bpf_program__attach_xdp(struct bpf_program *prog, int ifindex); struct bpf_map; diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 6f0856abe299..ca49a6a7e5b2 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -286,6 +286,7 @@ LIBBPF_0.1.0 { bpf_map__set_value_size; bpf_map__type; bpf_map__value_size; + bpf_program__attach_xdp; bpf_program__autoload; bpf_program__is_sk_lookup; bpf_program__set_autoload; diff --git a/tools/testing/selftests/bpf/prog_tests/section_names.c b/tools/testing/selftests/bpf/prog_tests/section_names.c index 713167449c98..8b571890c57e 100644 --- a/tools/testing/selftests/bpf/prog_tests/section_names.c +++ b/tools/testing/selftests/bpf/prog_tests/section_names.c @@ -35,7 +35,7 @@ static struct sec_name_test tests[] = { {-EINVAL, 0}, }, {"raw_tp/", {0, BPF_PROG_TYPE_RAW_TRACEPOINT, 0}, {-EINVAL, 0} }, - {"xdp", {0, BPF_PROG_TYPE_XDP, 0}, {-EINVAL, 0} }, + {"xdp", {0, BPF_PROG_TYPE_XDP, BPF_XDP}, {0, BPF_XDP} }, {"perf_event", {0, BPF_PROG_TYPE_PERF_EVENT, 0}, {-EINVAL, 0} }, {"lwt_in", {0, BPF_PROG_TYPE_LWT_IN, 0}, {-EINVAL, 0} }, {"lwt_out", {0, BPF_PROG_TYPE_LWT_OUT, 0}, {-EINVAL, 0} }, -- cgit v1.2.3 From fe48230cf2ae27c9e3b96d29908e22e2926fd1ab Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 21 Jul 2020 23:46:01 -0700 Subject: selftests/bpf: Add BPF XDP link selftests Add selftest validating all the attachment logic around BPF XDP link. Test also link updates and get_obj_info() APIs. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200722064603.3350758-9-andriin@fb.com --- tools/testing/selftests/bpf/prog_tests/xdp_link.c | 137 ++++++++++++++++++++++ tools/testing/selftests/bpf/progs/test_xdp_link.c | 12 ++ 2 files changed, 149 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/xdp_link.c create mode 100644 tools/testing/selftests/bpf/progs/test_xdp_link.c (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_link.c b/tools/testing/selftests/bpf/prog_tests/xdp_link.c new file mode 100644 index 000000000000..52cba6795d40 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/xdp_link.c @@ -0,0 +1,137 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include +#include +#include "test_xdp_link.skel.h" + +#define IFINDEX_LO 1 + +void test_xdp_link(void) +{ + __u32 duration = 0, id1, id2, id0 = 0, prog_fd1, prog_fd2, err; + DECLARE_LIBBPF_OPTS(bpf_xdp_set_link_opts, opts, .old_fd = -1); + struct test_xdp_link *skel1 = NULL, *skel2 = NULL; + struct bpf_link_info link_info; + struct bpf_prog_info prog_info; + struct bpf_link *link; + __u32 link_info_len = sizeof(link_info); + __u32 prog_info_len = sizeof(prog_info); + + skel1 = test_xdp_link__open_and_load(); + if (CHECK(!skel1, "skel_load", "skeleton open and load failed\n")) + goto cleanup; + prog_fd1 = bpf_program__fd(skel1->progs.xdp_handler); + + skel2 = test_xdp_link__open_and_load(); + if (CHECK(!skel2, "skel_load", "skeleton open and load failed\n")) + goto cleanup; + prog_fd2 = bpf_program__fd(skel2->progs.xdp_handler); + + memset(&prog_info, 0, sizeof(prog_info)); + err = bpf_obj_get_info_by_fd(prog_fd1, &prog_info, &prog_info_len); + if (CHECK(err, "fd_info1", "failed %d\n", -errno)) + goto cleanup; + id1 = prog_info.id; + + memset(&prog_info, 0, sizeof(prog_info)); + err = bpf_obj_get_info_by_fd(prog_fd2, &prog_info, &prog_info_len); + if (CHECK(err, "fd_info2", "failed %d\n", -errno)) + goto cleanup; + id2 = prog_info.id; + + /* set initial prog attachment */ + err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, prog_fd1, XDP_FLAGS_REPLACE, &opts); + if (CHECK(err, "fd_attach", "initial prog attach failed: %d\n", err)) + goto cleanup; + + /* validate prog ID */ + err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0); + CHECK(err || id0 != id1, "id1_check", + "loaded prog id %u != id1 %u, err %d", id0, id1, err); + + /* BPF link is not allowed to replace prog attachment */ + link = bpf_program__attach_xdp(skel1->progs.xdp_handler, IFINDEX_LO); + if (CHECK(!IS_ERR(link), "link_attach_fail", "unexpected success\n")) { + bpf_link__destroy(link); + /* best-effort detach prog */ + opts.old_fd = prog_fd1; + bpf_set_link_xdp_fd_opts(IFINDEX_LO, -1, XDP_FLAGS_REPLACE, &opts); + goto cleanup; + } + + /* detach BPF program */ + opts.old_fd = prog_fd1; + err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, -1, XDP_FLAGS_REPLACE, &opts); + if (CHECK(err, "prog_detach", "failed %d\n", err)) + goto cleanup; + + /* now BPF link should attach successfully */ + link = bpf_program__attach_xdp(skel1->progs.xdp_handler, IFINDEX_LO); + if (CHECK(IS_ERR(link), "link_attach", "failed: %ld\n", PTR_ERR(link))) + goto cleanup; + skel1->links.xdp_handler = link; + + /* validate prog ID */ + err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0); + if (CHECK(err || id0 != id1, "id1_check", + "loaded prog id %u != id1 %u, err %d", id0, id1, err)) + goto cleanup; + + /* BPF prog attach is not allowed to replace BPF link */ + opts.old_fd = prog_fd1; + err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, prog_fd2, XDP_FLAGS_REPLACE, &opts); + if (CHECK(!err, "prog_attach_fail", "unexpected success\n")) + goto cleanup; + + /* Can't force-update when BPF link is active */ + err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd2, 0); + if (CHECK(!err, "prog_update_fail", "unexpected success\n")) + goto cleanup; + + /* Can't force-detach when BPF link is active */ + err = bpf_set_link_xdp_fd(IFINDEX_LO, -1, 0); + if (CHECK(!err, "prog_detach_fail", "unexpected success\n")) + goto cleanup; + + /* BPF link is not allowed to replace another BPF link */ + link = bpf_program__attach_xdp(skel2->progs.xdp_handler, IFINDEX_LO); + if (CHECK(!IS_ERR(link), "link_attach_fail", "unexpected success\n")) { + bpf_link__destroy(link); + goto cleanup; + } + + bpf_link__destroy(skel1->links.xdp_handler); + skel1->links.xdp_handler = NULL; + + /* new link attach should succeed */ + link = bpf_program__attach_xdp(skel2->progs.xdp_handler, IFINDEX_LO); + if (CHECK(IS_ERR(link), "link_attach", "failed: %ld\n", PTR_ERR(link))) + goto cleanup; + skel2->links.xdp_handler = link; + + err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0); + if (CHECK(err || id0 != id2, "id2_check", + "loaded prog id %u != id2 %u, err %d", id0, id1, err)) + goto cleanup; + + /* updating program under active BPF link works as expected */ + err = bpf_link__update_program(link, skel1->progs.xdp_handler); + if (CHECK(err, "link_upd", "failed: %d\n", err)) + goto cleanup; + + memset(&link_info, 0, sizeof(link_info)); + err = bpf_obj_get_info_by_fd(bpf_link__fd(link), &link_info, &link_info_len); + if (CHECK(err, "link_info", "failed: %d\n", err)) + goto cleanup; + + CHECK(link_info.type != BPF_LINK_TYPE_XDP, "link_type", + "got %u != exp %u\n", link_info.type, BPF_LINK_TYPE_XDP); + CHECK(link_info.prog_id != id1, "link_prog_id", + "got %u != exp %u\n", link_info.prog_id, id1); + CHECK(link_info.xdp.ifindex != IFINDEX_LO, "link_ifindex", + "got %u != exp %u\n", link_info.xdp.ifindex, IFINDEX_LO); + +cleanup: + test_xdp_link__destroy(skel1); + test_xdp_link__destroy(skel2); +} diff --git a/tools/testing/selftests/bpf/progs/test_xdp_link.c b/tools/testing/selftests/bpf/progs/test_xdp_link.c new file mode 100644 index 000000000000..eb93ea95d1d8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_link.c @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include +#include + +char LICENSE[] SEC("license") = "GPL"; + +SEC("xdp/handler") +int xdp_handler(struct xdp_md *xdp) +{ + return 0; +} -- cgit v1.2.3 From 363885d7c62e293fb093c7c355bf5f05fa0a25a9 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 27 Jul 2020 16:33:45 -0700 Subject: selftests/bpf: Add new bpf_iter context structs to fix build on old kernels Add bpf_iter__bpf_map_elem and bpf_iter__bpf_sk_storage_map to bpf_iter.h. Fixes: 3b1c420bd882 ("selftests/bpf: Add a test for bpf sk_storage_map iterator") Fixes: 2a7c2fff7dd6 ("selftests/bpf: Add test for bpf hash map iterators") Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20200727233345.1686358-1-andriin@fb.com --- tools/testing/selftests/bpf/progs/bpf_iter.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/progs/bpf_iter.h b/tools/testing/selftests/bpf/progs/bpf_iter.h index 17db3bac518b..c196280df90d 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter.h +++ b/tools/testing/selftests/bpf/progs/bpf_iter.h @@ -11,6 +11,8 @@ #define tcp6_sock tcp6_sock___not_used #define bpf_iter__udp bpf_iter__udp___not_used #define udp6_sock udp6_sock___not_used +#define bpf_iter__bpf_map_elem bpf_iter__bpf_map_elem___not_used +#define bpf_iter__bpf_sk_storage_map bpf_iter__bpf_sk_storage_map___not_used #include "vmlinux.h" #undef bpf_iter_meta #undef bpf_iter__bpf_map @@ -22,6 +24,8 @@ #undef tcp6_sock #undef bpf_iter__udp #undef udp6_sock +#undef bpf_iter__bpf_map_elem +#undef bpf_iter__bpf_sk_storage_map struct bpf_iter_meta { struct seq_file *seq; @@ -78,3 +82,17 @@ struct udp6_sock { struct udp_sock udp; struct ipv6_pinfo inet6; } __attribute__((preserve_access_index)); + +struct bpf_iter__bpf_map_elem { + struct bpf_iter_meta *meta; + struct bpf_map *map; + void *key; + void *value; +}; + +struct bpf_iter__bpf_sk_storage_map { + struct bpf_iter_meta *meta; + struct bpf_map *map; + struct sock *sk; + void *value; +}; -- cgit v1.2.3 From ca5cd355b7f0372da0d50fce5b12a3367e417290 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 28 Jul 2020 07:39:02 -0700 Subject: bpf, selftests: use :: 1 for localhost in tcp_server.py Using localhost requires the host to have a /etc/hosts file with that specific line in it. By default my dev box did not, they used ip6-localhost, so the test was failing. To fix remove the need for any /etc/hosts and use ::1. I could just add the line, but this seems easier. Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Acked-by: Song Liu Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/159594714197.21431.10113693935099326445.stgit@john-Precision-5820-Tower --- tools/testing/selftests/bpf/tcp_client.py | 2 +- tools/testing/selftests/bpf/tcp_server.py | 2 +- tools/testing/selftests/bpf/test_netcnt.c | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/tcp_client.py b/tools/testing/selftests/bpf/tcp_client.py index a53ed58528d6..bfff82be3fc1 100755 --- a/tools/testing/selftests/bpf/tcp_client.py +++ b/tools/testing/selftests/bpf/tcp_client.py @@ -34,7 +34,7 @@ serverPort = int(sys.argv[1]) # create active socket sock = socket.socket(socket.AF_INET6, socket.SOCK_STREAM) try: - sock.connect(('localhost', serverPort)) + sock.connect(('::1', serverPort)) except socket.error as e: sys.exit(1) diff --git a/tools/testing/selftests/bpf/tcp_server.py b/tools/testing/selftests/bpf/tcp_server.py index 0ca60d193bed..42ab8882f00f 100755 --- a/tools/testing/selftests/bpf/tcp_server.py +++ b/tools/testing/selftests/bpf/tcp_server.py @@ -38,7 +38,7 @@ serverSocket = None # create passive socket serverSocket = socket.socket(socket.AF_INET6, socket.SOCK_STREAM) -try: serverSocket.bind(('localhost', 0)) +try: serverSocket.bind(('::1', 0)) except socket.error as msg: print('bind fails: ' + str(msg)) diff --git a/tools/testing/selftests/bpf/test_netcnt.c b/tools/testing/selftests/bpf/test_netcnt.c index c1da5404454a..7a68c9069639 100644 --- a/tools/testing/selftests/bpf/test_netcnt.c +++ b/tools/testing/selftests/bpf/test_netcnt.c @@ -82,9 +82,9 @@ int main(int argc, char **argv) } if (system("which ping6 &>/dev/null") == 0) - assert(!system("ping6 localhost -c 10000 -f -q > /dev/null")); + assert(!system("ping6 ::1 -c 10000 -f -q > /dev/null")); else - assert(!system("ping -6 localhost -c 10000 -f -q > /dev/null")); + assert(!system("ping -6 ::1 -c 10000 -f -q > /dev/null")); if (bpf_prog_query(cgroup_fd, BPF_CGROUP_INET_EGRESS, 0, NULL, NULL, &prog_cnt)) { -- cgit v1.2.3 From 12e6196fb15953605be54ac9320ac54371aecab7 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 28 Jul 2020 15:18:01 -0700 Subject: selftests/bpf: Test bpf_iter buffer access with negative offset Commit afbf21dce668 ("bpf: Support readonly/readwrite buffers in verifier") added readonly/readwrite buffer support which is currently used by bpf_iter tracing programs. It has a bug with incorrect parameter ordering which later fixed by Commit f6dfbe31e8fa ("bpf: Fix swapped arguments in calls to check_buffer_access"). This patch added a test case with a negative offset access which will trigger the error path. Without Commit f6dfbe31e8fa, running the test case in the patch, the error message looks like: R1_w=rdwr_buf(id=0,off=0,imm=0) R10=fp0 ; value_sum += *(__u32 *)(value - 4); 2: (61) r1 = *(u32 *)(r1 -4) R1 invalid (null) buffer access: off=-4, size=4 With the above commit, the error message looks like: R1_w=rdwr_buf(id=0,off=0,imm=0) R10=fp0 ; value_sum += *(__u32 *)(value - 4); 2: (61) r1 = *(u32 *)(r1 -4) R1 invalid rdwr buffer access: off=-4, size=4 Signed-off-by: Yonghong Song Signed-off-by: Daniel Borkmann Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20200728221801.1090406-1-yhs@fb.com --- tools/testing/selftests/bpf/prog_tests/bpf_iter.c | 13 +++++++++++++ .../selftests/bpf/progs/bpf_iter_test_kern6.c | 21 +++++++++++++++++++++ 2 files changed, 34 insertions(+) create mode 100644 tools/testing/selftests/bpf/progs/bpf_iter_test_kern6.c (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index d95de80b1851..4ffefdc1130f 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -21,6 +21,7 @@ #include "bpf_iter_bpf_percpu_array_map.skel.h" #include "bpf_iter_bpf_sk_storage_map.skel.h" #include "bpf_iter_test_kern5.skel.h" +#include "bpf_iter_test_kern6.skel.h" static int duration; @@ -885,6 +886,16 @@ static void test_rdonly_buf_out_of_bound(void) bpf_iter_test_kern5__destroy(skel); } +static void test_buf_neg_offset(void) +{ + struct bpf_iter_test_kern6 *skel; + + skel = bpf_iter_test_kern6__open_and_load(); + if (CHECK(skel, "bpf_iter_test_kern6__open_and_load", + "skeleton open_and_load unexpected success\n")) + bpf_iter_test_kern6__destroy(skel); +} + void test_bpf_iter(void) { if (test__start_subtest("btf_id_or_null")) @@ -933,4 +944,6 @@ void test_bpf_iter(void) test_bpf_sk_storage_map(); if (test__start_subtest("rdonly-buf-out-of-bound")) test_rdonly_buf_out_of_bound(); + if (test__start_subtest("buf-neg-offset")) + test_buf_neg_offset(); } diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern6.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern6.c new file mode 100644 index 000000000000..1c7304f56b1e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern6.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include "bpf_iter.h" +#include + +char _license[] SEC("license") = "GPL"; + +__u32 value_sum = 0; + +SEC("iter/bpf_map_elem") +int dump_bpf_hash_map(struct bpf_iter__bpf_map_elem *ctx) +{ + void *value = ctx->value; + + if (value == (void *)0) + return 0; + + /* negative offset, verifier failure. */ + value_sum += *(__u32 *)(value - 4); + return 0; +} -- cgit v1.2.3 From 4fb5f94911405b6d2645d4384c2ae1215bfc6a76 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Tue, 28 Jul 2020 17:31:04 -0700 Subject: selftests/bpf: Verify socket storage in cgroup/sock_{create, release} Augment udp_limit test to set and verify socket storage value. That should be enough to exercise the changes from the previous patch. Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20200729003104.1280813-2-sdf@google.com --- tools/testing/selftests/bpf/progs/udp_limit.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/progs/udp_limit.c b/tools/testing/selftests/bpf/progs/udp_limit.c index 8429b22525a7..165e3c2dd9a3 100644 --- a/tools/testing/selftests/bpf/progs/udp_limit.c +++ b/tools/testing/selftests/bpf/progs/udp_limit.c @@ -6,14 +6,28 @@ int invocations = 0, in_use = 0; +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, int); +} sk_map SEC(".maps"); + SEC("cgroup/sock_create") int sock(struct bpf_sock *ctx) { + int *sk_storage; __u32 key; if (ctx->type != SOCK_DGRAM) return 1; + sk_storage = bpf_sk_storage_get(&sk_map, ctx, 0, + BPF_SK_STORAGE_GET_F_CREATE); + if (!sk_storage) + return 0; + *sk_storage = 0xdeadbeef; + __sync_fetch_and_add(&invocations, 1); if (in_use > 0) { @@ -31,11 +45,16 @@ int sock(struct bpf_sock *ctx) SEC("cgroup/sock_release") int sock_release(struct bpf_sock *ctx) { + int *sk_storage; __u32 key; if (ctx->type != SOCK_DGRAM) return 1; + sk_storage = bpf_sk_storage_get(&sk_map, ctx, 0, 0); + if (!sk_storage || *sk_storage != 0xdeadbeef) + return 0; + __sync_fetch_and_add(&invocations, 1); __sync_fetch_and_add(&in_use, -1); return 1; -- cgit v1.2.3 From dfdb0d93e5bc351af5b286ae9c630d3cf869b810 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Wed, 29 Jul 2020 16:56:58 +0800 Subject: selftests/bpf: Add xdpdrv mode for test_xdp_redirect This patch add xdpdrv mode for test_xdp_redirect.sh since veth has support native mode. After update here is the test result: # ./test_xdp_redirect.sh selftests: test_xdp_redirect xdpgeneric [PASS] selftests: test_xdp_redirect xdpdrv [PASS] Signed-off-by: Hangbin Liu Signed-off-by: Daniel Borkmann Acked-by: Song Liu Acked-by: William Tu Link: https://lore.kernel.org/bpf/20200729085658.403794-1-liuhangbin@gmail.com --- tools/testing/selftests/bpf/test_xdp_redirect.sh | 84 +++++++++++++++--------- 1 file changed, 52 insertions(+), 32 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/test_xdp_redirect.sh b/tools/testing/selftests/bpf/test_xdp_redirect.sh index c4b17e08d431..dd80f0c84afb 100755 --- a/tools/testing/selftests/bpf/test_xdp_redirect.sh +++ b/tools/testing/selftests/bpf/test_xdp_redirect.sh @@ -10,52 +10,72 @@ # | xdp forwarding | # ------------------ -cleanup() +ret=0 + +setup() { - if [ "$?" = "0" ]; then - echo "selftests: test_xdp_redirect [PASS]"; - else - echo "selftests: test_xdp_redirect [FAILED]"; - fi - set +e + local xdpmode=$1 + + ip netns add ns1 + ip netns add ns2 + + ip link add veth1 index 111 type veth peer name veth11 netns ns1 + ip link add veth2 index 222 type veth peer name veth22 netns ns2 + + ip link set veth1 up + ip link set veth2 up + ip -n ns1 link set dev veth11 up + ip -n ns2 link set dev veth22 up + + ip -n ns1 addr add 10.1.1.11/24 dev veth11 + ip -n ns2 addr add 10.1.1.22/24 dev veth22 +} + +cleanup() +{ ip link del veth1 2> /dev/null ip link del veth2 2> /dev/null ip netns del ns1 2> /dev/null ip netns del ns2 2> /dev/null } -ip link set dev lo xdpgeneric off 2>/dev/null > /dev/null -if [ $? -ne 0 ];then - echo "selftests: [SKIP] Could not run test without the ip xdpgeneric support" - exit 0 -fi -set -e - -ip netns add ns1 -ip netns add ns2 +test_xdp_redirect() +{ + local xdpmode=$1 -trap cleanup 0 2 3 6 9 + setup -ip link add veth1 index 111 type veth peer name veth11 -ip link add veth2 index 222 type veth peer name veth22 + ip link set dev veth1 $xdpmode off &> /dev/null + if [ $? -ne 0 ];then + echo "selftests: test_xdp_redirect $xdpmode [SKIP]" + return 0 + fi -ip link set veth11 netns ns1 -ip link set veth22 netns ns2 + ip -n ns1 link set veth11 $xdpmode obj xdp_dummy.o sec xdp_dummy &> /dev/null + ip -n ns2 link set veth22 $xdpmode obj xdp_dummy.o sec xdp_dummy &> /dev/null + ip link set dev veth1 $xdpmode obj test_xdp_redirect.o sec redirect_to_222 &> /dev/null + ip link set dev veth2 $xdpmode obj test_xdp_redirect.o sec redirect_to_111 &> /dev/null -ip link set veth1 up -ip link set veth2 up + ip netns exec ns1 ping -c 1 10.1.1.22 &> /dev/null + local ret1=$? + ip netns exec ns2 ping -c 1 10.1.1.11 &> /dev/null + local ret2=$? -ip netns exec ns1 ip addr add 10.1.1.11/24 dev veth11 -ip netns exec ns2 ip addr add 10.1.1.22/24 dev veth22 + if [ $ret1 -eq 0 -a $ret2 -eq 0 ]; then + echo "selftests: test_xdp_redirect $xdpmode [PASS]"; + else + ret=1 + echo "selftests: test_xdp_redirect $xdpmode [FAILED]"; + fi -ip netns exec ns1 ip link set dev veth11 up -ip netns exec ns2 ip link set dev veth22 up + cleanup +} -ip link set dev veth1 xdpgeneric obj test_xdp_redirect.o sec redirect_to_222 -ip link set dev veth2 xdpgeneric obj test_xdp_redirect.o sec redirect_to_111 +set -e +trap cleanup 2 3 6 9 -ip netns exec ns1 ping -c 1 10.1.1.22 -ip netns exec ns2 ping -c 1 10.1.1.11 +test_xdp_redirect xdpgeneric +test_xdp_redirect xdpdrv -exit 0 +exit $ret -- cgit v1.2.3 From 80546ac4586c0bd326aa7ce80f076646db02bcd0 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 28 Jul 2020 21:50:56 -0700 Subject: selftests/bpf: Don't destroy failed link Check that link is NULL or proper pointer before invoking bpf_link__destroy(). Not doing this causes crash in test_progs, when cg_storage_multi selftest fails. Fixes: 3573f384014f ("selftests/bpf: Test CGROUP_STORAGE behavior on shared egress + ingress") Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20200729045056.3363921-1-andriin@fb.com --- .../selftests/bpf/prog_tests/cg_storage_multi.c | 42 ++++++++++++++-------- 1 file changed, 28 insertions(+), 14 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c b/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c index c67d8c076a34..643dfa35419c 100644 --- a/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c @@ -147,8 +147,10 @@ static void test_egress_only(int parent_cgroup_fd, int child_cgroup_fd) goto close_bpf_object; close_bpf_object: - bpf_link__destroy(parent_link); - bpf_link__destroy(child_link); + if (!IS_ERR(parent_link)) + bpf_link__destroy(parent_link); + if (!IS_ERR(child_link)) + bpf_link__destroy(child_link); cg_storage_multi_egress_only__destroy(obj); } @@ -262,12 +264,18 @@ static void test_isolated(int parent_cgroup_fd, int child_cgroup_fd) goto close_bpf_object; close_bpf_object: - bpf_link__destroy(parent_egress1_link); - bpf_link__destroy(parent_egress2_link); - bpf_link__destroy(parent_ingress_link); - bpf_link__destroy(child_egress1_link); - bpf_link__destroy(child_egress2_link); - bpf_link__destroy(child_ingress_link); + if (!IS_ERR(parent_egress1_link)) + bpf_link__destroy(parent_egress1_link); + if (!IS_ERR(parent_egress2_link)) + bpf_link__destroy(parent_egress2_link); + if (!IS_ERR(parent_ingress_link)) + bpf_link__destroy(parent_ingress_link); + if (!IS_ERR(child_egress1_link)) + bpf_link__destroy(child_egress1_link); + if (!IS_ERR(child_egress2_link)) + bpf_link__destroy(child_egress2_link); + if (!IS_ERR(child_ingress_link)) + bpf_link__destroy(child_ingress_link); cg_storage_multi_isolated__destroy(obj); } @@ -367,12 +375,18 @@ static void test_shared(int parent_cgroup_fd, int child_cgroup_fd) goto close_bpf_object; close_bpf_object: - bpf_link__destroy(parent_egress1_link); - bpf_link__destroy(parent_egress2_link); - bpf_link__destroy(parent_ingress_link); - bpf_link__destroy(child_egress1_link); - bpf_link__destroy(child_egress2_link); - bpf_link__destroy(child_ingress_link); + if (!IS_ERR(parent_egress1_link)) + bpf_link__destroy(parent_egress1_link); + if (!IS_ERR(parent_egress2_link)) + bpf_link__destroy(parent_egress2_link); + if (!IS_ERR(parent_ingress_link)) + bpf_link__destroy(parent_ingress_link); + if (!IS_ERR(child_egress1_link)) + bpf_link__destroy(child_egress1_link); + if (!IS_ERR(child_egress2_link)) + bpf_link__destroy(child_egress2_link); + if (!IS_ERR(child_ingress_link)) + bpf_link__destroy(child_ingress_link); cg_storage_multi_shared__destroy(obj); } -- cgit v1.2.3 From a6599abdeac30063baf89df166068b20758e0e86 Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Thu, 30 Jul 2020 14:53:25 +0200 Subject: selftests/bpf: Omit nodad flag when adding addresses to loopback Setting IFA_F_NODAD flag for IPv6 addresses to add to loopback is unnecessary. Duplicate Address Detection does not happen on loopback device. Also, passing 'nodad' flag to 'ip address' breaks libbpf CI, which runs in an environment with BusyBox implementation of 'ip' command, that doesn't understand this flag. Fixes: 0ab5539f8584 ("selftests/bpf: Tests for BPF_SK_LOOKUP attach point") Reported-by: Andrii Nakryiko Signed-off-by: Jakub Sitnicki Signed-off-by: Daniel Borkmann Tested-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200730125325.1869363-1-jakub@cloudflare.com --- tools/testing/selftests/bpf/prog_tests/sk_lookup.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c index 9bbd2b2b7630..379da6f10ee9 100644 --- a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c +++ b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c @@ -1290,8 +1290,8 @@ static void run_tests(struct test_sk_lookup *skel) static int switch_netns(void) { static const char * const setup_script[] = { - "ip -6 addr add dev lo " EXT_IP6 "/128 nodad", - "ip -6 addr add dev lo " INT_IP6 "/128 nodad", + "ip -6 addr add dev lo " EXT_IP6 "/128", + "ip -6 addr add dev lo " INT_IP6 "/128", "ip link set dev lo up", NULL, }; -- cgit v1.2.3 From d3239425351a219ec779488ffb125352449c4106 Mon Sep 17 00:00:00 2001 From: Jian Yang Date: Mon, 27 Jul 2020 14:14:38 -0700 Subject: selftests: txtimestamp: add flag for timestamp validation tolerance. The txtimestamp selftest sets a fixed 500us tolerance. This value was arrived at experimentally. Some platforms have higher variances. Make this adjustable by adding the following flag: -t N: tolerance (usec) for timestamp validation. Signed-off-by: Jian Yang Acked-by: Willem de Bruijn Signed-off-by: David S. Miller --- tools/testing/selftests/net/txtimestamp.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/net/txtimestamp.c b/tools/testing/selftests/net/txtimestamp.c index 011b0da6b033..490a8cca708a 100644 --- a/tools/testing/selftests/net/txtimestamp.c +++ b/tools/testing/selftests/net/txtimestamp.c @@ -64,6 +64,7 @@ static int cfg_payload_len = 10; static int cfg_poll_timeout = 100; static int cfg_delay_snd; static int cfg_delay_ack; +static int cfg_delay_tolerance_usec = 500; static bool cfg_show_payload; static bool cfg_do_pktinfo; static bool cfg_busy_poll; @@ -152,11 +153,12 @@ static void validate_key(int tskey, int tstype) static void validate_timestamp(struct timespec *cur, int min_delay) { - int max_delay = min_delay + 500 /* processing time upper bound */; int64_t cur64, start64; + int max_delay; cur64 = timespec_to_us64(cur); start64 = timespec_to_us64(&ts_usr); + max_delay = min_delay + cfg_delay_tolerance_usec; if (cur64 < start64 + min_delay || cur64 > start64 + max_delay) { fprintf(stderr, "ERROR: %lu us expected between %d and %d\n", @@ -683,6 +685,7 @@ static void __attribute__((noreturn)) usage(const char *filepath) " -r: use raw\n" " -R: use raw (IP_HDRINCL)\n" " -S N: usec to sleep before reading error queue\n" + " -t N: tolerance (usec) for timestamp validation\n" " -u: use udp\n" " -v: validate SND delay (usec)\n" " -V: validate ACK delay (usec)\n" @@ -697,7 +700,7 @@ static void parse_opt(int argc, char **argv) int c; while ((c = getopt(argc, argv, - "46bc:CeEFhIl:LnNp:PrRS:uv:V:x")) != -1) { + "46bc:CeEFhIl:LnNp:PrRS:t:uv:V:x")) != -1) { switch (c) { case '4': do_ipv6 = 0; @@ -760,6 +763,9 @@ static void parse_opt(int argc, char **argv) case 'S': cfg_sleep_usec = strtoul(optarg, NULL, 10); break; + case 't': + cfg_delay_tolerance_usec = strtoul(optarg, NULL, 10); + break; case 'u': proto_count++; cfg_proto = SOCK_DGRAM; -- cgit v1.2.3 From fed61c4b584c5839543fe46a2ee55e21dd1bbf80 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 30 Jul 2020 21:25:57 +0200 Subject: selftests: mptcp: make 2nd net namespace use tcp syn cookies unconditionally check we can establish connections also when syn cookies are in use. Check that MPTcpExtMPCapableSYNRX and MPTcpExtMPCapableACKRX increase for each MPTCP test. Check TcpExtSyncookiesSent and TcpExtSyncookiesRecv increase in netns2. Signed-off-by: Florian Westphal Reviewed-by: Mat Martineau Signed-off-by: David S. Miller --- tools/testing/selftests/net/mptcp/mptcp_connect.sh | 47 ++++++++++++++++++++++ 1 file changed, 47 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index c0589e071f20..57d75b7f6220 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -196,6 +196,9 @@ ip -net "$ns4" link set ns4eth3 up ip -net "$ns4" route add default via 10.0.3.2 ip -net "$ns4" route add default via dead:beef:3::2 +# use TCP syn cookies, even if no flooding was detected. +ip netns exec "$ns2" sysctl -q net.ipv4.tcp_syncookies=2 + set_ethtool_flags() { local ns="$1" local dev="$2" @@ -407,6 +410,11 @@ do_transfer() sleep 1 fi + local stat_synrx_last_l=$(ip netns exec ${listener_ns} nstat -z -a MPTcpExtMPCapableSYNRX | while read a count c rest ;do echo $count;done) + local stat_ackrx_last_l=$(ip netns exec ${listener_ns} nstat -z -a MPTcpExtMPCapableACKRX | while read a count c rest ;do echo $count;done) + local stat_cookietx_last=$(ip netns exec ${listener_ns} nstat -z -a TcpExtSyncookiesSent | while read a count c rest ;do echo $count;done) + local stat_cookierx_last=$(ip netns exec ${listener_ns} nstat -z -a TcpExtSyncookiesRecv | while read a count c rest ;do echo $count;done) + ip netns exec ${listener_ns} ./mptcp_connect -t $timeout -l -p $port -s ${srv_proto} $extra_args $local_addr < "$sin" > "$sout" & local spid=$! @@ -450,6 +458,45 @@ do_transfer() check_transfer $cin $sout "file received by server" rets=$? + local stat_synrx_now_l=$(ip netns exec ${listener_ns} nstat -z -a MPTcpExtMPCapableSYNRX | while read a count c rest ;do echo $count;done) + local stat_ackrx_now_l=$(ip netns exec ${listener_ns} nstat -z -a MPTcpExtMPCapableACKRX | while read a count c rest ;do echo $count;done) + + local stat_cookietx_now=$(ip netns exec ${listener_ns} nstat -z -a TcpExtSyncookiesSent | while read a count c rest ;do echo $count;done) + local stat_cookierx_now=$(ip netns exec ${listener_ns} nstat -z -a TcpExtSyncookiesRecv | while read a count c rest ;do echo $count;done) + + expect_synrx=$((stat_synrx_last_l)) + expect_ackrx=$((stat_ackrx_last_l)) + + cookies=$(ip netns exec ${listener_ns} sysctl net.ipv4.tcp_syncookies) + cookies=${cookies##*=} + + if [ ${cl_proto} = "MPTCP" ] && [ ${srv_proto} = "MPTCP" ]; then + expect_synrx=$((stat_synrx_last_l+1)) + expect_ackrx=$((stat_ackrx_last_l+1)) + fi + if [ $cookies -eq 2 ];then + if [ $stat_cookietx_last -ge $stat_cookietx_now ] ;then + echo "${listener_ns} CookieSent: ${cl_proto} -> ${srv_proto}: did not advance" + fi + if [ $stat_cookierx_last -ge $stat_cookierx_now ] ;then + echo "${listener_ns} CookieRecv: ${cl_proto} -> ${srv_proto}: did not advance" + fi + else + if [ $stat_cookietx_last -ne $stat_cookietx_now ] ;then + echo "${listener_ns} CookieSent: ${cl_proto} -> ${srv_proto}: changed" + fi + if [ $stat_cookierx_last -ne $stat_cookierx_now ] ;then + echo "${listener_ns} CookieRecv: ${cl_proto} -> ${srv_proto}: changed" + fi + fi + + if [ $expect_synrx -ne $stat_synrx_now_l ] ;then + echo "${listener_ns} SYNRX: ${cl_proto} -> ${srv_proto}: expect ${expect_synrx}, got ${stat_synrx_now_l}" + fi + if [ $expect_ackrx -ne $stat_ackrx_now_l ] ;then + echo "${listener_ns} ACKRX: ${cl_proto} -> ${srv_proto}: expect ${expect_synrx}, got ${stat_synrx_now_l}" + fi + if [ $retc -eq 0 ] && [ $rets -eq 0 ];then echo "$duration [ OK ]" cat "$capout" -- cgit v1.2.3 From 00587187ad3016382bd8d3fad0f3bba0a518ab40 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 30 Jul 2020 21:25:58 +0200 Subject: selftests: mptcp: add test cases for mptcp join tests with syn cookies Also add test cases with MP_JOIN when tcp_syncookies sysctl is 2 (i.e., syncookies are always-on). While at it, also print the test number and add the test number to the pcap files that can be generated optionally. This makes it easier to match the pcap to the test case. Signed-off-by: Florian Westphal Reviewed-by: Mat Martineau Signed-off-by: David S. Miller --- tools/testing/selftests/net/mptcp/mptcp_join.sh | 66 ++++++++++++++++++++++++- 1 file changed, 64 insertions(+), 2 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index dd42c2f692d0..f39c1129ce5f 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -72,6 +72,15 @@ reset() init } +reset_with_cookies() +{ + reset + + for netns in "$ns1" "$ns2";do + ip netns exec $netns sysctl -q net.ipv4.tcp_syncookies=2 + done +} + for arg in "$@"; do if [ "$arg" = "-c" ]; then capture=1 @@ -138,7 +147,7 @@ do_transfer() capuser="-Z $SUDO_USER" fi - capfile="mp_join-${listener_ns}.pcap" + capfile=$(printf "mp_join-%02u-%s.pcap" "$TEST_COUNT" "${listener_ns}") echo "Capturing traffic for test $TEST_COUNT into $capfile" ip netns exec ${listener_ns} tcpdump -i any -s 65535 -B 32768 $capuser -w $capfile > "$capout" 2>&1 & @@ -227,7 +236,7 @@ chk_join_nr() local count local dump_stats - printf "%-36s %s" "$msg" "syn" + printf "%02u %-36s %s" "$TEST_COUNT" "$msg" "syn" count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinSynRx | awk '{print $2}'` [ -z "$count" ] && count=0 if [ "$count" != "$syn_nr" ]; then @@ -354,4 +363,57 @@ ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "multiple subflows and signal" 3 3 3 +# single subflow, syncookies +reset_with_cookies +ip netns exec $ns1 ./pm_nl_ctl limits 0 1 +ip netns exec $ns2 ./pm_nl_ctl limits 0 1 +ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow +run_tests $ns1 $ns2 10.0.1.1 +chk_join_nr "single subflow with syn cookies" 1 1 1 + +# multiple subflows with syn cookies +reset_with_cookies +ip netns exec $ns1 ./pm_nl_ctl limits 0 2 +ip netns exec $ns2 ./pm_nl_ctl limits 0 2 +ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow +ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow +run_tests $ns1 $ns2 10.0.1.1 +chk_join_nr "multiple subflows with syn cookies" 2 2 2 + +# multiple subflows limited by server +reset_with_cookies +ip netns exec $ns1 ./pm_nl_ctl limits 0 1 +ip netns exec $ns2 ./pm_nl_ctl limits 0 2 +ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow +ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow +run_tests $ns1 $ns2 10.0.1.1 +chk_join_nr "subflows limited by server w cookies" 2 2 1 + +# test signal address with cookies +reset_with_cookies +ip netns exec $ns1 ./pm_nl_ctl limits 0 1 +ip netns exec $ns2 ./pm_nl_ctl limits 1 1 +ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal +run_tests $ns1 $ns2 10.0.1.1 +chk_join_nr "signal address with syn cookies" 1 1 1 + +# test cookie with subflow and signal +reset_with_cookies +ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal +ip netns exec $ns1 ./pm_nl_ctl limits 0 2 +ip netns exec $ns2 ./pm_nl_ctl limits 1 2 +ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow +run_tests $ns1 $ns2 10.0.1.1 +chk_join_nr "subflow and signal w cookies" 2 2 2 + +# accept and use add_addr with additional subflows +reset_with_cookies +ip netns exec $ns1 ./pm_nl_ctl limits 0 3 +ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal +ip netns exec $ns2 ./pm_nl_ctl limits 1 3 +ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow +ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow +run_tests $ns1 $ns2 10.0.1.1 +chk_join_nr "subflows and signal w. cookies" 3 3 3 + exit $ret -- cgit v1.2.3 From 4939b2847d26c025e2e2118744226967f239a1ac Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 31 Jul 2020 15:09:14 -0700 Subject: bpf, selftests: Use single cgroup helpers for both test_sockmap/progs Nearly every user of cgroup helpers does the same sequence of API calls. So push these into a single helper cgroup_setup_and_join. The cases that do a bit of extra logic are test_progs which currently uses an env variable to decide if it needs to setup the cgroup environment or can use an existingi environment. And then tests that are doing cgroup tests themselves. We skip these cases for now. Signed-off-by: John Fastabend Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/159623335418.30208.15807461815525100199.stgit@john-XPS-13-9370 --- tools/testing/selftests/bpf/cgroup_helpers.c | 23 ++++++++++++++++++++++ tools/testing/selftests/bpf/cgroup_helpers.h | 1 + tools/testing/selftests/bpf/get_cgroup_id_user.c | 14 ++----------- tools/testing/selftests/bpf/test_cgroup_storage.c | 17 +--------------- tools/testing/selftests/bpf/test_dev_cgroup.c | 15 ++------------ tools/testing/selftests/bpf/test_netcnt.c | 17 ++-------------- .../selftests/bpf/test_skb_cgroup_id_user.c | 8 +------- tools/testing/selftests/bpf/test_sock.c | 8 +------- tools/testing/selftests/bpf/test_sock_addr.c | 8 +------- tools/testing/selftests/bpf/test_sock_fields.c | 14 +++---------- tools/testing/selftests/bpf/test_socket_cookie.c | 8 +------- tools/testing/selftests/bpf/test_sockmap.c | 18 ++--------------- tools/testing/selftests/bpf/test_sysctl.c | 8 +------- tools/testing/selftests/bpf/test_tcpbpf_user.c | 8 +------- tools/testing/selftests/bpf/test_tcpnotify_user.c | 8 +------- 15 files changed, 43 insertions(+), 132 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c index 0fb910df5387..033051717ba5 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.c +++ b/tools/testing/selftests/bpf/cgroup_helpers.c @@ -290,3 +290,26 @@ free_mem: free(fhp); return ret; } + +int cgroup_setup_and_join(const char *path) { + int cg_fd; + + if (setup_cgroup_environment()) { + fprintf(stderr, "Failed to setup cgroup environment\n"); + return -EINVAL; + } + + cg_fd = create_and_get_cgroup(path); + if (cg_fd < 0) { + fprintf(stderr, "Failed to create test cgroup\n"); + cleanup_cgroup_environment(); + return cg_fd; + } + + if (join_cgroup(path)) { + fprintf(stderr, "Failed to join cgroup\n"); + cleanup_cgroup_environment(); + return -EINVAL; + } + return cg_fd; +} diff --git a/tools/testing/selftests/bpf/cgroup_helpers.h b/tools/testing/selftests/bpf/cgroup_helpers.h index d64bb8957090..5fe3d88e4f0d 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.h +++ b/tools/testing/selftests/bpf/cgroup_helpers.h @@ -9,6 +9,7 @@ __FILE__, __LINE__, clean_errno(), ##__VA_ARGS__) +int cgroup_setup_and_join(const char *path); int create_and_get_cgroup(const char *path); int join_cgroup(const char *path); int setup_cgroup_environment(void); diff --git a/tools/testing/selftests/bpf/get_cgroup_id_user.c b/tools/testing/selftests/bpf/get_cgroup_id_user.c index e8da7b39158d..b8d6aef99db4 100644 --- a/tools/testing/selftests/bpf/get_cgroup_id_user.c +++ b/tools/testing/selftests/bpf/get_cgroup_id_user.c @@ -58,20 +58,10 @@ int main(int argc, char **argv) int exit_code = 1; char buf[256]; - err = setup_cgroup_environment(); - if (CHECK(err, "setup_cgroup_environment", "err %d errno %d\n", err, - errno)) + cgroup_fd = cgroup_setup_and_join(TEST_CGROUP); + if (CHECK(cgroup_fd < 0, "cgroup_setup_and_join", "err %d errno %d\n", cgroup_fd, errno)) return 1; - cgroup_fd = create_and_get_cgroup(TEST_CGROUP); - if (CHECK(cgroup_fd < 0, "create_and_get_cgroup", "err %d errno %d\n", - cgroup_fd, errno)) - goto cleanup_cgroup_env; - - err = join_cgroup(TEST_CGROUP); - if (CHECK(err, "join_cgroup", "err %d errno %d\n", err, errno)) - goto cleanup_cgroup_env; - err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd); if (CHECK(err, "bpf_prog_load", "err %d errno %d\n", err, errno)) goto cleanup_cgroup_env; diff --git a/tools/testing/selftests/bpf/test_cgroup_storage.c b/tools/testing/selftests/bpf/test_cgroup_storage.c index 655729004391..d946252a25bb 100644 --- a/tools/testing/selftests/bpf/test_cgroup_storage.c +++ b/tools/testing/selftests/bpf/test_cgroup_storage.c @@ -74,22 +74,7 @@ int main(int argc, char **argv) goto out; } - if (setup_cgroup_environment()) { - printf("Failed to setup cgroup environment\n"); - goto err; - } - - /* Create a cgroup, get fd, and join it */ - cgroup_fd = create_and_get_cgroup(TEST_CGROUP); - if (cgroup_fd < 0) { - printf("Failed to create test cgroup\n"); - goto err; - } - - if (join_cgroup(TEST_CGROUP)) { - printf("Failed to join cgroup\n"); - goto err; - } + cgroup_fd = cgroup_setup_and_join(TEST_CGROUP); /* Attach the bpf program */ if (bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_INET_EGRESS, 0)) { diff --git a/tools/testing/selftests/bpf/test_dev_cgroup.c b/tools/testing/selftests/bpf/test_dev_cgroup.c index d850fb9076b5..804dddd97d4c 100644 --- a/tools/testing/selftests/bpf/test_dev_cgroup.c +++ b/tools/testing/selftests/bpf/test_dev_cgroup.c @@ -33,21 +33,10 @@ int main(int argc, char **argv) goto out; } - if (setup_cgroup_environment()) { - printf("Failed to load DEV_CGROUP program\n"); - goto err; - } - - /* Create a cgroup, get fd, and join it */ - cgroup_fd = create_and_get_cgroup(TEST_CGROUP); + cgroup_fd = cgroup_setup_and_join(TEST_CGROUP); if (cgroup_fd < 0) { printf("Failed to create test cgroup\n"); - goto err; - } - - if (join_cgroup(TEST_CGROUP)) { - printf("Failed to join cgroup\n"); - goto err; + goto out; } /* Attach bpf program */ diff --git a/tools/testing/selftests/bpf/test_netcnt.c b/tools/testing/selftests/bpf/test_netcnt.c index 7a68c9069639..a7b9a69f4fd5 100644 --- a/tools/testing/selftests/bpf/test_netcnt.c +++ b/tools/testing/selftests/bpf/test_netcnt.c @@ -58,22 +58,9 @@ int main(int argc, char **argv) goto out; } - if (setup_cgroup_environment()) { - printf("Failed to load bpf program\n"); - goto err; - } - - /* Create a cgroup, get fd, and join it */ - cgroup_fd = create_and_get_cgroup(TEST_CGROUP); - if (cgroup_fd < 0) { - printf("Failed to create test cgroup\n"); + cgroup_fd = cgroup_setup_and_join(TEST_CGROUP); + if (cgroup_fd < 0) goto err; - } - - if (join_cgroup(TEST_CGROUP)) { - printf("Failed to join cgroup\n"); - goto err; - } /* Attach bpf program */ if (bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_INET_EGRESS, 0)) { 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 356351c0ac28..4a64306728ab 100644 --- a/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c +++ b/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c @@ -160,16 +160,10 @@ int main(int argc, char **argv) exit(EXIT_FAILURE); } - if (setup_cgroup_environment()) - goto err; - - cgfd = create_and_get_cgroup(CGROUP_PATH); + cgfd = cgroup_setup_and_join(CGROUP_PATH); if (cgfd < 0) goto err; - if (join_cgroup(CGROUP_PATH)) - goto err; - if (send_packet(argv[1])) goto err; diff --git a/tools/testing/selftests/bpf/test_sock.c b/tools/testing/selftests/bpf/test_sock.c index 52bf14955797..9613f7538840 100644 --- a/tools/testing/selftests/bpf/test_sock.c +++ b/tools/testing/selftests/bpf/test_sock.c @@ -464,16 +464,10 @@ int main(int argc, char **argv) int cgfd = -1; int err = 0; - if (setup_cgroup_environment()) - goto err; - - cgfd = create_and_get_cgroup(CG_PATH); + cgfd = cgroup_setup_and_join(CG_PATH); if (cgfd < 0) goto err; - if (join_cgroup(CG_PATH)) - goto err; - if (run_tests(cgfd)) goto err; diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c index 0358814c67dc..b8c72c1d9cf7 100644 --- a/tools/testing/selftests/bpf/test_sock_addr.c +++ b/tools/testing/selftests/bpf/test_sock_addr.c @@ -1638,16 +1638,10 @@ int main(int argc, char **argv) exit(err); } - if (setup_cgroup_environment()) - goto err; - - cgfd = create_and_get_cgroup(CG_PATH); + cgfd = cgroup_setup_and_join(CG_PATH); if (cgfd < 0) goto err; - if (join_cgroup(CG_PATH)) - goto err; - if (run_tests(cgfd)) goto err; diff --git a/tools/testing/selftests/bpf/test_sock_fields.c b/tools/testing/selftests/bpf/test_sock_fields.c index f0fc103261a4..6c9f269c396d 100644 --- a/tools/testing/selftests/bpf/test_sock_fields.c +++ b/tools/testing/selftests/bpf/test_sock_fields.c @@ -421,19 +421,11 @@ int main(int argc, char **argv) struct bpf_object *obj; struct bpf_map *map; - err = setup_cgroup_environment(); - CHECK(err, "setup_cgroup_environment()", "err:%d errno:%d", - err, errno); - - atexit(cleanup_cgroup_environment); - /* Create a cgroup, get fd, and join it */ - cgroup_fd = create_and_get_cgroup(TEST_CGROUP); - CHECK(cgroup_fd == -1, "create_and_get_cgroup()", + cgroup_fd = cgroup_setup_and_join(TEST_CGROUP); + CHECK(cgroup_fd < 0, "cgroup_setup_and_join()", "cgroup_fd:%d errno:%d", cgroup_fd, errno); - - err = join_cgroup(TEST_CGROUP); - CHECK(err, "join_cgroup", "err:%d errno:%d", err, errno); + atexit(cleanup_cgroup_environment); err = bpf_prog_load_xattr(&attr, &obj, &egress_fd); CHECK(err, "bpf_prog_load_xattr()", "err:%d", err); diff --git a/tools/testing/selftests/bpf/test_socket_cookie.c b/tools/testing/selftests/bpf/test_socket_cookie.c index 15653b0e26eb..154a8fd2a48d 100644 --- a/tools/testing/selftests/bpf/test_socket_cookie.c +++ b/tools/testing/selftests/bpf/test_socket_cookie.c @@ -191,16 +191,10 @@ int main(int argc, char **argv) int cgfd = -1; int err = 0; - if (setup_cgroup_environment()) - goto err; - - cgfd = create_and_get_cgroup(CG_PATH); + cgfd = cgroup_setup_and_join(CG_PATH); if (cgfd < 0) goto err; - if (join_cgroup(CG_PATH)) - goto err; - if (run_test(cgfd)) goto err; diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index 78789b27e573..9b6fb00dc7a0 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -1963,23 +1963,9 @@ int main(int argc, char **argv) } if (!cg_fd) { - if (setup_cgroup_environment()) { - fprintf(stderr, "ERROR: cgroup env failed\n"); - return -EINVAL; - } - - cg_fd = create_and_get_cgroup(CG_PATH); - if (cg_fd < 0) { - fprintf(stderr, - "ERROR: (%i) open cg path failed: %s\n", - cg_fd, strerror(errno)); + cg_fd = cgroup_setup_and_join(CG_PATH); + if (cg_fd < 0) return cg_fd; - } - - if (join_cgroup(CG_PATH)) { - fprintf(stderr, "ERROR: failed to join cgroup\n"); - return -EINVAL; - } cg_created = 1; } diff --git a/tools/testing/selftests/bpf/test_sysctl.c b/tools/testing/selftests/bpf/test_sysctl.c index d196e2a4a6e0..a20a919244c0 100644 --- a/tools/testing/selftests/bpf/test_sysctl.c +++ b/tools/testing/selftests/bpf/test_sysctl.c @@ -1619,16 +1619,10 @@ int main(int argc, char **argv) int cgfd = -1; int err = 0; - if (setup_cgroup_environment()) - goto err; - - cgfd = create_and_get_cgroup(CG_PATH); + cgfd = cgroup_setup_and_join(CG_PATH); if (cgfd < 0) goto err; - if (join_cgroup(CG_PATH)) - goto err; - if (run_tests(cgfd)) goto err; diff --git a/tools/testing/selftests/bpf/test_tcpbpf_user.c b/tools/testing/selftests/bpf/test_tcpbpf_user.c index 3ae127620463..74a9e49988b6 100644 --- a/tools/testing/selftests/bpf/test_tcpbpf_user.c +++ b/tools/testing/selftests/bpf/test_tcpbpf_user.c @@ -102,16 +102,10 @@ int main(int argc, char **argv) __u32 key = 0; int rv; - if (setup_cgroup_environment()) - goto err; - - cg_fd = create_and_get_cgroup(cg_path); + cg_fd = cgroup_setup_and_join(cg_path); if (cg_fd < 0) goto err; - if (join_cgroup(cg_path)) - goto err; - if (bpf_prog_load(file, BPF_PROG_TYPE_SOCK_OPS, &obj, &prog_fd)) { printf("FAILED: load_bpf_file failed for: %s\n", file); goto err; diff --git a/tools/testing/selftests/bpf/test_tcpnotify_user.c b/tools/testing/selftests/bpf/test_tcpnotify_user.c index f9765ddf0761..8549b31716ab 100644 --- a/tools/testing/selftests/bpf/test_tcpnotify_user.c +++ b/tools/testing/selftests/bpf/test_tcpnotify_user.c @@ -86,16 +86,10 @@ int main(int argc, char **argv) CPU_SET(0, &cpuset); pthread_setaffinity_np(pthread_self(), sizeof(cpu_set_t), &cpuset); - if (setup_cgroup_environment()) - goto err; - - cg_fd = create_and_get_cgroup(cg_path); + cg_fd = cgroup_setup_and_join(cg_path); if (cg_fd < 0) goto err; - if (join_cgroup(cg_path)) - goto err; - if (bpf_prog_load(file, BPF_PROG_TYPE_SOCK_OPS, &obj, &prog_fd)) { printf("FAILED: load_bpf_file failed for: %s\n", file); goto err; -- cgit v1.2.3 From 90806ccc90bbd0150267a97ae4003269597a6a6c Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 31 Jul 2020 11:28:28 -0700 Subject: selftests/bpf: Add link detach tests for cgroup, netns, and xdp bpf_links Add bpf_link__detach() testing to selftests for cgroup, netns, and xdp bpf_links. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20200731182830.286260-4-andriin@fb.com --- .../testing/selftests/bpf/prog_tests/cgroup_link.c | 20 ++++++++- tools/testing/selftests/bpf/prog_tests/sk_lookup.c | 51 ++++++++++------------ tools/testing/selftests/bpf/prog_tests/xdp_link.c | 14 ++++++ tools/testing/selftests/bpf/testing_helpers.c | 14 ++++++ tools/testing/selftests/bpf/testing_helpers.h | 3 ++ 5 files changed, 73 insertions(+), 29 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_link.c b/tools/testing/selftests/bpf/prog_tests/cgroup_link.c index 6e04f8d1d15b..4d9b514b3fd9 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_link.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_link.c @@ -2,6 +2,7 @@ #include #include "cgroup_helpers.h" +#include "testing_helpers.h" #include "test_cgroup_link.skel.h" static __u32 duration = 0; @@ -37,7 +38,8 @@ void test_cgroup_link(void) int last_cg = ARRAY_SIZE(cgs) - 1, cg_nr = ARRAY_SIZE(cgs); DECLARE_LIBBPF_OPTS(bpf_link_update_opts, link_upd_opts); struct bpf_link *links[ARRAY_SIZE(cgs)] = {}, *tmp_link; - __u32 prog_ids[ARRAY_SIZE(cgs)], prog_cnt = 0, attach_flags; + __u32 prog_ids[ARRAY_SIZE(cgs)], prog_cnt = 0, attach_flags, prog_id; + struct bpf_link_info info; int i = 0, err, prog_fd; bool detach_legacy = false; @@ -219,6 +221,22 @@ void test_cgroup_link(void) /* BPF programs should still get called */ ping_and_check(0, cg_nr); + prog_id = link_info_prog_id(links[0], &info); + CHECK(prog_id == 0, "link_info", "failed\n"); + CHECK(info.cgroup.cgroup_id == 0, "cgroup_id", "unexpected %llu\n", info.cgroup.cgroup_id); + + err = bpf_link__detach(links[0]); + if (CHECK(err, "link_detach", "failed %d\n", err)) + goto cleanup; + + /* cgroup_id should be zero in link_info */ + prog_id = link_info_prog_id(links[0], &info); + CHECK(prog_id == 0, "link_info", "failed\n"); + CHECK(info.cgroup.cgroup_id != 0, "cgroup_id", "unexpected %llu\n", info.cgroup.cgroup_id); + + /* First BPF program shouldn't be called anymore */ + ping_and_check(0, cg_nr - 1); + /* leave cgroup and remove them, don't detach programs */ cleanup_cgroup_environment(); diff --git a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c index 379da6f10ee9..c571584c00f5 100644 --- a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c +++ b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c @@ -34,6 +34,7 @@ #include "bpf_util.h" #include "cgroup_helpers.h" #include "network_helpers.h" +#include "testing_helpers.h" #include "test_sk_lookup.skel.h" /* External (address, port) pairs the client sends packets to. */ @@ -469,34 +470,10 @@ static int update_lookup_map(struct bpf_map *map, int index, int sock_fd) return 0; } -static __u32 link_info_prog_id(struct bpf_link *link) -{ - struct bpf_link_info info = {}; - __u32 info_len = sizeof(info); - int link_fd, err; - - link_fd = bpf_link__fd(link); - if (CHECK(link_fd < 0, "bpf_link__fd", "failed\n")) { - errno = -link_fd; - log_err("bpf_link__fd failed"); - return 0; - } - - err = bpf_obj_get_info_by_fd(link_fd, &info, &info_len); - if (CHECK(err, "bpf_obj_get_info_by_fd", "failed\n")) { - log_err("bpf_obj_get_info_by_fd"); - return 0; - } - if (CHECK(info_len != sizeof(info), "bpf_obj_get_info_by_fd", - "unexpected info len %u\n", info_len)) - return 0; - - return info.prog_id; -} - static void query_lookup_prog(struct test_sk_lookup *skel) { struct bpf_link *link[3] = {}; + struct bpf_link_info info; __u32 attach_flags = 0; __u32 prog_ids[3] = {}; __u32 prog_cnt = 3; @@ -534,18 +511,36 @@ static void query_lookup_prog(struct test_sk_lookup *skel) if (CHECK(prog_cnt != 3, "bpf_prog_query", "wrong program count on query: %u", prog_cnt)) goto detach; - prog_id = link_info_prog_id(link[0]); + prog_id = link_info_prog_id(link[0], &info); CHECK(prog_ids[0] != prog_id, "bpf_prog_query", "invalid program #0 id on query: %u != %u\n", prog_ids[0], prog_id); - prog_id = link_info_prog_id(link[1]); + CHECK(info.netns.netns_ino == 0, "netns_ino", + "unexpected netns_ino: %u\n", info.netns.netns_ino); + prog_id = link_info_prog_id(link[1], &info); CHECK(prog_ids[1] != prog_id, "bpf_prog_query", "invalid program #1 id on query: %u != %u\n", prog_ids[1], prog_id); - prog_id = link_info_prog_id(link[2]); + CHECK(info.netns.netns_ino == 0, "netns_ino", + "unexpected netns_ino: %u\n", info.netns.netns_ino); + prog_id = link_info_prog_id(link[2], &info); CHECK(prog_ids[2] != prog_id, "bpf_prog_query", "invalid program #2 id on query: %u != %u\n", prog_ids[2], prog_id); + CHECK(info.netns.netns_ino == 0, "netns_ino", + "unexpected netns_ino: %u\n", info.netns.netns_ino); + + err = bpf_link__detach(link[0]); + if (CHECK(err, "link_detach", "failed %d\n", err)) + goto detach; + + /* prog id is still there, but netns_ino is zeroed out */ + prog_id = link_info_prog_id(link[0], &info); + CHECK(prog_ids[0] != prog_id, "bpf_prog_query", + "invalid program #0 id on query: %u != %u\n", + prog_ids[0], prog_id); + CHECK(info.netns.netns_ino != 0, "netns_ino", + "unexpected netns_ino: %u\n", info.netns.netns_ino); detach: if (link[2]) diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_link.c b/tools/testing/selftests/bpf/prog_tests/xdp_link.c index 52cba6795d40..6f814999b395 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_link.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_link.c @@ -131,6 +131,20 @@ void test_xdp_link(void) CHECK(link_info.xdp.ifindex != IFINDEX_LO, "link_ifindex", "got %u != exp %u\n", link_info.xdp.ifindex, IFINDEX_LO); + err = bpf_link__detach(link); + if (CHECK(err, "link_detach", "failed %d\n", err)) + goto cleanup; + + memset(&link_info, 0, sizeof(link_info)); + err = bpf_obj_get_info_by_fd(bpf_link__fd(link), &link_info, &link_info_len); + if (CHECK(err, "link_info", "failed: %d\n", err)) + goto cleanup; + CHECK(link_info.prog_id != id1, "link_prog_id", + "got %u != exp %u\n", link_info.prog_id, id1); + /* ifindex should be zeroed out */ + CHECK(link_info.xdp.ifindex != 0, "link_ifindex", + "got %u != exp %u\n", link_info.xdp.ifindex, 0); + cleanup: test_xdp_link__destroy(skel1); test_xdp_link__destroy(skel2); diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c index 0af6337a8962..800d503e5cb4 100644 --- a/tools/testing/selftests/bpf/testing_helpers.c +++ b/tools/testing/selftests/bpf/testing_helpers.c @@ -64,3 +64,17 @@ int parse_num_list(const char *s, bool **num_set, int *num_set_len) return 0; } + +__u32 link_info_prog_id(const struct bpf_link *link, struct bpf_link_info *info) +{ + __u32 info_len = sizeof(*info); + int err; + + memset(info, 0, sizeof(*info)); + err = bpf_obj_get_info_by_fd(bpf_link__fd(link), info, &info_len); + if (err) { + printf("failed to get link info: %d\n", -errno); + return 0; + } + return info->prog_id; +} diff --git a/tools/testing/selftests/bpf/testing_helpers.h b/tools/testing/selftests/bpf/testing_helpers.h index 923b51762759..d4f8e749611b 100644 --- a/tools/testing/selftests/bpf/testing_helpers.h +++ b/tools/testing/selftests/bpf/testing_helpers.h @@ -1,5 +1,8 @@ /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ /* Copyright (C) 2020 Facebook, Inc. */ #include +#include +#include int parse_num_list(const char *s, bool **set, int *set_len); +__u32 link_info_prog_id(const struct bpf_link *link, struct bpf_link_info *info); -- cgit v1.2.3 From b5cc46cdff76cdfe2cb45ab2636d847efb1012cc Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 31 Jul 2020 13:49:57 -0700 Subject: selftests/bpf: Fix spurious test failures in core_retro selftest core_retro selftest uses BPF program that's triggered on sys_enter system-wide, but has no protection from some unrelated process doing syscall while selftest is running. This leads to occasional test failures with unexpected PIDs being returned. Fix that by filtering out all processes that are not test_progs process. Fixes: fcda189a5133 ("selftests/bpf: Add test relying only on CO-RE and no recent kernel features") Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20200731204957.2047119-1-andriin@fb.com --- tools/testing/selftests/bpf/prog_tests/core_retro.c | 8 ++++++-- tools/testing/selftests/bpf/progs/test_core_retro.c | 13 +++++++++++++ 2 files changed, 19 insertions(+), 2 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/bpf/prog_tests/core_retro.c b/tools/testing/selftests/bpf/prog_tests/core_retro.c index 78e30d3a23d5..6acb0e94d4d7 100644 --- a/tools/testing/selftests/bpf/prog_tests/core_retro.c +++ b/tools/testing/selftests/bpf/prog_tests/core_retro.c @@ -6,7 +6,7 @@ void test_core_retro(void) { - int err, zero = 0, res, duration = 0; + int err, zero = 0, res, duration = 0, my_pid = getpid(); struct test_core_retro *skel; /* load program */ @@ -14,6 +14,10 @@ void test_core_retro(void) if (CHECK(!skel, "skel_load", "skeleton open/load failed\n")) goto out_close; + err = bpf_map_update_elem(bpf_map__fd(skel->maps.exp_tgid_map), &zero, &my_pid, 0); + if (CHECK(err, "map_update", "failed to set expected PID: %d\n", errno)) + goto out_close; + /* attach probe */ err = test_core_retro__attach(skel); if (CHECK(err, "attach_kprobe", "err %d\n", err)) @@ -26,7 +30,7 @@ void test_core_retro(void) if (CHECK(err, "map_lookup", "failed to lookup result: %d\n", errno)) goto out_close; - CHECK(res != getpid(), "pid_check", "got %d != exp %d\n", res, getpid()); + CHECK(res != my_pid, "pid_check", "got %d != exp %d\n", res, my_pid); out_close: test_core_retro__destroy(skel); diff --git a/tools/testing/selftests/bpf/progs/test_core_retro.c b/tools/testing/selftests/bpf/progs/test_core_retro.c index 75c60c3c29cf..20861ec2f674 100644 --- a/tools/testing/selftests/bpf/progs/test_core_retro.c +++ b/tools/testing/selftests/bpf/progs/test_core_retro.c @@ -8,6 +8,13 @@ struct task_struct { int tgid; } __attribute__((preserve_access_index)); +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} exp_tgid_map SEC(".maps"); + struct { __uint(type, BPF_MAP_TYPE_ARRAY); __uint(max_entries, 1); @@ -21,6 +28,12 @@ int handle_sys_enter(void *ctx) struct task_struct *task = (void *)bpf_get_current_task(); int tgid = BPF_CORE_READ(task, tgid); int zero = 0; + int real_tgid = bpf_get_current_pid_tgid() >> 32; + int *exp_tgid = bpf_map_lookup_elem(&exp_tgid_map, &zero); + + /* only pass through sys_enters from test process */ + if (!exp_tgid || *exp_tgid != real_tgid) + return 0; bpf_map_update_elem(&results, &zero, &tgid, 0); -- cgit v1.2.3 From 2ef740da4fef947fb4614808fb61ca8ccb313e0b Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sun, 2 Aug 2020 03:26:21 +0200 Subject: selftests: netfilter: add meta iif/oif match test simple test case, but would have caught this: FAIL: iifgroupcount, want "packets 2", got table inet filter { counter iifgroupcount { packets 0 bytes 0 } } Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- tools/testing/selftests/netfilter/Makefile | 2 +- tools/testing/selftests/netfilter/nft_meta.sh | 124 ++++++++++++++++++++++++++ 2 files changed, 125 insertions(+), 1 deletion(-) create mode 100755 tools/testing/selftests/netfilter/nft_meta.sh (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index a179f0dca8ce..a374e10ef506 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -4,7 +4,7 @@ TEST_PROGS := nft_trans_stress.sh nft_nat.sh bridge_brouter.sh \ conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \ nft_concat_range.sh nft_conntrack_helper.sh \ - nft_queue.sh + nft_queue.sh nft_meta.sh LDLIBS = -lmnl TEST_GEN_FILES = nf-queue diff --git a/tools/testing/selftests/netfilter/nft_meta.sh b/tools/testing/selftests/netfilter/nft_meta.sh new file mode 100755 index 000000000000..d250b84dd5bc --- /dev/null +++ b/tools/testing/selftests/netfilter/nft_meta.sh @@ -0,0 +1,124 @@ +#!/bin/bash + +# check iif/iifname/oifgroup/iiftype match. + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 +sfx=$(mktemp -u "XXXXXXXX") +ns0="ns0-$sfx" + +nft --version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without nft tool" + exit $ksft_skip +fi + +cleanup() +{ + ip netns del "$ns0" +} + +ip netns add "$ns0" +ip -net "$ns0" link set lo up +ip -net "$ns0" addr add 127.0.0.1 dev lo + +trap cleanup EXIT + +ip netns exec "$ns0" nft -f /dev/stdin < /dev/null + +check_lo_counters "2" true + +check_one_counter oskuidcounter "1" true +check_one_counter oskgidcounter "1" true +check_one_counter imarkcounter "1" true +check_one_counter omarkcounter "1" true + +if [ $ret -eq 0 ];then + echo "OK: nftables meta iif/oif counters at expected values" +fi + +exit $ret -- cgit v1.2.3 From 21594c44083c375697d418729c4b2e4522cf9f70 Mon Sep 17 00:00:00 2001 From: Dmitry Yakunin Date: Mon, 3 Aug 2020 12:05:45 +0300 Subject: bpf: Allow to specify ifindex for skb in bpf_prog_test_run_skb Now skb->dev is unconditionally set to the loopback device in current net namespace. But if we want to test bpf program which contains code branch based on ifindex condition (eg filters out localhost packets) it is useful to allow specifying of ifindex from userspace. This patch adds such option through ctx_in (__sk_buff) parameter. Signed-off-by: Dmitry Yakunin Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20200803090545.82046-3-zeil@yandex-team.ru --- net/bpf/test_run.c | 22 ++++++++++++++++++++-- tools/testing/selftests/bpf/prog_tests/skb_ctx.c | 5 +++++ 2 files changed, 25 insertions(+), 2 deletions(-) (limited to 'tools/testing/selftests') diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 736a5964fa95..99eb8c6c0fbc 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -327,6 +327,12 @@ static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb) /* priority is allowed */ if (!range_is_zero(__skb, offsetofend(struct __sk_buff, priority), + offsetof(struct __sk_buff, ifindex))) + return -EINVAL; + + /* ifindex is allowed */ + + if (!range_is_zero(__skb, offsetofend(struct __sk_buff, ifindex), offsetof(struct __sk_buff, cb))) return -EINVAL; @@ -381,6 +387,7 @@ static void convert_skb_to___skb(struct sk_buff *skb, struct __sk_buff *__skb) __skb->mark = skb->mark; __skb->priority = skb->priority; + __skb->ifindex = skb->dev->ifindex; __skb->tstamp = skb->tstamp; memcpy(__skb->cb, &cb->data, QDISC_CB_PRIV_LEN); __skb->wire_len = cb->pkt_len; @@ -391,6 +398,8 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { bool is_l2 = false, is_direct_pkt_access = false; + struct net *net = current->nsproxy->net_ns; + struct net_device *dev = net->loopback_dev; u32 size = kattr->test.data_size_in; u32 repeat = kattr->test.repeat; struct __sk_buff *ctx = NULL; @@ -432,7 +441,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, kfree(ctx); return -ENOMEM; } - sock_net_set(sk, current->nsproxy->net_ns); + sock_net_set(sk, net); sock_init_data(NULL, sk); skb = build_skb(data, 0); @@ -446,7 +455,14 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); __skb_put(skb, size); - skb->protocol = eth_type_trans(skb, current->nsproxy->net_ns->loopback_dev); + if (ctx && ctx->ifindex > 1) { + dev = dev_get_by_index(net, ctx->ifindex); + if (!dev) { + ret = -ENODEV; + goto out; + } + } + skb->protocol = eth_type_trans(skb, dev); skb_reset_network_header(skb); switch (skb->protocol) { @@ -502,6 +518,8 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, ret = bpf_ctx_finish(kattr, uattr, ctx, sizeof(struct __sk_buff)); out: + if (dev && dev != net->loopback_dev) + dev_put(dev); kfree_skb(skb); bpf_sk_storage_free(sk); kfree(sk); diff --git a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c index 7021b92af313..25de86af2d03 100644 --- a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c +++ b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c @@ -11,6 +11,7 @@ void test_skb_ctx(void) .cb[3] = 4, .cb[4] = 5, .priority = 6, + .ifindex = 1, .tstamp = 7, .wire_len = 100, .gso_segs = 8, @@ -92,6 +93,10 @@ void test_skb_ctx(void) "ctx_out_priority", "skb->priority == %d, expected %d\n", skb.priority, 7); + CHECK_ATTR(skb.ifindex != 1, + "ctx_out_ifindex", + "skb->ifindex == %d, expected %d\n", + skb.ifindex, 1); CHECK_ATTR(skb.tstamp != 8, "ctx_out_tstamp", "skb->tstamp == %lld, expected %d\n", -- cgit v1.2.3 From 8fb6ac457d5be8516eeed2b92342f7f95c448275 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Mon, 3 Aug 2020 19:11:41 +0300 Subject: selftests: mlxsw: RED: Test offload of trapping on RED qevents Add a selftest for RED early_drop and mark qevents when a trap action is attached at the associated block. Signed-off-by: Petr Machata Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- .../selftests/drivers/net/mlxsw/sch_red_core.sh | 35 ++++++++++++++++++---- .../selftests/drivers/net/mlxsw/sch_red_ets.sh | 11 +++++++ 2 files changed, 40 insertions(+), 6 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh index 45042105ead7..517297a14ecf 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh @@ -568,17 +568,12 @@ do_drop_test() busywait 1100 until_counter_is ">= $((base + 1))" $fetch_counter >/dev/null check_fail $? "Spurious packets observed without buffer pressure" - qevent_rule_uninstall_$subtest - # Push to the queue until it's at the limit. The configured limit is # rounded by the qdisc and then by the driver, so this is the best we - # can do to get to the real limit of the system. Do this with the rules - # uninstalled so that the inevitable drops don't get counted. + # can do to get to the real limit of the system. build_backlog $vlan $((3 * limit / 2)) udp >/dev/null - qevent_rule_install_$subtest base=$($fetch_counter) - send_packets $vlan udp 11 now=$(busywait 1100 until_counter_is ">= $((base + 10))" $fetch_counter) @@ -631,3 +626,31 @@ do_drop_mirror_test() tc filter del dev $h2 ingress pref 1 handle 101 flower } + +qevent_rule_install_trap() +{ + tc filter add block 10 pref 1234 handle 102 matchall skip_sw \ + action trap hw_stats disabled +} + +qevent_rule_uninstall_trap() +{ + tc filter del block 10 pref 1234 handle 102 matchall +} + +qevent_counter_fetch_trap() +{ + local trap_name=$1; shift + + devlink_trap_rx_packets_get "$trap_name" +} + +do_drop_trap_test() +{ + local vlan=$1; shift + local limit=$1; shift + local trap_name=$1; shift + + do_drop_test "$vlan" "$limit" "$trap_name" trap \ + "qevent_counter_fetch_trap $trap_name" +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh index c8968b041bea..3f007c5f8361 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh @@ -8,6 +8,7 @@ ALL_TESTS=" red_test mc_backlog_test red_mirror_test + red_trap_test " : ${QDISC:=ets} source sch_red_core.sh @@ -94,6 +95,16 @@ red_mirror_test() uninstall_qdisc } +red_trap_test() +{ + install_qdisc qevent early_drop block 10 + + do_drop_trap_test 10 $BACKLOG1 early_drop + do_drop_trap_test 11 $BACKLOG2 early_drop + + uninstall_qdisc +} + trap cleanup EXIT setup_prepare -- cgit v1.2.3 From df40e39c0df025da38dd819152a877a07ab1c115 Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Tue, 4 Aug 2020 07:53:46 +0200 Subject: selftests: pmtu.sh: Add tests for bridged UDP tunnels The new tests check that IP and IPv6 packets exceeding the local PMTU estimate, both locally generated and forwarded by a bridge from another node, result in the correct route exceptions being created, and that communication with end-to-end fragmentation over VXLAN and GENEVE tunnels is now possible as a result of PMTU discovery. Part of the existing setup functions aren't generic enough to simply add a namespace and a bridge to the existing routing setup. This rework is in progress and we can easily shrink this once more generic topology functions are available. Signed-off-by: Stefano Brivio Reviewed-by: David Ahern Signed-off-by: David S. Miller --- tools/testing/selftests/net/pmtu.sh | 166 ++++++++++++++++++++++++++++++++++-- 1 file changed, 159 insertions(+), 7 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 77c09cd339c3..774e526573f3 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -59,6 +59,25 @@ # Same as pmtu_ipv6_vxlan6_exception, but using a GENEVE tunnel instead of # VXLAN # +# - pmtu_ipv{4,6}_br_vxlan{4,6}_exception +# Set up three namespaces, A, B, and C, with routing between A and B over +# R1. R2 is unused in these tests. A has a veth connection to C, and is +# connected to B via a VXLAN endpoint, which is directly bridged to C. +# MTU on the B-R1 link is lower than other MTUs. +# +# Check that both C and A are able to communicate with B over the VXLAN +# tunnel, and that PMTU exceptions with the correct values are created. +# +# segment a_r1 segment b_r1 b_r1: 4000 +# .--------------R1--------------. everything +# C---veth A B else: 5000 +# ' bridge | +# '---- - - - - - VXLAN - - - - - - - ' +# +# - pmtu_ipv{4,6}_br_geneve{4,6}_exception +# Same as pmtu_ipv{4,6}_br_vxlan{4,6}_exception, with a GENEVE tunnel +# instead. +# # - pmtu_ipv{4,6}_fou{4,6}_exception # Same as pmtu_ipv4_vxlan4, but using a direct IPv4/IPv6 encapsulation # (FoU) over IPv4/IPv6, instead of VXLAN @@ -147,6 +166,14 @@ tests=" pmtu_ipv6_geneve4_exception IPv6 over geneve4: PMTU exceptions 1 pmtu_ipv4_geneve6_exception IPv4 over geneve6: PMTU exceptions 1 pmtu_ipv6_geneve6_exception IPv6 over geneve6: PMTU exceptions 1 + pmtu_ipv4_br_vxlan4_exception IPv4, bridged vxlan4: PMTU exceptions 1 + pmtu_ipv6_br_vxlan4_exception IPv6, bridged vxlan4: PMTU exceptions 1 + pmtu_ipv4_br_vxlan6_exception IPv4, bridged vxlan6: PMTU exceptions 1 + pmtu_ipv6_br_vxlan6_exception IPv6, bridged vxlan6: PMTU exceptions 1 + pmtu_ipv4_br_geneve4_exception IPv4, bridged geneve4: PMTU exceptions 1 + pmtu_ipv6_br_geneve4_exception IPv6, bridged geneve4: PMTU exceptions 1 + pmtu_ipv4_br_geneve6_exception IPv4, bridged geneve6: PMTU exceptions 1 + pmtu_ipv6_br_geneve6_exception IPv6, bridged geneve6: PMTU exceptions 1 pmtu_ipv4_fou4_exception IPv4 over fou4: PMTU exceptions 1 pmtu_ipv6_fou4_exception IPv6 over fou4: PMTU exceptions 1 pmtu_ipv4_fou6_exception IPv4 over fou6: PMTU exceptions 1 @@ -173,10 +200,12 @@ tests=" NS_A="ns-A" NS_B="ns-B" +NS_C="ns-C" NS_R1="ns-R1" NS_R2="ns-R2" ns_a="ip netns exec ${NS_A}" ns_b="ip netns exec ${NS_B}" +ns_c="ip netns exec ${NS_C}" ns_r1="ip netns exec ${NS_R1}" ns_r2="ip netns exec ${NS_R2}" @@ -239,9 +268,11 @@ routes_nh=" veth4_a_addr="192.168.1.1" veth4_b_addr="192.168.1.2" +veth4_c_addr="192.168.2.10" veth4_mask="24" veth6_a_addr="fd00:1::a" veth6_b_addr="fd00:1::b" +veth6_c_addr="fd00:2::c" veth6_mask="64" tunnel4_a_addr="192.168.2.1" @@ -428,7 +459,7 @@ setup_ip6ip6() { } setup_namespaces() { - for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do + for n in ${NS_A} ${NS_B} ${NS_C} ${NS_R1} ${NS_R2}; do ip netns add ${n} || return 1 # Disable DAD, so that we don't have to wait to use the @@ -484,6 +515,7 @@ setup_vxlan_or_geneve() { a_addr="${2}" b_addr="${3}" opts="${4}" + br_if_a="${5}" if [ "${type}" = "vxlan" ]; then opts="${opts} ttl 64 dstport 4789" @@ -497,10 +529,16 @@ setup_vxlan_or_geneve() { run_cmd ${ns_a} ip link add ${type}_a type ${type} id 1 ${opts_a} remote ${b_addr} ${opts} || return 1 run_cmd ${ns_b} ip link add ${type}_b type ${type} id 1 ${opts_b} remote ${a_addr} ${opts} - run_cmd ${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ${type}_a - run_cmd ${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ${type}_b + if [ -n "${br_if_a}" ]; then + run_cmd ${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ${br_if_a} + run_cmd ${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ${br_if_a} + run_cmd ${ns_a} ip link set ${type}_a master ${br_if_a} + else + run_cmd ${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ${type}_a + run_cmd ${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ${type}_a + fi - run_cmd ${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ${type}_a + run_cmd ${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ${type}_b run_cmd ${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev ${type}_b run_cmd ${ns_a} ip link set ${type}_a up @@ -516,11 +554,27 @@ setup_vxlan4() { } setup_geneve6() { - setup_vxlan_or_geneve geneve ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 + setup_vxlan_or_geneve geneve ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "" } setup_vxlan6() { - setup_vxlan_or_geneve vxlan ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 + setup_vxlan_or_geneve vxlan ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "" +} + +setup_bridged_geneve4() { + setup_vxlan_or_geneve geneve ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "df set" "br0" +} + +setup_bridged_vxlan4() { + setup_vxlan_or_geneve vxlan ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "df set" "br0" +} + +setup_bridged_geneve6() { + setup_vxlan_or_geneve geneve ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "" "br0" +} + +setup_bridged_vxlan6() { + setup_vxlan_or_geneve vxlan ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "" "br0" } setup_xfrm() { @@ -630,6 +684,20 @@ setup_routing() { return 0 } +setup_bridge() { + run_cmd ${ns_a} ip link add br0 type bridge || return 2 + run_cmd ${ns_a} ip link set br0 up + + run_cmd ${ns_c} ip link add veth_C-A type veth peer name veth_A-C + run_cmd ${ns_c} ip link set veth_A-C netns ns-A + + run_cmd ${ns_a} ip link set veth_A-C up + run_cmd ${ns_c} ip link set veth_C-A up + run_cmd ${ns_c} ip addr add ${veth4_c_addr}/${veth4_mask} dev veth_C-A + run_cmd ${ns_c} ip addr add ${veth6_c_addr}/${veth6_mask} dev veth_C-A + run_cmd ${ns_a} ip link set veth_A-C master br0 +} + setup() { [ "$(id -u)" -ne 0 ] && echo " need to run as root" && return $ksft_skip @@ -657,7 +725,7 @@ cleanup() { done tcpdump_pids= - for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do + for n in ${NS_A} ${NS_B} ${NS_C} ${NS_R1} ${NS_R2}; do ip netns del ${n} 2> /dev/null done } @@ -892,6 +960,90 @@ test_pmtu_ipv6_geneve6_exception() { test_pmtu_ipvX_over_vxlanY_or_geneveY_exception geneve 6 6 } +test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception() { + type=${1} + family=${2} + outer_family=${3} + ll_mtu=4000 + + if [ ${outer_family} -eq 4 ]; then + setup namespaces routing bridge bridged_${type}4 || return 2 + # IPv4 header UDP header VXLAN/GENEVE header Ethernet header + exp_mtu=$((${ll_mtu} - 20 - 8 - 8 - 14)) + else + setup namespaces routing bridge bridged_${type}6 || return 2 + # IPv6 header UDP header VXLAN/GENEVE header Ethernet header + exp_mtu=$((${ll_mtu} - 40 - 8 - 8 - 14)) + fi + + trace "${ns_a}" ${type}_a "${ns_b}" ${type}_b \ + "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \ + "${ns_b}" veth_B-R1 "${ns_r1}" veth_R1-B \ + "${ns_a}" br0 "${ns_a}" veth-A-C \ + "${ns_c}" veth_C-A + + if [ ${family} -eq 4 ]; then + ping=ping + dst=${tunnel4_b_addr} + else + ping=${ping6} + dst=${tunnel6_b_addr} + fi + + # Create route exception by exceeding link layer MTU + mtu "${ns_a}" veth_A-R1 $((${ll_mtu} + 1000)) + mtu "${ns_a}" br0 $((${ll_mtu} + 1000)) + mtu "${ns_a}" veth_A-C $((${ll_mtu} + 1000)) + mtu "${ns_c}" veth_C-A $((${ll_mtu} + 1000)) + mtu "${ns_r1}" veth_R1-A $((${ll_mtu} + 1000)) + mtu "${ns_b}" veth_B-R1 ${ll_mtu} + mtu "${ns_r1}" veth_R1-B ${ll_mtu} + + mtu "${ns_a}" ${type}_a $((${ll_mtu} + 1000)) + mtu "${ns_b}" ${type}_b $((${ll_mtu} + 1000)) + + run_cmd ${ns_c} ${ping} -q -M want -i 0.1 -c 10 -s $((${ll_mtu} + 500)) ${dst} || return 1 + run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${dst} || return 1 + + # Check that exceptions were created + pmtu="$(route_get_dst_pmtu_from_exception "${ns_c}" ${dst})" + check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on bridged ${type} interface" + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})" + check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on locally bridged ${type} interface" +} + +test_pmtu_ipv4_br_vxlan4_exception() { + test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception vxlan 4 4 +} + +test_pmtu_ipv6_br_vxlan4_exception() { + test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception vxlan 6 4 +} + +test_pmtu_ipv4_br_geneve4_exception() { + test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception geneve 4 4 +} + +test_pmtu_ipv6_br_geneve4_exception() { + test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception geneve 6 4 +} + +test_pmtu_ipv4_br_vxlan6_exception() { + test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception vxlan 4 6 +} + +test_pmtu_ipv6_br_vxlan6_exception() { + test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception vxlan 6 6 +} + +test_pmtu_ipv4_br_geneve6_exception() { + test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception geneve 4 6 +} + +test_pmtu_ipv6_br_geneve6_exception() { + test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception geneve 6 6 +} + test_pmtu_ipvX_over_fouY_or_gueY() { inner_family=${1} outer_family=${2} -- cgit v1.2.3 From 7b53682c94032a7a7adec400400c65d0af7fea5a Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Tue, 4 Aug 2020 07:53:47 +0200 Subject: selftests: pmtu.sh: Add tests for UDP tunnels handled by Open vSwitch The new tests check that IP and IPv6 packets exceeding the local PMTU estimate, forwarded by an Open vSwitch instance from another node, result in the correct route exceptions being created, and that communication with end-to-end fragmentation, over GENEVE and VXLAN Open vSwitch ports, is now possible as a result of PMTU discovery. Signed-off-by: Stefano Brivio Signed-off-by: David S. Miller --- tools/testing/selftests/net/pmtu.sh | 180 ++++++++++++++++++++++++++++++++++++ 1 file changed, 180 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 774e526573f3..6bbf69a28e12 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -78,6 +78,26 @@ # Same as pmtu_ipv{4,6}_br_vxlan{4,6}_exception, with a GENEVE tunnel # instead. # +# - pmtu_ipv{4,6}_ovs_vxlan{4,6}_exception +# Set up two namespaces, B, and C, with routing between the init namespace +# and B over R1. A and R2 are unused in these tests. The init namespace +# has a veth connection to C, and is connected to B via a VXLAN endpoint, +# which is handled by Open vSwitch and bridged to C. MTU on the B-R1 link +# is lower than other MTUs. +# +# Check that C is able to communicate with B over the VXLAN tunnel, and +# that PMTU exceptions with the correct values are created. +# +# segment a_r1 segment b_r1 b_r1: 4000 +# .--------------R1--------------. everything +# C---veth init B else: 5000 +# '- ovs | +# '---- - - - - - VXLAN - - - - - - - ' +# +# - pmtu_ipv{4,6}_ovs_geneve{4,6}_exception +# Same as pmtu_ipv{4,6}_ovs_vxlan{4,6}_exception, with a GENEVE tunnel +# instead. +# # - pmtu_ipv{4,6}_fou{4,6}_exception # Same as pmtu_ipv4_vxlan4, but using a direct IPv4/IPv6 encapsulation # (FoU) over IPv4/IPv6, instead of VXLAN @@ -174,6 +194,14 @@ tests=" pmtu_ipv6_br_geneve4_exception IPv6, bridged geneve4: PMTU exceptions 1 pmtu_ipv4_br_geneve6_exception IPv4, bridged geneve6: PMTU exceptions 1 pmtu_ipv6_br_geneve6_exception IPv6, bridged geneve6: PMTU exceptions 1 + pmtu_ipv4_ovs_vxlan4_exception IPv4, OVS vxlan4: PMTU exceptions 1 + pmtu_ipv6_ovs_vxlan4_exception IPv6, OVS vxlan4: PMTU exceptions 1 + pmtu_ipv4_ovs_vxlan6_exception IPv4, OVS vxlan6: PMTU exceptions 1 + pmtu_ipv6_ovs_vxlan6_exception IPv6, OVS vxlan6: PMTU exceptions 1 + pmtu_ipv4_ovs_geneve4_exception IPv4, OVS geneve4: PMTU exceptions 1 + pmtu_ipv6_ovs_geneve4_exception IPv6, OVS geneve4: PMTU exceptions 1 + pmtu_ipv4_ovs_geneve6_exception IPv4, OVS geneve6: PMTU exceptions 1 + pmtu_ipv6_ovs_geneve6_exception IPv6, OVS geneve6: PMTU exceptions 1 pmtu_ipv4_fou4_exception IPv4 over fou4: PMTU exceptions 1 pmtu_ipv6_fou4_exception IPv6 over fou4: PMTU exceptions 1 pmtu_ipv4_fou6_exception IPv4 over fou6: PMTU exceptions 1 @@ -698,6 +726,66 @@ setup_bridge() { run_cmd ${ns_a} ip link set veth_A-C master br0 } +setup_ovs_vxlan_or_geneve() { + type="${1}" + a_addr="${2}" + b_addr="${3}" + + if [ "${type}" = "vxlan" ]; then + opts="${opts} ttl 64 dstport 4789" + opts_b="local ${b_addr}" + fi + + run_cmd ovs-vsctl add-port ovs_br0 ${type}_a -- \ + set interface ${type}_a type=${type} \ + options:remote_ip=${b_addr} options:key=1 options:csum=true || return 1 + + run_cmd ${ns_b} ip link add ${type}_b type ${type} id 1 ${opts_b} remote ${a_addr} ${opts} || return 1 + + run_cmd ${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ${type}_b + run_cmd ${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev ${type}_b + + run_cmd ${ns_b} ip link set ${type}_b up +} + +setup_ovs_geneve4() { + setup_ovs_vxlan_or_geneve geneve ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 +} + +setup_ovs_vxlan4() { + setup_ovs_vxlan_or_geneve vxlan ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 +} + +setup_ovs_geneve6() { + setup_ovs_vxlan_or_geneve geneve ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 +} + +setup_ovs_vxlan6() { + setup_ovs_vxlan_or_geneve vxlan ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 +} + +setup_ovs_bridge() { + run_cmd ovs-vsctl add-br ovs_br0 || return 2 + run_cmd ip link set ovs_br0 up + + run_cmd ${ns_c} ip link add veth_C-A type veth peer name veth_A-C + run_cmd ${ns_c} ip link set veth_A-C netns 1 + + run_cmd ip link set veth_A-C up + run_cmd ${ns_c} ip link set veth_C-A up + run_cmd ${ns_c} ip addr add ${veth4_c_addr}/${veth4_mask} dev veth_C-A + run_cmd ${ns_c} ip addr add ${veth6_c_addr}/${veth6_mask} dev veth_C-A + run_cmd ovs-vsctl add-port ovs_br0 veth_A-C + + # Move veth_A-R1 to init + run_cmd ${ns_a} ip link set veth_A-R1 netns 1 + run_cmd ip addr add ${prefix4}.${a_r1}.1/${veth4_mask} dev veth_A-R1 + run_cmd ip addr add ${prefix6}:${a_r1}::1/${veth6_mask} dev veth_A-R1 + run_cmd ip link set veth_A-R1 up + run_cmd ip route add ${prefix4}.${b_r1}.1 via ${prefix4}.${a_r1}.2 + run_cmd ip route add ${prefix6}:${b_r1}::1 via ${prefix6}:${a_r1}::2 +} + setup() { [ "$(id -u)" -ne 0 ] && echo " need to run as root" && return $ksft_skip @@ -728,6 +816,11 @@ cleanup() { for n in ${NS_A} ${NS_B} ${NS_C} ${NS_R1} ${NS_R2}; do ip netns del ${n} 2> /dev/null done + + ip link del veth_A-C 2>/dev/null + ip link del veth_A-R1 2>/dev/null + ovs-vsctl --if-exists del-port vxlan_a 2>/dev/null + ovs-vsctl --if-exists del-br ovs_br0 2>/dev/null } mtu() { @@ -1044,6 +1137,93 @@ test_pmtu_ipv6_br_geneve6_exception() { test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception geneve 6 6 } +test_pmtu_ipvX_over_ovs_vxlanY_or_geneveY_exception() { + type=${1} + family=${2} + outer_family=${3} + ll_mtu=4000 + + if [ ${outer_family} -eq 4 ]; then + setup namespaces routing ovs_bridge ovs_${type}4 || return 2 + # IPv4 header UDP header VXLAN/GENEVE header Ethernet header + exp_mtu=$((${ll_mtu} - 20 - 8 - 8 - 14)) + else + setup namespaces routing ovs_bridge ovs_${type}6 || return 2 + # IPv6 header UDP header VXLAN/GENEVE header Ethernet header + exp_mtu=$((${ll_mtu} - 40 - 8 - 8 - 14)) + fi + + if [ "${type}" = "vxlan" ]; then + tun_a="vxlan_sys_4789" + elif [ "${type}" = "geneve" ]; then + tun_a="genev_sys_6081" + fi + + trace "" "${tun_a}" "${ns_b}" ${type}_b \ + "" veth_A-R1 "${ns_r1}" veth_R1-A \ + "${ns_b}" veth_B-R1 "${ns_r1}" veth_R1-B \ + "" ovs_br0 "" veth-A-C \ + "${ns_c}" veth_C-A + + if [ ${family} -eq 4 ]; then + ping=ping + dst=${tunnel4_b_addr} + else + ping=${ping6} + dst=${tunnel6_b_addr} + fi + + # Create route exception by exceeding link layer MTU + mtu "" veth_A-R1 $((${ll_mtu} + 1000)) + mtu "" ovs_br0 $((${ll_mtu} + 1000)) + mtu "" veth_A-C $((${ll_mtu} + 1000)) + mtu "${ns_c}" veth_C-A $((${ll_mtu} + 1000)) + mtu "${ns_r1}" veth_R1-A $((${ll_mtu} + 1000)) + mtu "${ns_b}" veth_B-R1 ${ll_mtu} + mtu "${ns_r1}" veth_R1-B ${ll_mtu} + + mtu "" ${tun_a} $((${ll_mtu} + 1000)) + mtu "${ns_b}" ${type}_b $((${ll_mtu} + 1000)) + + run_cmd ${ns_c} ${ping} -q -M want -i 0.1 -c 20 -s $((${ll_mtu} + 500)) ${dst} || return 1 + + # Check that exceptions were created + pmtu="$(route_get_dst_pmtu_from_exception "${ns_c}" ${dst})" + check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on Open vSwitch ${type} interface" +} + +test_pmtu_ipv4_ovs_vxlan4_exception() { + test_pmtu_ipvX_over_ovs_vxlanY_or_geneveY_exception vxlan 4 4 +} + +test_pmtu_ipv6_ovs_vxlan4_exception() { + test_pmtu_ipvX_over_ovs_vxlanY_or_geneveY_exception vxlan 6 4 +} + +test_pmtu_ipv4_ovs_geneve4_exception() { + test_pmtu_ipvX_over_ovs_vxlanY_or_geneveY_exception geneve 4 4 +} + +test_pmtu_ipv6_ovs_geneve4_exception() { + test_pmtu_ipvX_over_ovs_vxlanY_or_geneveY_exception geneve 6 4 +} + +test_pmtu_ipv4_ovs_vxlan6_exception() { + test_pmtu_ipvX_over_ovs_vxlanY_or_geneveY_exception vxlan 4 6 +} + +test_pmtu_ipv6_ovs_vxlan6_exception() { + test_pmtu_ipvX_over_ovs_vxlanY_or_geneveY_exception vxlan 6 6 +} + +test_pmtu_ipv4_ovs_geneve6_exception() { + test_pmtu_ipvX_over_ovs_vxlanY_or_geneveY_exception geneve 4 6 +} + +test_pmtu_ipv6_ovs_geneve6_exception() { + test_pmtu_ipvX_over_ovs_vxlanY_or_geneveY_exception geneve 6 6 +} + test_pmtu_ipvX_over_fouY_or_gueY() { inner_family=${1} outer_family=${2} -- cgit v1.2.3 From c2a4d2747996ee6a1397e2064d44a4f57ac442e6 Mon Sep 17 00:00:00 2001 From: Po-Hsu Lin Date: Tue, 4 Aug 2020 18:18:02 +0800 Subject: selftests: rtnetlink: correct the final return value for the test The return value "ret" will be reset to 0 from the beginning of each sub-test in rtnetlink.sh, therefore this test will always pass if the last sub-test has passed: $ sudo ./rtnetlink.sh PASS: policy routing PASS: route get PASS: preferred_lft addresses have expired PASS: promote_secondaries complete PASS: tc htb hierarchy PASS: gre tunnel endpoint PASS: gretap PASS: ip6gretap PASS: erspan PASS: ip6erspan PASS: bridge setup PASS: ipv6 addrlabel PASS: set ifalias a39ee707-e36b-41d3-802f-63179ed4d580 for test-dummy0 PASS: vrf PASS: vxlan FAIL: can't add fou port 7777, skipping test PASS: macsec PASS: ipsec 3,7c3,7 < sa[0] spi=0x00000009 proto=0x32 salt=0x64636261 crypt=1 < sa[0] key=0x31323334 35363738 39303132 33343536 < sa[1] rx ipaddr=0x00000000 00000000 00000000 c0a87b03 < sa[1] spi=0x00000009 proto=0x32 salt=0x64636261 crypt=1 < sa[1] key=0x31323334 35363738 39303132 33343536 --- > sa[0] spi=0x00000009 proto=0x32 salt=0x61626364 crypt=1 > sa[0] key=0x34333231 38373635 32313039 36353433 > sa[1] rx ipaddr=0x00000000 00000000 00000000 037ba8c0 > sa[1] spi=0x00000009 proto=0x32 salt=0x61626364 crypt=1 > sa[1] key=0x34333231 38373635 32313039 36353433 FAIL: ipsec_offload incorrect driver data FAIL: ipsec_offload PASS: bridge fdb get PASS: neigh get $ echo $? 0 Make "ret" become a local variable for all sub-tests. Also, check the sub-test results in kci_test_rtnl() and return the final result for this test. Signed-off-by: Po-Hsu Lin Signed-off-by: David S. Miller --- tools/testing/selftests/net/rtnetlink.sh | 65 +++++++++++++++++++++----------- 1 file changed, 43 insertions(+), 22 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index bdbf4b3125b6..9db66bef6f1e 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -5,7 +5,6 @@ # set -e devdummy="test-dummy0" -ret=0 # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 @@ -66,7 +65,7 @@ kci_test_bridge() devbr="test-br0" vlandev="testbr-vlan1" - ret=0 + local ret=0 ip link add name "$devbr" type bridge check_err $? @@ -113,7 +112,7 @@ kci_test_gre() rem=10.42.42.1 loc=10.0.0.1 - ret=0 + local ret=0 ip tunnel add $gredev mode gre remote $rem local $loc ttl 1 check_err $? ip link set $gredev up @@ -149,7 +148,7 @@ kci_test_gre() kci_test_tc() { dev=lo - ret=0 + local ret=0 tc qdisc add dev "$dev" root handle 1: htb check_err $? @@ -184,7 +183,7 @@ kci_test_tc() kci_test_polrouting() { - ret=0 + local ret=0 ip rule add fwmark 1 lookup 100 check_err $? ip route add local 0.0.0.0/0 dev lo table 100 @@ -207,7 +206,7 @@ kci_test_route_get() { local hash_policy=$(sysctl -n net.ipv4.fib_multipath_hash_policy) - ret=0 + local ret=0 ip route get 127.0.0.1 > /dev/null check_err $? @@ -290,7 +289,7 @@ kci_test_promote_secondaries() kci_test_addrlabel() { - ret=0 + local ret=0 ip addrlabel add prefix dead::/64 dev lo label 1 check_err $? @@ -330,7 +329,7 @@ kci_test_addrlabel() kci_test_ifalias() { - ret=0 + local ret=0 namewant=$(uuidgen) syspathname="/sys/class/net/$devdummy/ifalias" @@ -385,7 +384,7 @@ kci_test_ifalias() kci_test_vrf() { vrfname="test-vrf" - ret=0 + local ret=0 ip link show type vrf 2>/dev/null if [ $? -ne 0 ]; then @@ -425,7 +424,7 @@ kci_test_vrf() kci_test_encap_vxlan() { - ret=0 + local ret=0 vxlan="test-vxlan0" vlan="test-vlan0" testns="$1" @@ -511,7 +510,7 @@ kci_test_encap_vxlan() kci_test_encap_fou() { - ret=0 + local ret=0 name="test-fou" testns="$1" @@ -548,7 +547,7 @@ kci_test_encap_fou() kci_test_encap() { testns="testns" - ret=0 + local ret=0 ip netns add "$testns" if [ $? -ne 0 ]; then @@ -573,7 +572,7 @@ kci_test_encap() kci_test_macsec() { msname="test_macsec0" - ret=0 + local ret=0 ip macsec help 2>&1 | grep -q "^Usage: ip macsec" if [ $? -ne 0 ]; then @@ -631,7 +630,7 @@ kci_test_macsec() #------------------------------------------------------------------- kci_test_ipsec() { - ret=0 + local ret=0 algo="aead rfc4106(gcm(aes)) 0x3132333435363738393031323334353664636261 128" srcip=192.168.123.1 dstip=192.168.123.2 @@ -731,7 +730,7 @@ kci_test_ipsec() #------------------------------------------------------------------- kci_test_ipsec_offload() { - ret=0 + local ret=0 algo="aead rfc4106(gcm(aes)) 0x3132333435363738393031323334353664636261 128" srcip=192.168.123.3 dstip=192.168.123.4 @@ -841,7 +840,7 @@ kci_test_gretap() { testns="testns" DEV_NS=gretap00 - ret=0 + local ret=0 ip netns add "$testns" if [ $? -ne 0 ]; then @@ -891,7 +890,7 @@ kci_test_ip6gretap() { testns="testns" DEV_NS=ip6gretap00 - ret=0 + local ret=0 ip netns add "$testns" if [ $? -ne 0 ]; then @@ -941,7 +940,7 @@ kci_test_erspan() { testns="testns" DEV_NS=erspan00 - ret=0 + local ret=0 ip link help erspan 2>&1 | grep -q "^Usage:" if [ $? -ne 0 ];then @@ -1006,7 +1005,7 @@ kci_test_ip6erspan() { testns="testns" DEV_NS=ip6erspan00 - ret=0 + local ret=0 ip link help ip6erspan 2>&1 | grep -q "^Usage:" if [ $? -ne 0 ];then @@ -1077,7 +1076,7 @@ kci_test_fdb_get() test_mac=de:ad:be:ef:13:37 localip="10.0.2.2" dstip="10.0.2.3" - ret=0 + local ret=0 bridge fdb help 2>&1 |grep -q 'bridge fdb get' if [ $? -ne 0 ];then @@ -1125,7 +1124,7 @@ kci_test_neigh_get() dstmac=de:ad:be:ef:13:37 dstip=10.0.2.4 dstip6=dead::2 - ret=0 + local ret=0 ip neigh help 2>&1 |grep -q 'ip neigh get' if [ $? -ne 0 ];then @@ -1175,6 +1174,7 @@ kci_test_neigh_get() kci_test_rtnl() { + local ret=0 kci_add_dummy if [ $ret -ne 0 ];then echo "FAIL: cannot add dummy interface" @@ -1182,27 +1182,48 @@ kci_test_rtnl() fi kci_test_polrouting + check_err $? kci_test_route_get + check_err $? kci_test_addrlft + check_err $? kci_test_promote_secondaries + check_err $? kci_test_tc + check_err $? kci_test_gre + check_err $? kci_test_gretap + check_err $? kci_test_ip6gretap + check_err $? kci_test_erspan + check_err $? kci_test_ip6erspan + check_err $? kci_test_bridge + check_err $? kci_test_addrlabel + check_err $? kci_test_ifalias + check_err $? kci_test_vrf + check_err $? kci_test_encap + check_err $? kci_test_macsec + check_err $? kci_test_ipsec + check_err $? kci_test_ipsec_offload + check_err $? kci_test_fdb_get + check_err $? kci_test_neigh_get + check_err $? kci_del_dummy + return $ret } #check for needed privileges @@ -1221,4 +1242,4 @@ done kci_test_rtnl -exit $ret +exit $? -- cgit v1.2.3 From 72f70c159b53e1363191953875e0223ed959e143 Mon Sep 17 00:00:00 2001 From: Po-Hsu Lin Date: Tue, 4 Aug 2020 18:18:03 +0800 Subject: selftests: rtnetlink: make kci_test_encap() return sub-test result kci_test_encap() is actually composed by two different sub-tests, kci_test_encap_vxlan() and kci_test_encap_fou() Therefore we should check the test result of these two in kci_test_encap() to let the script be aware of the pass / fail status. Otherwise it will generate false-negative result like below: $ sudo ./test.sh PASS: policy routing PASS: route get PASS: preferred_lft addresses have expired PASS: promote_secondaries complete PASS: tc htb hierarchy PASS: gre tunnel endpoint PASS: gretap PASS: ip6gretap PASS: erspan PASS: ip6erspan PASS: bridge setup PASS: ipv6 addrlabel PASS: set ifalias 5b193daf-0a08-46d7-af2c-e7aadd422ded for test-dummy0 PASS: vrf PASS: vxlan FAIL: can't add fou port 7777, skipping test PASS: macsec PASS: bridge fdb get PASS: neigh get $ echo $? 0 Signed-off-by: Po-Hsu Lin Signed-off-by: David S. Miller --- tools/testing/selftests/net/rtnetlink.sh | 3 +++ 1 file changed, 3 insertions(+) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 9db66bef6f1e..7c38a909f8b8 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -564,9 +564,12 @@ kci_test_encap() check_err $? kci_test_encap_vxlan "$testns" + check_err $? kci_test_encap_fou "$testns" + check_err $? ip netns del "$testns" + return $ret } kci_test_macsec() -- cgit v1.2.3 From 16f6458f2478b55e2b628797bc81a4455045c74e Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Wed, 5 Aug 2020 04:40:45 -0400 Subject: selftests/net: relax cpu affinity requirement in msg_zerocopy test The msg_zerocopy test pins the sender and receiver threads to separate cores to reduce variance between runs. But it hardcodes the cores and skips core 0, so it fails on machines with the selected cores offline, or simply fewer cores. The test mainly gives code coverage in automated runs. The throughput of zerocopy ('-z') and non-zerocopy runs is logged for manual inspection. Continue even when sched_setaffinity fails. Just log to warn anyone interpreting the data. Fixes: 07b65c5b31ce ("test: add msg_zerocopy test") Reported-by: Colin Ian King Signed-off-by: Willem de Bruijn Acked-by: Colin Ian King Signed-off-by: David S. Miller --- tools/testing/selftests/net/msg_zerocopy.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'tools/testing/selftests') diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c index 4b02933cab8a..bdc03a2097e8 100644 --- a/tools/testing/selftests/net/msg_zerocopy.c +++ b/tools/testing/selftests/net/msg_zerocopy.c @@ -125,9 +125,8 @@ static int do_setcpu(int cpu) CPU_ZERO(&mask); CPU_SET(cpu, &mask); if (sched_setaffinity(0, sizeof(mask), &mask)) - error(1, 0, "setaffinity %d", cpu); - - if (cfg_verbose) + fprintf(stderr, "cpu: unable to pin, may increase variance.\n"); + else if (cfg_verbose) fprintf(stderr, "cpu: %u\n", cpu); return 0; -- cgit v1.2.3