diff options
| author | David S. Miller <davem@davemloft.net> | 2020-05-01 17:02:27 -0700 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2020-05-01 17:02:27 -0700 |
| commit | 115506fea499f1cd9a80290b31eca4352e0559e9 (patch) | |
| tree | 25e4ff3b5a49115d964fab690cf72fa18a5f96bf /tools | |
| parent | 5b95dea31636ce93660930d16172fe75589b2e70 (diff) | |
| parent | 57dc6f3b4133f45e73d87895180ca1f3eaf01722 (diff) | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Alexei Starovoitov says:
====================
pull-request: bpf-next 2020-05-01 (v2)
The following pull-request contains BPF updates for your *net-next* tree.
We've added 61 non-merge commits during the last 6 day(s) which contain
a total of 153 files changed, 6739 insertions(+), 3367 deletions(-).
The main changes are:
1) pulled work.sysctl from vfs tree with sysctl bpf changes.
2) bpf_link observability, from Andrii.
3) BTF-defined map in map, from Andrii.
4) asan fixes for selftests, from Andrii.
5) Allow bpf_map_lookup_elem for SOCKMAP and SOCKHASH, from Jakub.
6) production cloudflare classifier as a selftes, from Lorenz.
7) bpf_ktime_get_*_ns() helper improvements, from Maciej.
8) unprivileged bpftool feature probe, from Quentin.
9) BPF_ENABLE_STATS command, from Song.
10) enable bpf_[gs]etsockopt() helpers for sock_ops progs, from Stanislav.
11) enable a bunch of common helpers for cg-device, sysctl, sockopt progs,
from Stanislav.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'tools')
46 files changed, 3591 insertions, 555 deletions
diff --git a/tools/bpf/bpftool/Documentation/bpftool-feature.rst b/tools/bpf/bpftool/Documentation/bpftool-feature.rst index b04156cfd7a3..1fa755f55e0c 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-feature.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-feature.rst @@ -19,7 +19,7 @@ SYNOPSIS FEATURE COMMANDS ================ -| **bpftool** **feature probe** [*COMPONENT*] [**full**] [**macros** [**prefix** *PREFIX*]] +| **bpftool** **feature probe** [*COMPONENT*] [**full**] [**unprivileged**] [**macros** [**prefix** *PREFIX*]] | **bpftool** **feature help** | | *COMPONENT* := { **kernel** | **dev** *NAME* } @@ -49,6 +49,16 @@ DESCRIPTION Keyword **kernel** can be omitted. If no probe target is specified, probing the kernel is the default behaviour. + When the **unprivileged** keyword is used, bpftool will dump + only the features available to a user who does not have the + **CAP_SYS_ADMIN** capability set. The features available in + that case usually represent a small subset of the parameters + supported by the system. Unprivileged users MUST use the + **unprivileged** keyword: This is to avoid misdetection if + bpftool is inadvertently run as non-root, for example. This + keyword is unavailable if bpftool was compiled without + libcap. + **bpftool feature probe dev** *NAME* [**full**] [**macros** [**prefix** *PREFIX*]] Probe network device for supported eBPF features and dump results to the console. diff --git a/tools/bpf/bpftool/Documentation/bpftool-link.rst b/tools/bpf/bpftool/Documentation/bpftool-link.rst new file mode 100644 index 000000000000..ee6500d6e6e4 --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-link.rst @@ -0,0 +1,118 @@ +================ +bpftool-link +================ +------------------------------------------------------------------------------- +tool for inspection and simple manipulation of eBPF links +------------------------------------------------------------------------------- + +:Manual section: 8 + +SYNOPSIS +======== + + **bpftool** [*OPTIONS*] **link** *COMMAND* + + *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-f** | **--bpffs** } } + + *COMMANDS* := { **show** | **list** | **pin** | **help** } + +LINK COMMANDS +============= + +| **bpftool** **link { show | list }** [*LINK*] +| **bpftool** **link pin** *LINK* *FILE* +| **bpftool** **link help** +| +| *LINK* := { **id** *LINK_ID* | **pinned** *FILE* } + + +DESCRIPTION +=========== + **bpftool link { show | list }** [*LINK*] + Show information about active links. If *LINK* is + specified show information only about given link, + otherwise list all links currently active on the system. + + Output will start with link ID followed by link type and + zero or more named attributes, some of which depend on type + of link. + + **bpftool link pin** *LINK* *FILE* + Pin link *LINK* as *FILE*. + + Note: *FILE* must be located in *bpffs* mount. It must not + contain a dot character ('.'), which is reserved for future + extensions of *bpffs*. + + **bpftool link help** + Print short help message. + +OPTIONS +======= + -h, --help + Print short generic help message (similar to **bpftool help**). + + -V, --version + Print version number (similar to **bpftool version**). + + -j, --json + Generate JSON output. For commands that cannot produce JSON, this + option has no effect. + + -p, --pretty + Generate human-readable JSON output. Implies **-j**. + + -f, --bpffs + When showing BPF links, show file names of pinned + links. + + -n, --nomount + Do not automatically attempt to mount any virtual file system + (such as tracefs or BPF virtual file system) when necessary. + + -d, --debug + Print all logs available, even debug-level information. This + includes logs from libbpf. + +EXAMPLES +======== +**# bpftool link show** + +:: + + 10: cgroup prog 25 + cgroup_id 614 attach_type egress + +**# bpftool --json --pretty link show** + +:: + + [{ + "type": "cgroup", + "prog_id": 25, + "cgroup_id": 614, + "attach_type": "egress" + } + ] + +| +| **# bpftool link pin id 10 /sys/fs/bpf/link** +| **# ls -l /sys/fs/bpf/** + +:: + + -rw------- 1 root root 0 Apr 23 21:39 link + + +SEE ALSO +======== + **bpf**\ (2), + **bpf-helpers**\ (7), + **bpftool**\ (8), + **bpftool-prog\ (8), + **bpftool-map**\ (8), + **bpftool-cgroup**\ (8), + **bpftool-feature**\ (8), + **bpftool-net**\ (8), + **bpftool-perf**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index f584d1fdfc64..2759f9cc3289 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -55,16 +55,15 @@ ifneq ($(EXTRA_LDFLAGS),) LDFLAGS += $(EXTRA_LDFLAGS) endif -LIBS = $(LIBBPF) -lelf -lz - INSTALL ?= install RM ?= rm -f CLANG ?= clang FEATURE_USER = .bpftool -FEATURE_TESTS = libbfd disassembler-four-args reallocarray zlib \ +FEATURE_TESTS = libbfd disassembler-four-args reallocarray zlib libcap \ + clang-bpf-global-var +FEATURE_DISPLAY = libbfd disassembler-four-args zlib libcap \ clang-bpf-global-var -FEATURE_DISPLAY = libbfd disassembler-four-args zlib clang-bpf-global-var check_feat := 1 NON_CHECK_FEAT_TARGETS := clean uninstall doc doc-clean doc-install doc-uninstall @@ -90,6 +89,12 @@ ifeq ($(feature-reallocarray), 0) CFLAGS += -DCOMPAT_NEED_REALLOCARRAY endif +LIBS = $(LIBBPF) -lelf -lz +ifeq ($(feature-libcap), 1) +CFLAGS += -DUSE_LIBCAP +LIBS += -lcap +endif + include $(wildcard $(OUTPUT)*.d) all: $(OUTPUT)bpftool diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index 45ee99b159e2..fc989ead7313 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -98,6 +98,12 @@ _bpftool_get_btf_ids() command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) ) } +_bpftool_get_link_ids() +{ + COMPREPLY+=( $( compgen -W "$( bpftool -jp link 2>&1 | \ + command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) ) +} + _bpftool_get_obj_map_names() { local obj @@ -1073,7 +1079,7 @@ _bpftool() COMPREPLY+=( $( compgen -W 'macros' -- "$cur" ) ) fi _bpftool_one_of_list 'kernel dev' - _bpftool_once_attr 'full' + _bpftool_once_attr 'full unprivileged' return 0 ;; *) @@ -1082,6 +1088,39 @@ _bpftool() ;; esac ;; + link) + case $command in + show|list|pin) + case $prev in + id) + _bpftool_get_link_ids + return 0 + ;; + esac + ;; + esac + + local LINK_TYPE='id pinned' + case $command in + show|list) + [[ $prev != "$command" ]] && return 0 + COMPREPLY=( $( compgen -W "$LINK_TYPE" -- "$cur" ) ) + return 0 + ;; + pin) + if [[ $prev == "$command" ]]; then + COMPREPLY=( $( compgen -W "$LINK_TYPE" -- "$cur" ) ) + else + _filedir + fi + return 0 + ;; + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'help pin show list' -- "$cur" ) ) + ;; + esac + ;; esac } && complete -F _bpftool bpftool diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index bcaf55b59498..41a1346934a1 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -15,7 +15,6 @@ #include <linux/hashtable.h> #include <sys/types.h> #include <sys/stat.h> -#include <unistd.h> #include "json_writer.h" #include "main.h" diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c index 62c6a1d7cd18..1693c802bb20 100644 --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@ -31,42 +31,20 @@ static unsigned int query_flags; -static const char * const attach_type_strings[] = { - [BPF_CGROUP_INET_INGRESS] = "ingress", - [BPF_CGROUP_INET_EGRESS] = "egress", - [BPF_CGROUP_INET_SOCK_CREATE] = "sock_create", - [BPF_CGROUP_SOCK_OPS] = "sock_ops", - [BPF_CGROUP_DEVICE] = "device", - [BPF_CGROUP_INET4_BIND] = "bind4", - [BPF_CGROUP_INET6_BIND] = "bind6", - [BPF_CGROUP_INET4_CONNECT] = "connect4", - [BPF_CGROUP_INET6_CONNECT] = "connect6", - [BPF_CGROUP_INET4_POST_BIND] = "post_bind4", - [BPF_CGROUP_INET6_POST_BIND] = "post_bind6", - [BPF_CGROUP_UDP4_SENDMSG] = "sendmsg4", - [BPF_CGROUP_UDP6_SENDMSG] = "sendmsg6", - [BPF_CGROUP_SYSCTL] = "sysctl", - [BPF_CGROUP_UDP4_RECVMSG] = "recvmsg4", - [BPF_CGROUP_UDP6_RECVMSG] = "recvmsg6", - [BPF_CGROUP_GETSOCKOPT] = "getsockopt", - [BPF_CGROUP_SETSOCKOPT] = "setsockopt", - [__MAX_BPF_ATTACH_TYPE] = NULL, -}; - static enum bpf_attach_type parse_attach_type(const char *str) { enum bpf_attach_type type; for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) { - if (attach_type_strings[type] && - is_prefix(str, attach_type_strings[type])) + if (attach_type_name[type] && + is_prefix(str, attach_type_name[type])) return type; } return __MAX_BPF_ATTACH_TYPE; } -static int show_bpf_prog(int id, const char *attach_type_str, +static int show_bpf_prog(int id, enum bpf_attach_type attach_type, const char *attach_flags_str, int level) { @@ -86,18 +64,22 @@ static int show_bpf_prog(int id, const char *attach_type_str, if (json_output) { jsonw_start_object(json_wtr); jsonw_uint_field(json_wtr, "id", info.id); - jsonw_string_field(json_wtr, "attach_type", - attach_type_str); + if (attach_type < ARRAY_SIZE(attach_type_name)) + jsonw_string_field(json_wtr, "attach_type", + attach_type_name[attach_type]); + else + jsonw_uint_field(json_wtr, "attach_type", attach_type); jsonw_string_field(json_wtr, "attach_flags", attach_flags_str); jsonw_string_field(json_wtr, "name", info.name); jsonw_end_object(json_wtr); } else { - printf("%s%-8u %-15s %-15s %-15s\n", level ? " " : "", - info.id, - attach_type_str, - attach_flags_str, - info.name); + printf("%s%-8u ", level ? " " : "", info.id); + if (attach_type < ARRAY_SIZE(attach_type_name)) + printf("%-15s", attach_type_name[attach_type]); + else + printf("type %-10u", attach_type); + printf(" %-15s %-15s\n", attach_flags_str, info.name); } close(prog_fd); @@ -171,7 +153,7 @@ static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type, } for (iter = 0; iter < prog_cnt; iter++) - show_bpf_prog(prog_ids[iter], attach_type_strings[type], + show_bpf_prog(prog_ids[iter], type, attach_flags_str, level); return 0; diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index f2223dbdfb0a..c47bdc65de8e 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -262,6 +262,8 @@ int get_fd_type(int fd) return BPF_OBJ_MAP; else if (strstr(buf, "bpf-prog")) return BPF_OBJ_PROG; + else if (strstr(buf, "bpf-link")) + return BPF_OBJ_LINK; return BPF_OBJ_UNKNOWN; } diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index 88718ee6a438..f54347f55ee0 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -6,6 +6,9 @@ #include <string.h> #include <unistd.h> #include <net/if.h> +#ifdef USE_LIBCAP +#include <sys/capability.h> +#endif #include <sys/utsname.h> #include <sys/vfs.h> @@ -35,6 +38,11 @@ static const char * const helper_name[] = { #undef BPF_HELPER_MAKE_ENTRY +static bool full_mode; +#ifdef USE_LIBCAP +static bool run_as_unprivileged; +#endif + /* Miscellaneous utility functions */ static bool check_procfs(void) @@ -471,6 +479,13 @@ probe_prog_type(enum bpf_prog_type prog_type, bool *supported_types, } res = bpf_probe_prog_type(prog_type, ifindex); +#ifdef USE_LIBCAP + /* Probe may succeed even if program load fails, for unprivileged users + * check that we did not fail because of insufficient permissions + */ + if (run_as_unprivileged && errno == EPERM) + res = false; +#endif supported_types[prog_type] |= res; @@ -499,6 +514,10 @@ probe_map_type(enum bpf_map_type map_type, const char *define_prefix, res = bpf_probe_map_type(map_type, ifindex); + /* Probe result depends on the success of map creation, no additional + * check required for unprivileged users + */ + maxlen = sizeof(plain_desc) - strlen(plain_comment) - 1; if (strlen(map_type_name[map_type]) > maxlen) { p_info("map type name too long"); @@ -518,12 +537,19 @@ probe_helper_for_progtype(enum bpf_prog_type prog_type, bool supported_type, const char *define_prefix, unsigned int id, const char *ptype_name, __u32 ifindex) { - bool res; + bool res = false; - if (!supported_type) - res = false; - else + if (supported_type) { res = bpf_probe_helper(id, prog_type, ifindex); +#ifdef USE_LIBCAP + /* Probe may succeed even if program load fails, for + * unprivileged users check that we did not fail because of + * insufficient permissions + */ + if (run_as_unprivileged && errno == EPERM) + res = false; +#endif + } if (json_output) { if (res) @@ -540,8 +566,7 @@ probe_helper_for_progtype(enum bpf_prog_type prog_type, bool supported_type, static void probe_helpers_for_progtype(enum bpf_prog_type prog_type, bool supported_type, - const char *define_prefix, bool full_mode, - __u32 ifindex) + const char *define_prefix, __u32 ifindex) { const char *ptype_name = prog_type_name[prog_type]; char feat_name[128]; @@ -678,8 +703,7 @@ static void section_map_types(const char *define_prefix, __u32 ifindex) } static void -section_helpers(bool *supported_types, const char *define_prefix, - bool full_mode, __u32 ifindex) +section_helpers(bool *supported_types, const char *define_prefix, __u32 ifindex) { unsigned int i; @@ -704,8 +728,8 @@ section_helpers(bool *supported_types, const char *define_prefix, define_prefix, define_prefix, define_prefix, define_prefix); for (i = BPF_PROG_TYPE_UNSPEC + 1; i < ARRAY_SIZE(prog_type_name); i++) - probe_helpers_for_progtype(i, supported_types[i], - define_prefix, full_mode, ifindex); + probe_helpers_for_progtype(i, supported_types[i], define_prefix, + ifindex); print_end_section(); } @@ -720,23 +744,86 @@ static void section_misc(const char *define_prefix, __u32 ifindex) print_end_section(); } -static int do_probe(int argc, char **argv) +static int handle_perms(void) { - enum probe_component target = COMPONENT_UNSPEC; - const char *define_prefix = NULL; - bool supported_types[128] = {}; - bool full_mode = false; - __u32 ifindex = 0; - char *ifname; +#ifdef USE_LIBCAP + cap_value_t cap_list[1] = { CAP_SYS_ADMIN }; + bool has_sys_admin_cap = false; + cap_flag_value_t val; + int res = -1; + cap_t caps; + + caps = cap_get_proc(); + if (!caps) { + p_err("failed to get capabilities for process: %s", + strerror(errno)); + return -1; + } + + if (cap_get_flag(caps, CAP_SYS_ADMIN, CAP_EFFECTIVE, &val)) { + p_err("bug: failed to retrieve CAP_SYS_ADMIN status"); + goto exit_free; + } + if (val == CAP_SET) + has_sys_admin_cap = true; + + if (!run_as_unprivileged && !has_sys_admin_cap) { + p_err("full feature probing requires CAP_SYS_ADMIN, run as root or use 'unprivileged'"); + goto exit_free; + } + + if ((run_as_unprivileged && !has_sys_admin_cap) || + (!run_as_unprivileged && has_sys_admin_cap)) { + /* We are all good, exit now */ + res = 0; + goto exit_free; + } + /* if (run_as_unprivileged && has_sys_admin_cap), drop CAP_SYS_ADMIN */ + + if (cap_set_flag(caps, CAP_EFFECTIVE, ARRAY_SIZE(cap_list), cap_list, + CAP_CLEAR)) { + p_err("bug: failed to clear CAP_SYS_ADMIN from capabilities"); + goto exit_free; + } + + if (cap_set_proc(caps)) { + p_err("failed to drop CAP_SYS_ADMIN: %s", strerror(errno)); + goto exit_free; + } + + res = 0; + +exit_free: + if (cap_free(caps) && !res) { + p_err("failed to clear storage object for capabilities: %s", + strerror(errno)); + res = -1; + } + + return res; +#else /* Detection assumes user has sufficient privileges (CAP_SYS_ADMIN). - * Let's approximate, and restrict usage to root user only. + * We do not use libpcap so let's approximate, and restrict usage to + * root user only. */ if (geteuid()) { - p_err("please run this command as root user"); + p_err("full feature probing requires root privileges"); return -1; } + return 0; +#endif /* USE_LIBCAP */ +} + +static int do_probe(int argc, char **argv) +{ + enum probe_component target = COMPONENT_UNSPEC; + const char *define_prefix = NULL; + bool supported_types[128] = {}; + __u32 ifindex = 0; + char *ifname; + set_max_rlimit(); while (argc) { @@ -785,6 +872,14 @@ static int do_probe(int argc, char **argv) if (!REQ_ARGS(1)) return -1; define_prefix = GET_ARG(); + } else if (is_prefix(*argv, "unprivileged")) { +#ifdef USE_LIBCAP + run_as_unprivileged = true; + NEXT_ARG(); +#else + p_err("unprivileged run not supported, recompile bpftool with libcap"); + return -1; +#endif } else { p_err("expected no more arguments, 'kernel', 'dev', 'macros' or 'prefix', got: '%s'?", *argv); @@ -792,6 +887,12 @@ static int do_probe(int argc, char **argv) } } + /* Full feature detection requires CAP_SYS_ADMIN privilege. + * Let's approximate, and warn if user is not root. + */ + if (handle_perms()) + return -1; + if (json_output) { define_prefix = NULL; jsonw_start_object(json_wtr); @@ -803,7 +904,7 @@ static int do_probe(int argc, char **argv) goto exit_close_json; section_program_types(supported_types, define_prefix, ifindex); section_map_types(define_prefix, ifindex); - section_helpers(supported_types, define_prefix, full_mode, ifindex); + section_helpers(supported_types, define_prefix, ifindex); section_misc(define_prefix, ifindex); exit_close_json: @@ -822,7 +923,7 @@ static int do_help(int argc, char **argv) } fprintf(stderr, - "Usage: %s %s probe [COMPONENT] [full] [macros [prefix PREFIX]]\n" + "Usage: %s %s probe [COMPONENT] [full] [unprivileged] [macros [prefix PREFIX]]\n" " %s %s help\n" "\n" " COMPONENT := { kernel | dev NAME }\n" diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c index f8113b3646f5..0e5f0236cc76 100644 --- a/tools/bpf/bpftool/gen.c +++ b/tools/bpf/bpftool/gen.c @@ -17,7 +17,6 @@ #include <sys/types.h> #include <sys/stat.h> #include <sys/mman.h> -#include <unistd.h> #include <bpf/btf.h> #include "bpf/libbpf_internal.h" diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c index f7f5885aa3ba..e7e7eee9f172 100644 --- a/tools/bpf/bpftool/jit_disasm.c +++ b/tools/bpf/bpftool/jit_disasm.c @@ -15,7 +15,6 @@ #include <stdio.h> #include <stdarg.h> #include <stdint.h> -#include <stdio.h> #include <stdlib.h> #include <assert.h> #include <unistd.h> diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c new file mode 100644 index 000000000000..adc7dc431ed8 --- /dev/null +++ b/tools/bpf/bpftool/link.c @@ -0,0 +1,333 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2020 Facebook */ + +#include <errno.h> +#include <net/if.h> +#include <stdio.h> +#include <unistd.h> + +#include <bpf/bpf.h> + +#include "json_writer.h" +#include "main.h" + +static const char * const link_type_name[] = { + [BPF_LINK_TYPE_UNSPEC] = "unspec", + [BPF_LINK_TYPE_RAW_TRACEPOINT] = "raw_tracepoint", + [BPF_LINK_TYPE_TRACING] = "tracing", + [BPF_LINK_TYPE_CGROUP] = "cgroup", +}; + +static int link_parse_fd(int *argc, char ***argv) +{ + if (is_prefix(**argv, "id")) { + unsigned int id; + char *endptr; + + NEXT_ARGP(); + + id = strtoul(**argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as ID", **argv); + return -1; + } + NEXT_ARGP(); + + return bpf_link_get_fd_by_id(id); + } else if (is_prefix(**argv, "pinned")) { + char *path; + + NEXT_ARGP(); + + path = **argv; + NEXT_ARGP(); + + return open_obj_pinned_any(path, BPF_OBJ_LINK); + } + + p_err("expected 'id' or 'pinned', got: '%s'?", **argv); + return -1; +} + +static void +show_link_header_json(struct bpf_link_info *info, json_writer_t *wtr) +{ + jsonw_uint_field(wtr, "id", info->id); + if (info->type < ARRAY_SIZE(link_type_name)) + jsonw_string_field(wtr, "type", link_type_name[info->type]); + else + jsonw_uint_field(wtr, "type", info->type); + + jsonw_uint_field(json_wtr, "prog_id", info->prog_id); +} + +static int get_prog_info(int prog_id, struct bpf_prog_info *info) +{ + __u32 len = sizeof(*info); + int err, prog_fd; + + prog_fd = bpf_prog_get_fd_by_id(prog_id); + if (prog_fd < 0) + return prog_fd; + + memset(info, 0, sizeof(*info)); + err = bpf_obj_get_info_by_fd(prog_fd, info, &len); + if (err) + p_err("can't get prog info: %s", strerror(errno)); + close(prog_fd); + return err; +} + +static int show_link_close_json(int fd, struct bpf_link_info *info) +{ + struct bpf_prog_info prog_info; + int err; + + jsonw_start_object(json_wtr); + + show_link_header_json(info, json_wtr); + + switch (info->type) { + case BPF_LINK_TYPE_RAW_TRACEPOINT: + jsonw_string_field(json_wtr, "tp_name", + (const char *)info->raw_tracepoint.tp_name); + break; + case BPF_LINK_TYPE_TRACING: + err = get_prog_info(info->prog_id, &prog_info); + if (err) + return err; + + if (prog_info.type < ARRAY_SIZE(prog_type_name)) + jsonw_string_field(json_wtr, "prog_type", + prog_type_name[prog_info.type]); + else + jsonw_uint_field(json_wtr, "prog_type", + prog_info.type); + + if (info->tracing.attach_type < ARRAY_SIZE(attach_type_name)) + jsonw_string_field(json_wtr, "attach_type", + attach_type_name[info->tracing.attach_type]); + else + jsonw_uint_field(json_wtr, "attach_type", + info->tracing.attach_type); + break; + case BPF_LINK_TYPE_CGROUP: + jsonw_lluint_field(json_wtr, "cgroup_id", + info->cgroup.cgroup_id); + if (info->cgroup.attach_type < ARRAY_SIZE(attach_type_name)) + jsonw_string_field(json_wtr, "attach_type", + attach_type_name[info->cgroup.attach_type]); + else + jsonw_uint_field(json_wtr, "attach_type", + info->cgroup.attach_type); + break; + default: + break; + } + + if (!hash_empty(link_table.table)) { + struct pinned_obj *obj; + + jsonw_name(json_wtr, "pinned"); + jsonw_start_array(json_wtr); + hash_for_each_possible(link_table.table, obj, hash, info->id) { + if (obj->id == info->id) + jsonw_string(json_wtr, obj->path); + } + jsonw_end_array(json_wtr); + } + jsonw_end_object(json_wtr); + + return 0; +} + +static void show_link_header_plain(struct bpf_link_info *info) +{ + printf("%u: ", info->id); + if (info->type < ARRAY_SIZE(link_type_name)) + printf("%s ", link_type_name[info->type]); + else + printf("type %u ", info->type); + + printf("prog %u ", info->prog_id); +} + +static int show_link_close_plain(int fd, struct bpf_link_info *info) +{ + struct bpf_prog_info prog_info; + int err; + + show_link_header_plain(info); + + switch (info->type) { + case BPF_LINK_TYPE_RAW_TRACEPOINT: + printf("\n\ttp '%s' ", + (const char *)info->raw_tracepoint.tp_name); + break; + case BPF_LINK_TYPE_TRACING: + err = get_prog_info(info->prog_id, &prog_info); + if (err) + return err; + + if (prog_info.type < ARRAY_SIZE(prog_type_name)) + printf("\n\tprog_type %s ", + prog_type_name[prog_info.type]); + else + printf("\n\tprog_type %u ", prog_info.type); + + if (info->tracing.attach_type < ARRAY_SIZE(attach_type_name)) + printf("attach_type %s ", + attach_type_name[info->tracing.attach_type]); + else + printf("attach_type %u ", info->tracing.attach_type); + break; + case BPF_LINK_TYPE_CGROUP: + printf("\n\tcgroup_id %zu ", (size_t)info->cgroup.cgroup_id); + if (info->cgroup.attach_type < ARRAY_SIZE(attach_type_name)) + printf("attach_type %s ", + attach_type_name[info->cgroup.attach_type]); + else + printf("attach_type %u ", info->cgroup.attach_type); + break; + default: + break; + } + + if (!hash_empty(link_table.table)) { + struct pinned_obj *obj; + + hash_for_each_possible(link_table.table, obj, hash, info->id) { + if (obj->id == info->id) + printf("\n\tpinned %s", obj->path); + } + } + + printf("\n"); + + return 0; +} + +static int do_show_link(int fd) +{ + struct bpf_link_info info; + __u32 len = sizeof(info); + char raw_tp_name[256]; + int err; + + memset(&info, 0, sizeof(info)); +again: + err = bpf_obj_get_info_by_fd(fd, &info, &len); + if (err) { + p_err("can't get link info: %s", + strerror(errno)); + close(fd); + return err; + } + if (info.type == BPF_LINK_TYPE_RAW_TRACEPOINT && + !info.raw_tracepoint.tp_name) { + info.raw_tracepoint.tp_name = (unsigned long)&raw_tp_name; + info.raw_tracepoint.tp_name_len = sizeof(raw_tp_name); + goto again; + } + + if (json_output) + show_link_close_json(fd, &info); + else + show_link_close_plain(fd, &info); + + close(fd); + return 0; +} + +static int do_show(int argc, char **argv) +{ + __u32 id = 0; + int err, fd; + + if (show_pinned) + build_pinned_obj_table(&link_table, BPF_OBJ_LINK); + + if (argc == 2) { + fd = link_parse_fd(&argc, &argv); + if (fd < 0) + return fd; + return do_show_link(fd); + } + + if (argc) + return BAD_ARG(); + + if (json_output) + jsonw_start_array(json_wtr); + while (true) { + err = bpf_link_get_next_id(id, &id); + if (err) { + if (errno == ENOENT) + break; + p_err("can't get next link: %s%s", strerror(errno), + errno == EINVAL ? " -- kernel too old?" : ""); + break; + } + + fd = bpf_link_get_fd_by_id(id); + if (fd < 0) { + if (errno == ENOENT) + continue; + p_err("can't get link by id (%u): %s", + id, strerror(errno)); + break; + } + + err = do_show_link(fd); + if (err) + break; + } + if (json_output) + jsonw_end_array(json_wtr); + + return errno == ENOENT ? 0 : -1; +} + +static int do_pin(int argc, char **argv) +{ + int err; + + err = do_pin_any(argc, argv, link_parse_fd); + if (!err && json_output) + jsonw_null(json_wtr); + return err; +} + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %1$s %2$s { show | list } [LINK]\n" + " %1$s %2$s pin LINK FILE\n" + " %1$s %2$s help\n" + "\n" + " " HELP_SPEC_LINK "\n" + " " HELP_SPEC_PROGRAM "\n" + " " HELP_SPEC_OPTIONS "\n" + "", + bin_name, argv[-2]); + + return 0; +} + +static const struct cmd cmds[] = { + { "show", do_show }, + { "list", do_show }, + { "help", do_help }, + { "pin", do_pin }, + { 0 } +}; + +int do_link(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index 466c269eabdd..1413a154806e 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -30,6 +30,7 @@ bool verifier_logs; bool relaxed_maps; struct pinned_obj_table prog_table; struct pinned_obj_table map_table; +struct pinned_obj_table link_table; static void __noreturn clean_and_exit(int i) { @@ -58,7 +59,7 @@ static int do_help(int argc, char **argv) " %s batch file FILE\n" " %s version\n" "\n" - " OBJECT := { prog | map | cgroup | perf | net | feature | btf | gen | struct_ops }\n" + " OBJECT := { prog | map | link | cgroup | perf | net | feature | btf | gen | struct_ops }\n" " " HELP_SPEC_OPTIONS "\n" "", bin_name, bin_name, bin_name); @@ -215,6 +216,7 @@ static const struct cmd cmds[] = { { "batch", do_batch }, { "prog", do_prog }, { "map", do_map }, + { "link", do_link }, { "cgroup", do_cgroup }, { "perf", do_perf }, { "net", do_net }, @@ -364,6 +366,7 @@ int main(int argc, char **argv) hash_init(prog_table.table); hash_init(map_table.table); + hash_init(link_table.table); opterr = 0; while ((opt = getopt_long(argc, argv, "Vhpjfmnd", @@ -422,6 +425,7 @@ int main(int argc, char **argv) if (show_pinned) { delete_pinned_obj_table(&prog_table); delete_pinned_obj_table(&map_table); + delete_pinned_obj_table(&link_table); } return ret; diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 86f14ce26fd7..9b1fb81a8331 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -50,6 +50,8 @@ "\t {-m|--mapcompat} | {-n|--nomount} }" #define HELP_SPEC_MAP \ "MAP := { id MAP_ID | pinned FILE | name MAP_NAME }" +#define HELP_SPEC_LINK \ + "LINK := { id LINK_ID | pinned FILE }" static const char * const prog_type_name[] = { [BPF_PROG_TYPE_UNSPEC] = "unspec", @@ -83,6 +85,38 @@ static const char * const prog_type_name[] = { [BPF_PROG_TYPE_EXT] = "ext", }; +static const char * const attach_type_name[__MAX_BPF_ATTACH_TYPE] = { + [BPF_CGROUP_INET_INGRESS] = "ingress", + [BPF_CGROUP_INET_EGRESS] = "egress", + [BPF_CGROUP_INET_SOCK_CREATE] = "sock_create", + [BPF_CGROUP_SOCK_OPS] = "sock_ops", + [BPF_CGROUP_DEVICE] = "device", + [BPF_CGROUP_INET4_BIND] = "bind4", + [BPF_CGROUP_INET6_BIND] = "bind6", + [BPF_CGROUP_INET4_CONNECT] = "connect4", + [BPF_CGROUP_INET6_CONNECT] = "connect6", + [BPF_CGROUP_INET4_POST_BIND] = "post_bind4", + [BPF_CGROUP_INET6_POST_BIND] = "post_bind6", + [BPF_CGROUP_UDP4_SENDMSG] = "sendmsg4", + [BPF_CGROUP_UDP6_SENDMSG] = "sendmsg6", + [BPF_CGROUP_SYSCTL] = "sysctl", + [BPF_CGROUP_UDP4_RECVMSG] = "recvmsg4", + [BPF_CGROUP_UDP6_RECVMSG] = "recvmsg6", + [BPF_CGROUP_GETSOCKOPT] = "getsockopt", + [BPF_CGROUP_SETSOCKOPT] = "setsockopt", + + [BPF_SK_SKB_STREAM_PARSER] = "sk_skb_stream_parser", + [BPF_SK_SKB_STREAM_VERDICT] = "sk_skb_stream_verdict", + [BPF_SK_MSG_VERDICT] = "sk_msg_verdict", + [BPF_LIRC_MODE2] = "lirc_mode2", + [BPF_FLOW_DISSECTOR] = "flow_dissector", + [BPF_TRACE_RAW_TP] = "raw_tp", + [BPF_TRACE_FENTRY] = "fentry", + [BPF_TRACE_FEXIT] = "fexit", + [BPF_MODIFY_RETURN] = "mod_ret", + [BPF_LSM_MAC] = "lsm_mac", +}; + extern const char * const map_type_name[]; extern const size_t map_type_name_size; @@ -90,6 +124,7 @@ enum bpf_obj_type { BPF_OBJ_UNKNOWN, BPF_OBJ_PROG, BPF_OBJ_MAP, + BPF_OBJ_LINK, }; extern const char *bin_name; @@ -102,6 +137,7 @@ extern bool verifier_logs; extern bool relaxed_maps; extern struct pinned_obj_table prog_table; extern struct pinned_obj_table map_table; +extern struct pinned_obj_table link_table; void __printf(1, 2) p_err(const char *fmt, ...); void __printf(1, 2) p_info(const char *fmt, ...); @@ -153,6 +189,7 @@ int do_pin_fd(int fd, const char *name); int do_prog(int argc, char **arg); int do_map(int argc, char **arg); +int do_link(int argc, char **arg); int do_event_pipe(int argc, char **argv); int do_cgroup(int argc, char **arg); int do_perf(int argc, char **arg); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 7bbf1b65be10..b3643e27e264 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -113,6 +113,9 @@ enum bpf_cmd { BPF_MAP_DELETE_BATCH, BPF_LINK_CREATE, BPF_LINK_UPDATE, + BPF_LINK_GET_FD_BY_ID, + BPF_LINK_GET_NEXT_ID, + BPF_ENABLE_STATS, }; enum bpf_map_type { @@ -220,6 +223,15 @@ enum bpf_attach_type { #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE +enum bpf_link_type { + BPF_LINK_TYPE_UNSPEC = 0, + BPF_LINK_TYPE_RAW_TRACEPOINT = 1, + BPF_LINK_TYPE_TRACING = 2, + BPF_LINK_TYPE_CGROUP = 3, + + MAX_BPF_LINK_TYPE, +}; + /* cgroup-bpf attach flags used in BPF_PROG_ATTACH command * * NONE(default): No further bpf programs allowed in the subtree. @@ -379,6 +391,12 @@ enum { */ #define BPF_F_QUERY_EFFECTIVE (1U << 0) +/* type for BPF_ENABLE_STATS */ +enum bpf_stats_type { + /* enabled run_time_ns and run_cnt */ + BPF_STATS_RUN_TIME = 0, +}; + enum bpf_stack_build_id_status { /* user space need an empty entry to identify end of a trace */ BPF_STACK_BUILD_ID_EMPTY = 0, @@ -523,6 +541,7 @@ union bpf_attr { __u32 prog_id; __u32 map_id; __u32 btf_id; + __u32 link_id; }; __u32 next_id; __u32 open_flags; @@ -589,6 +608,10 @@ union bpf_attr { __u32 old_prog_fd; } link_update; + struct { /* struct used by BPF_ENABLE_STATS command */ + __u32 type; + } enable_stats; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF @@ -652,6 +675,8 @@ union bpf_attr { * u64 bpf_ktime_get_ns(void) * Description * Return the time elapsed since system boot, in nanoseconds. + * Does not include time the system was suspended. + * See: clock_gettime(CLOCK_MONOTONIC) * Return * Current *ktime*. * @@ -1562,7 +1587,7 @@ union bpf_attr { * Return * 0 * - * int bpf_setsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen) + * int bpf_setsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen) * Description * Emulate a call to **setsockopt()** on the socket associated to * *bpf_socket*, which must be a full socket. The *level* at @@ -1570,6 +1595,11 @@ union bpf_attr { * must be specified, see **setsockopt(2)** for more information. * The option value of length *optlen* is pointed by *optval*. * + * *bpf_socket* should be one of the following: + * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**. + * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT** + * and **BPF_CGROUP_INET6_CONNECT**. + * * This helper actually implements a subset of **setsockopt()**. * It supports the following *level*\ s: * @@ -1764,7 +1794,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_getsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen) + * int bpf_getsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen) * Description * Emulate a call to **getsockopt()** on the socket associated to * *bpf_socket*, which must be a full socket. The *level* at @@ -1773,6 +1803,11 @@ union bpf_attr { * The retrieved value is stored in the structure pointed by * *opval* and of length *optlen*. * + * *bpf_socket* should be one of the following: + * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**. + * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT** + * and **BPF_CGROUP_INET6_CONNECT**. + * * This helper actually implements a subset of **getsockopt()**. * It supports the following *level*\ s: * @@ -3025,6 +3060,14 @@ union bpf_attr { * * **-EOPNOTSUPP** Unsupported operation, for example a * call from outside of TC ingress. * * **-ESOCKTNOSUPPORT** Socket type not supported (reuseport). + * + * u64 bpf_ktime_get_boot_ns(void) + * Description + * Return the time elapsed since system boot, in nanoseconds. + * Does include the time the system was suspended. + * See: clock_gettime(CLOCK_BOOTTIME) + * Return + * Current *ktime*. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3151,7 +3194,8 @@ union bpf_attr { FN(xdp_output), \ FN(get_netns_cookie), \ FN(get_current_ancestor_cgroup_id), \ - FN(sk_assign), + FN(sk_assign), \ + FN(ktime_get_boot_ns), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -3598,6 +3642,25 @@ struct bpf_btf_info { __u32 id; } __attribute__((aligned(8))); +struct bpf_link_info { + __u32 type; + __u32 id; + __u32 prog_id; + union { + struct { + __aligned_u64 tp_name; /* in/out: tp_name buffer ptr */ + __u32 tp_name_len; /* in/out: tp_name buffer len */ + } raw_tracepoint; + struct { + __u32 attach_type; + } tracing; + struct { + __u64 cgroup_id; + __u32 attach_type; + } cgroup; + }; +} __attribute__((aligned(8))); + /* User bpf_sock_addr struct to access socket fields and sockaddr struct passed * by user and intended to be used by socket (e.g. to bind to, depends on * attach attach type). diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 5cc1b0785d18..43322f0d6c7f 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -721,6 +721,11 @@ int bpf_btf_get_next_id(__u32 start_id, __u32 *next_id) return bpf_obj_get_next_id(start_id, next_id, BPF_BTF_GET_NEXT_ID); } +int bpf_link_get_next_id(__u32 start_id, __u32 *next_id) +{ + return bpf_obj_get_next_id(start_id, next_id, BPF_LINK_GET_NEXT_ID); +} + int bpf_prog_get_fd_by_id(__u32 id) { union bpf_attr attr; @@ -751,13 +756,23 @@ int bpf_btf_get_fd_by_id(__u32 id) return sys_bpf(BPF_BTF_GET_FD_BY_ID, &attr, sizeof(attr)); } -int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len) +int bpf_link_get_fd_by_id(__u32 id) +{ + union bpf_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.link_id = id; + + return sys_bpf(BPF_LINK_GET_FD_BY_ID, &attr, sizeof(attr)); +} + +int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len) { union bpf_attr attr; int err; memset(&attr, 0, sizeof(attr)); - attr.info.bpf_fd = prog_fd; + attr.info.bpf_fd = bpf_fd; attr.info.info_len = *info_len; attr.info.info = ptr_to_u64(info); @@ -826,3 +841,13 @@ int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len, return err; } + +int bpf_enable_stats(enum bpf_stats_type type) +{ + union bpf_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.enable_stats.type = type; + + return sys_bpf(BPF_ENABLE_STATS, &attr, sizeof(attr)); +} diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 46d47afdd887..1901b2777854 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -216,10 +216,12 @@ LIBBPF_API int bpf_prog_test_run(int prog_fd, int repeat, void *data, LIBBPF_API int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id); LIBBPF_API int bpf_map_get_next_id(__u32 start_id, __u32 *next_id); LIBBPF_API int bpf_btf_get_next_id(__u32 start_id, __u32 *next_id); +LIBBPF_API int bpf_link_get_next_id(__u32 start_id, __u32 *next_id); LIBBPF_API int bpf_prog_get_fd_by_id(__u32 id); LIBBPF_API int bpf_map_get_fd_by_id(__u32 id); LIBBPF_API int bpf_btf_get_fd_by_id(__u32 id); -LIBBPF_API int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len); +LIBBPF_API int bpf_link_get_fd_by_id(__u32 id); +LIBBPF_API int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len); LIBBPF_API int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags, __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt); @@ -229,6 +231,7 @@ LIBBPF_API int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len, __u32 *prog_id, __u32 *fd_type, __u64 *probe_offset, __u64 *probe_addr); +LIBBPF_API int bpf_enable_stats(enum bpf_stats_type type); #ifdef __cplusplus } /* extern "C" */ diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index f69cc208778a..da00b87aa199 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -2,10 +2,17 @@ #ifndef __BPF_HELPERS__ #define __BPF_HELPERS__ +/* + * Note that bpf programs need to include either + * vmlinux.h (auto-generated from BTF) or linux/types.h + * in advance since bpf_helper_defs.h uses such types + * as __u64. + */ #include "bpf_helper_defs.h" #define __uint(name, val) int (*name)[val] #define __type(name, val) typeof(val) *name +#define __array(name, val) typeof(val) *name[] /* Helper macro to print out debug messages */ #define bpf_printk(fmt, ...) \ diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index 0c28ee82834b..de07e559a11d 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -658,7 +658,7 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) if (!btf_dump_is_blacklisted(d, id)) { btf_dump_emit_typedef_def(d, id, t, 0); btf_dump_printf(d, ";\n\n"); - }; + } tstate->fwd_emitted = 1; break; default: diff --git a/tools/lib/bpf/hashmap.c b/tools/lib/bpf/hashmap.c index 54c30c802070..cffb96202e0d 100644 --- a/tools/lib/bpf/hashmap.c +++ b/tools/lib/bpf/hashmap.c @@ -59,7 +59,14 @@ struct hashmap *hashmap__new(hashmap_hash_fn hash_fn, void hashmap__clear(struct hashmap *map) { + struct hashmap_entry *cur, *tmp; + int bkt; + + hashmap__for_each_entry_safe(map, cur, tmp, bkt) { + free(cur); + } free(map->buckets); + map->buckets = NULL; map->cap = map->cap_bits = map->sz = 0; } diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 8f480e29a6b0..977add1b73e2 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -310,6 +310,7 @@ struct bpf_map { int map_ifindex; int inner_map_fd; struct bpf_map_def def; + __u32 btf_var_idx; __u32 btf_key_type_id; __u32 btf_value_type_id; __u32 btf_vmlinux_value_type_id; @@ -318,6 +319,9 @@ struct bpf_map { enum libbpf_map_type libbpf_type; void *mmaped; struct bpf_struct_ops *st_ops; + struct bpf_map *inner_map; + void **init_slots; + int init_slots_sz; char *pin_path; bool pinned; bool reused; @@ -389,6 +393,7 @@ struct bpf_object { int nr_reloc_sects; int maps_shndx; int btf_maps_shndx; + __u32 btf_maps_sec_btf_id; int text_shndx; int symbols_shndx; int data_shndx; @@ -1914,109 +1919,54 @@ static int build_map_pin_path(struct bpf_map *map, const char *path) return 0; } -static int bpf_object__init_user_btf_map(struct bpf_object *obj, - const struct btf_type *sec, - int var_idx, int sec_idx, - const Elf_Data *data, bool strict, - const char *pin_root_path) + +static int parse_btf_map_def(struct bpf_object *obj, + struct bpf_map *map, + const struct btf_type *def, + bool strict, bool is_inner, + const char *pin_root_path) { - const struct btf_type *var, *def, *t; - const struct btf_var_secinfo *vi; - const struct btf_var *var_extra; + const struct btf_type *t; const struct btf_member *m; - const char *map_name; - struct bpf_map *map; int vlen, i; - vi = btf_var_secinfos(sec) + var_idx; - var = btf__type_by_id(obj->btf, vi->type); - var_extra = btf_var(var); - map_name = btf__name_by_offset(obj->btf, var->name_off); - vlen = btf_vlen(var); - - if (map_name == NULL || map_name[0] == '\0') { - pr_warn("map #%d: empty name.\n", var_idx); - return -EINVAL; - } - if ((__u64)vi->offset + vi->size > data->d_size) { - pr_warn("map '%s' BTF data is corrupted.\n", map_name); - return -EINVAL; - } - if (!btf_is_var(var)) { - pr_warn("map '%s': unexpected var kind %u.\n", - map_name, btf_kind(var)); - return -EINVAL; - } - if (var_extra->linkage != BTF_VAR_GLOBAL_ALLOCATED && - var_extra->linkage != BTF_VAR_STATIC) { - pr_warn("map '%s': unsupported var linkage %u.\n", - map_name, var_extra->linkage); - return -EOPNOTSUPP; - } - - def = skip_mods_and_typedefs(obj->btf, var->type, NULL); - if (!btf_is_struct(def)) { - pr_warn("map '%s': unexpected def kind %u.\n", - map_name, btf_kind(var)); - return -EINVAL; - } - if (def->size > vi->size) { - pr_warn("map '%s': invalid def size.\n", map_name); - return -EINVAL; - } - - map = bpf_object__add_map(obj); - if (IS_ERR(map)) - return PTR_ERR(map); - map->name = strdup(map_name); - if (!map->name) { - pr_warn("map '%s': failed to alloc map name.\n", map_name); - return -ENOMEM; - } - map->libbpf_type = LIBBPF_MAP_UNSPEC; - map->def.type = BPF_MAP_TYPE_UNSPEC; - map->sec_idx = sec_idx; - map->sec_offset = vi->offset; - pr_debug("map '%s': at sec_idx %d, offset %zu.\n", - map_name, map->sec_idx, map->sec_offset); - vlen = btf_vlen(def); m = btf_members(def); for (i = 0; i < vlen; i++, m++) { const char *name = btf__name_by_offset(obj->btf, m->name_off); if (!name) { - pr_warn("map '%s': invalid field #%d.\n", map_name, i); + pr_warn("map '%s': invalid field #%d.\n", map->name, i); return -EINVAL; } if (strcmp(name, "type") == 0) { - if (!get_map_field_int(map_name, obj->btf, m, + if (!get_map_field_int(map->name, obj->btf, m, &map->def.type)) return -EINVAL; pr_debug("map '%s': found type = %u.\n", - map_name, map->def.type); + map->name, map->def.type); } else if (strcmp(name, "max_entries") == 0) { - if (!get_map_field_int(map_name, obj->btf, m, + if (!get_map_field_int(map->name, obj->btf, m, &map->def.max_entries)) return -EINVAL; pr_debug("map '%s': found max_entries = %u.\n", - map_name, map->def.max_entries); + map->name, map->def.max_entries); } else if (strcmp(name, "map_flags") == 0) { - if (!get_map_field_int(map_name, obj->btf, m, + if (!get_map_field_int(map->name, obj->btf, m, &map->def.map_flags)) return -EINVAL; pr_debug("map '%s': found map_flags = %u.\n", - map_name, map->def.map_flags); + map->name, map->def.map_flags); } else if (strcmp(name, "key_size") == 0) { __u32 sz; - if (!get_map_field_int(map_name, obj->btf, m, &sz)) + if (!get_map_field_int(map->name, obj->btf, m, &sz)) return -EINVAL; pr_debug("map '%s': found key_size = %u.\n", - map_name, sz); + map->name, sz); if (map->def.key_size && map->def.key_size != sz) { pr_warn("map '%s': conflicting key size %u != %u.\n", - map_name, map->def.key_size, sz); + map->name, map->def.key_size, sz); return -EINVAL; } map->def.key_size = sz; @@ -2026,25 +1976,25 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, t = btf__type_by_id(obj->btf, m->type); if (!t) { pr_warn("map '%s': key type [%d] not found.\n", - map_name, m->type); + map->name, m->type); return -EINVAL; } if (!btf_is_ptr(t)) { pr_warn("map '%s': key spec is not PTR: %u.\n", - map_name, btf_kind(t)); + map->name, btf_kind(t)); return -EINVAL; } sz = btf__resolve_size(obj->btf, t->type); if (sz < 0) { pr_warn("map '%s': can't determine key size for type [%u]: %zd.\n", - map_name, t->type, (ssize_t)sz); + map->name, t->type, (ssize_t)sz); return sz; } pr_debug("map '%s': found key [%u], sz = %zd.\n", - map_name, t->type, (ssize_t)sz); + map->name, t->type, (ssize_t)sz); if (map->def.key_size && map->def.key_size != sz) { pr_warn("map '%s': conflicting key size %u != %zd.\n", - map_name, map->def.key_size, (ssize_t)sz); + map->name, map->def.key_size, (ssize_t)sz); return -EINVAL; } map->def.key_size = sz; @@ -2052,13 +2002,13 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, } else if (strcmp(name, "value_size") == 0) { __u32 sz; - if (!get_map_field_int(map_name, obj->btf, m, &sz)) + if (!get_map_field_int(map->name, obj->btf, m, &sz)) return -EINVAL; pr_debug("map '%s': found value_size = %u.\n", - map_name, sz); + map->name, sz); if (map->def.value_size && map->def.value_size != sz) { pr_warn("map '%s': conflicting value size %u != %u.\n", - map_name, map->def.value_size, sz); + map->name, map->def.value_size, sz); return -EINVAL; } map->def.value_size = sz; @@ -2068,71 +2018,207 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, t = btf__type_by_id(obj->btf, m->type); if (!t) { pr_warn("map '%s': value type [%d] not found.\n", - map_name, m->type); + map->name, m->type); return -EINVAL; } if (!btf_is_ptr(t)) { pr_warn("map '%s': value spec is not PTR: %u.\n", - map_name, btf_kind(t)); + map->name, btf_kind(t)); return -EINVAL; } sz = btf__resolve_size(obj->btf, t->type); if (sz < 0) { pr_warn("map '%s': can't determine value size for type [%u]: %zd.\n", - map_name, t->type, (ssize_t)sz); + map->name, t->type, (ssize_t)sz); return sz; } pr_debug("map '%s': found value [%u], sz = %zd.\n", - map_name, t->type, (ssize_t)sz); + map->name, t->type, (ssize_t)sz); if (map->def.value_size && map->def.value_size != sz) { pr_warn("map '%s': conflicting value size %u != %zd.\n", - map_name, map->def.value_size, (ssize_t)sz); + map->name, map->def.value_size, (ssize_t)sz); return -EINVAL; } map->def.value_size = sz; map->btf_value_type_id = t->type; + } + else if (strcmp(name, "values") == 0) { + int err; + + if (is_inner) { + pr_warn("map '%s': multi-level inner maps not supported.\n", + map->name); + return -ENOTSUP; + } + if (i != vlen - 1) { + pr_warn("map '%s': '%s' member should be last.\n", + map->name, name); + return -EINVAL; + } + if (!bpf_map_type__is_map_in_map(map->def.type)) { + pr_warn("map '%s': should be map-in-map.\n", + map->name); + return -ENOTSUP; + } + if (map->def.value_size && map->def.value_size != 4) { + pr_warn("map '%s': conflicting value size %u != 4.\n", + map->name, map->def.value_size); + return -EINVAL; + } + map->def.value_size = 4; + t = btf__type_by_id(obj->btf, m->type); + if (!t) { + pr_warn("map '%s': map-in-map inner type [%d] not found.\n", + map->name, m->type); + return -EINVAL; + } + if (!btf_is_array(t) || btf_array(t)->nelems) { + pr_warn("map '%s': map-in-map inner spec is not a zero-sized array.\n", + map->name); + return -EINVAL; + } + t = skip_mods_and_typedefs(obj->btf, btf_array(t)->type, + NULL); + if (!btf_is_ptr(t)) { + pr_warn("map '%s': map-in-map inner def is of unexpected kind %u.\n", + map->name, btf_kind(t)); + return -EINVAL; + } + t = skip_mods_and_typedefs(obj->btf, t->type, NULL); + if (!btf_is_struct(t)) { + pr_warn("map '%s': map-in-map inner def is of unexpected kind %u.\n", + map->name, btf_kind(t)); + return -EINVAL; + } + + map->inner_map = calloc(1, sizeof(*map->inner_map)); + if (!map->inner_map) + return -ENOMEM; + map->inner_map->sec_idx = obj->efile.btf_maps_shndx; + map->inner_map->name = malloc(strlen(map->name) + + sizeof(".inner") + 1); + if (!map->inner_map->name) + return -ENOMEM; + sprintf(map->inner_map->name, "%s.inner", map->name); + + err = parse_btf_map_def(obj, map->inner_map, t, strict, + true /* is_inner */, NULL); + if (err) + return err; } else if (strcmp(name, "pinning") == 0) { __u32 val; int err; - if (!get_map_field_int(map_name, obj->btf, m, &val)) + if (is_inner) { + pr_debug("map '%s': inner def can't be pinned.\n", + map->name); + return -EINVAL; + } + if (!get_map_field_int(map->name, obj->btf, m, &val)) return -EINVAL; pr_debug("map '%s': found pinning = %u.\n", - map_name, val); + map->name, val); if (val != LIBBPF_PIN_NONE && val != LIBBPF_PIN_BY_NAME) { pr_warn("map '%s': invalid pinning value %u.\n", - map_name, val); + map->name, val); return -EINVAL; } if (val == LIBBPF_PIN_BY_NAME) { err = build_map_pin_path(map, pin_root_path); if (err) { pr_warn("map '%s': couldn't build pin path.\n", - map_name); + map->name); return err; } } } else { if (strict) { pr_warn("map '%s': unknown field '%s'.\n", - map_name, name); + map->name, name); return -ENOTSUP; } pr_debug("map '%s': ignoring unknown field '%s'.\n", - map_name, name); + map->name, name); } } if (map->def.type == BPF_MAP_TYPE_UNSPEC) { - pr_warn("map '%s': map type isn't specified.\n", map_name); + pr_warn("map '%s': map type isn't specified.\n", map->name); return -EINVAL; } return 0; } +static int bpf_object__init_user_btf_map(struct bpf_object *obj, + const struct btf_type *sec, + int var_idx, int sec_idx, + const Elf_Data *data, bool strict, + const char *pin_root_path) +{ + const struct btf_type *var, *def; + const struct btf_var_secinfo *vi; + const struct btf_var *var_extra; + const char *map_name; + struct bpf_map *map; + + vi = btf_var_secinfos(sec) + var_idx; + var = btf__type_by_id(obj->btf, vi->type); + var_extra = btf_var(var); + map_name = btf__name_by_offset(obj->btf, var->name_off); + + if (map_name == NULL || map_name[0] == '\0') { + pr_warn("map #%d: empty name.\n", var_idx); + return -EINVAL; + } + if ((__u64)vi->offset + vi->size > data->d_size) { + pr_warn("map '%s' BTF data is corrupted.\n", map_name); + return -EINVAL; + } + if (!btf_is_var(var)) { + pr_warn("map '%s': unexpected var kind %u.\n", + map_name, btf_kind(var)); + return -EINVAL; + } + if (var_extra->linkage != BTF_VAR_GLOBAL_ALLOCATED && + var_extra->linkage != BTF_VAR_STATIC) { + pr_warn("map '%s': unsupported var linkage %u.\n", + map_name, var_extra->linkage); + return -EOPNOTSUPP; + } + + def = skip_mods_and_typedefs(obj->btf, var->type, NULL); + if (!btf_is_struct(def)) { + pr_warn("map '%s': unexpected def kind %u.\n", + map_name, btf_kind(var)); + return -EINVAL; + } + if (def->size > vi->size) { + pr_warn("map '%s': invalid def size.\n", map_name); + return -EINVAL; + } + + map = bpf_object__add_map(obj); + if (IS_ERR(map)) + return PTR_ERR(map); + map->name = strdup(map_name); + if (!map->name) { + pr_warn("map '%s': failed to alloc map name.\n", map_name); + return -ENOMEM; + } + map->libbpf_type = LIBBPF_MAP_UNSPEC; + map->def.type = BPF_MAP_TYPE_UNSPEC; + map->sec_idx = sec_idx; + map->sec_offset = vi->offset; + map->btf_var_idx = var_idx; + pr_debug("map '%s': at sec_idx %d, offset %zu.\n", + map_name, map->sec_idx, map->sec_offset); + + return parse_btf_map_def(obj, map, def, strict, false, pin_root_path); +} + static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict, const char *pin_root_path) { @@ -2163,6 +2249,7 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict, name = btf__name_by_offset(obj->btf, t->name_off); if (strcmp(name, MAPS_ELF_SEC) == 0) { sec = t; + obj->efile.btf_maps_sec_btf_id = i; break; } } @@ -2549,7 +2636,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj) /* Only do relo for section with exec instructions */ if (!section_have_execinstr(obj, sec) && - strcmp(name, ".rel" STRUCT_OPS_SEC)) { + strcmp(name, ".rel" STRUCT_OPS_SEC) && + strcmp(name, ".rel" MAPS_ELF_SEC)) { pr_debug("skip relo %s(%d) for section(%d)\n", name, idx, sec); continue; @@ -3482,124 +3570,181 @@ bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map) return 0; } +static void bpf_map__destroy(struct bpf_map *map); + +static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map) +{ + struct bpf_create_map_attr create_attr; + struct bpf_map_def *def = &map->def; + + memset(&create_attr, 0, sizeof(create_attr)); + + if (obj->caps.name) + create_attr.name = map->name; + create_attr.map_ifindex = map->map_ifindex; + create_attr.map_type = def->type; + create_attr.map_flags = def->map_flags; + create_attr.key_size = def->key_size; + create_attr.value_size = def->value_size; + + if (def->type == BPF_MAP_TYPE_PERF_EVENT_ARRAY && !def->max_entries) { + int nr_cpus; + + nr_cpus = libbpf_num_possible_cpus(); + if (nr_cpus < 0) { + pr_warn("map '%s': failed to determine number of system CPUs: %d\n", + map->name, nr_cpus); + return nr_cpus; + } + pr_debug("map '%s': setting size to %d\n", map->name, nr_cpus); + create_attr.max_entries = nr_cpus; + } else { + create_attr.max_entries = def->max_entries; + } + + if (bpf_map__is_struct_ops(map)) + create_attr.btf_vmlinux_value_type_id = + map->btf_vmlinux_value_type_id; + + create_attr.btf_fd = 0; + create_attr.btf_key_type_id = 0; + create_attr.btf_value_type_id = 0; + if (obj->btf && !bpf_map_find_btf_info(obj, map)) { + create_attr.btf_fd = btf__fd(obj->btf); + create_attr.btf_key_type_id = map->btf_key_type_id; + create_attr.btf_value_type_id = map->btf_value_type_id; + } + + if (bpf_map_type__is_map_in_map(def->type)) { + if (map->inner_map) { + int err; + + err = bpf_object__create_map(obj, map->inner_map); + if (err) { + pr_warn("map '%s': failed to create inner map: %d\n", + map->name, err); + return err; + } + map->inner_map_fd = bpf_map__fd(map->inner_map); + } + if (map->inner_map_fd >= 0) + create_attr.inner_map_fd = map->inner_map_fd; + } + + map->fd = bpf_create_map_xattr(&create_attr); + if (map->fd < 0 && (create_attr.btf_key_type_id || + create_attr.btf_value_type_id)) { + char *cp, errmsg[STRERR_BUFSIZE]; + int err = -errno; + + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); + pr_warn("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n", + map->name, cp, err); + create_attr.btf_fd = 0; + create_attr.btf_key_type_id = 0; + create_attr.btf_value_type_id = 0; + map->btf_key_type_id = 0; + map->btf_value_type_id = 0; + map->fd = bpf_create_map_xattr(&create_attr); + } + + if (map->fd < 0) + return -errno; + + if (bpf_map_type__is_map_in_map(def->type) && map->inner_map) { + bpf_map__destroy(map->inner_map); + zfree(&map->inner_map); + } + + return 0; +} + static int bpf_object__create_maps(struct bpf_object *obj) { - struct bpf_create_map_attr create_attr = {}; - int nr_cpus = 0; - unsigned int i; + struct bpf_map *map; + char *cp, errmsg[STRERR_BUFSIZE]; + unsigned int i, j; int err; for (i = 0; i < obj->nr_maps; i++) { - struct bpf_map *map = &obj->maps[i]; - struct bpf_map_def *def = &map->def; - char *cp, errmsg[STRERR_BUFSIZE]; - int *pfd = &map->fd; + map = &obj->maps[i]; if (map->pin_path) { err = bpf_object__reuse_map(map); if (err) { - pr_warn("error reusing pinned map %s\n", + pr_warn("map '%s': error reusing pinned map\n", map->name); - return err; + goto err_out; } } if (map->fd >= 0) { - pr_debug("skip map create (preset) %s: fd=%d\n", + pr_debug("map '%s': skipping creation (preset fd=%d)\n", map->name, map->fd); continue; } - if (obj->caps.name) - create_attr.name = map->name; - create_attr.map_ifindex = map->map_ifindex; - create_attr.map_type = def->type; - create_attr.map_flags = def->map_flags; - create_attr.key_size = def->key_size; - create_attr.value_size = def->value_size; - if (def->type == BPF_MAP_TYPE_PERF_EVENT_ARRAY && - !def->max_entries) { - if (!nr_cpus) - nr_cpus = libbpf_num_possible_cpus(); - if (nr_cpus < 0) { - pr_warn("failed to determine number of system CPUs: %d\n", - nr_cpus); - err = nr_cpus; - goto err_out; - } - pr_debug("map '%s': setting size to %d\n", - map->name, nr_cpus); - create_attr.max_entries = nr_cpus; - } else { - create_attr.max_entries = def->max_entries; - } - create_attr.btf_fd = 0; - create_attr.btf_key_type_id = 0; - create_attr.btf_value_type_id = 0; - if (bpf_map_type__is_map_in_map(def->type) && - map->inner_map_fd >= 0) - create_attr.inner_map_fd = map->inner_map_fd; - if (bpf_map__is_struct_ops(map)) - create_attr.btf_vmlinux_value_type_id = - map->btf_vmlinux_value_type_id; - - if (obj->btf && !bpf_map_find_btf_info(obj, map)) { - create_attr.btf_fd = btf__fd(obj->btf); - create_attr.btf_key_type_id = map->btf_key_type_id; - create_attr.btf_value_type_id = map->btf_value_type_id; - } - - *pfd = bpf_create_map_xattr(&create_attr); - if (*pfd < 0 && (create_attr.btf_key_type_id || - create_attr.btf_value_type_id)) { - err = -errno; - cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); - pr_warn("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n", - map->name, cp, err); - create_attr.btf_fd = 0; - create_attr.btf_key_type_id = 0; - create_attr.btf_value_type_id = 0; - map->btf_key_type_id = 0; - map->btf_value_type_id = 0; - *pfd = bpf_create_map_xattr(&create_attr); - } + err = bpf_object__create_map(obj, map); + if (err) + goto err_out; - if (*pfd < 0) { - size_t j; - - err = -errno; -err_out: - cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); - pr_warn("failed to create map (name: '%s'): %s(%d)\n", - map->name, cp, err); - pr_perm_msg(err); - for (j = 0; j < i; j++) - zclose(obj->maps[j].fd); - return err; - } + pr_debug("map '%s': created successfully, fd=%d\n", map->name, + map->fd); if (bpf_map__is_internal(map)) { err = bpf_object__populate_internal_map(obj, map); if (err < 0) { - zclose(*pfd); + zclose(map->fd); goto err_out; } } + if (map->init_slots_sz) { + for (j = 0; j < map->init_slots_sz; j++) { + const struct bpf_map *targ_map; + int fd; + + if (!map->init_slots[j]) + continue; + + targ_map = map->init_slots[j]; + fd = bpf_map__fd(targ_map); + err = bpf_map_update_elem(map->fd, &j, &fd, 0); + if (err) { + err = -errno; + pr_warn("map '%s': failed to initialize slot [%d] to map '%s' fd=%d: %d\n", + map->name, j, targ_map->name, + fd, err); + goto err_out; + } + pr_debug("map '%s': slot [%d] set to map '%s' fd=%d\n", + map->name, j, targ_map->name, fd); + } + zfree(&map->init_slots); + map->init_slots_sz = 0; + } + if (map->pin_path && !map->pinned) { err = bpf_map__pin(map, NULL); if (err) { - pr_warn("failed to auto-pin map name '%s' at '%s'\n", - map->name, map->pin_path); - return err; + pr_warn("map '%s': failed to auto-pin at '%s': %d\n", + map->name, map->pin_path, err); + zclose(map->fd); + goto err_out; } } - - pr_debug("created map %s: fd=%d\n", map->name, *pfd); } return 0; + +err_out: + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); + pr_warn("map '%s': failed to create: %s(%d)\n", map->name, cp, err); + pr_perm_msg(err); + for (j = 0; j < i; j++) + zclose(obj->maps[j].fd); + return err; } static int @@ -4851,9 +4996,118 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) return 0; } -static int bpf_object__collect_struct_ops_map_reloc(struct bpf_object *obj, - GElf_Shdr *shdr, - Elf_Data *data); +static int bpf_object__collect_st_ops_relos(struct bpf_object *obj, + GElf_Shdr *shdr, Elf_Data *data); + +static int bpf_object__collect_map_relos(struct bpf_object *obj, + GElf_Shdr *shdr, Elf_Data *data) +{ + int i, j, nrels, new_sz, ptr_sz = sizeof(void *); + const struct btf_var_secinfo *vi = NULL; + const struct btf_type *sec, *var, *def; + const struct btf_member *member; + struct bpf_map *map, *targ_map; + const char *name, *mname; + Elf_Data *symbols; + unsigned int moff; + GElf_Sym sym; + GElf_Rel rel; + void *tmp; + + if (!obj->efile.btf_maps_sec_btf_id || !obj->btf) + return -EINVAL; + sec = btf__type_by_id(obj->btf, obj->efile.btf_maps_sec_btf_id); + if (!sec) + return -EINVAL; + + symbols = obj->efile.symbols; + nrels = shdr->sh_size / shdr->sh_entsize; + for (i = 0; i < nrels; i++) { + if (!gelf_getrel(data, i, &rel)) { + pr_warn(".maps relo #%d: failed to get ELF relo\n", i); + return -LIBBPF_ERRNO__FORMAT; + } + if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) { + pr_warn(".maps relo #%d: symbol %zx not found\n", + i, (size_t)GELF_R_SYM(rel.r_info)); + return -LIBBPF_ERRNO__FORMAT; + } + name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, + sym.st_name) ? : "<?>"; + if (sym.st_shndx != obj->efile.btf_maps_shndx) { + pr_warn(".maps relo #%d: '%s' isn't a BTF-defined map\n", + i, name); + return -LIBBPF_ERRNO__RELOC; + } + + pr_debug(".maps relo #%d: for %zd value %zd rel.r_offset %zu name %d ('%s')\n", + i, (ssize_t)(rel.r_info >> 32), (size_t)sym.st_value, + (size_t)rel.r_offset, sym.st_name, name); + + for (j = 0; j < obj->nr_maps; j++) { + map = &obj->maps[j]; + if (map->sec_idx != obj->efile.btf_maps_shndx) + continue; + + vi = btf_var_secinfos(sec) + map->btf_var_idx; + if (vi->offset <= rel.r_offset && + rel.r_offset + sizeof(void *) <= vi->offset + vi->size) + break; + } + if (j == obj->nr_maps) { + pr_warn(".maps relo #%d: cannot find map '%s' at rel.r_offset %zu\n", + i, name, (size_t)rel.r_offset); + return -EINVAL; + } + + if (!bpf_map_type__is_map_in_map(map->def.type)) + return -EINVAL; + if (map->def.type == BPF_MAP_TYPE_HASH_OF_MAPS && + map->def.key_size != sizeof(int)) { + pr_warn(".maps relo #%d: hash-of-maps '%s' should have key size %zu.\n", + i, map->name, sizeof(int)); + return -EINVAL; + } + + targ_map = bpf_object__find_map_by_name(obj, name); + if (!targ_map) + return -ESRCH; + + var = btf__type_by_id(obj->btf, vi->type); + def = skip_mods_and_typedefs(obj->btf, var->type, NULL); + if (btf_vlen(def) == 0) + return -EINVAL; + member = btf_members(def) + btf_vlen(def) - 1; + mname = btf__name_by_offset(obj->btf, member->name_off); + if (strcmp(mname, "values")) + return -EINVAL; + + moff = btf_member_bit_offset(def, btf_vlen(def) - 1) / 8; + if (rel.r_offset - vi->offset < moff) + return -EINVAL; + + moff = rel.r_offset - vi->offset - moff; + if (moff % ptr_sz) + return -EINVAL; + moff /= ptr_sz; + if (moff >= map->init_slots_sz) { + new_sz = moff + 1; + tmp = realloc(map->init_slots, new_sz * ptr_sz); + if (!tmp) + return -ENOMEM; + map->init_slots = tmp; + memset(map->init_slots + map->init_slots_sz, 0, + (new_sz - map->init_slots_sz) * ptr_sz); + map->init_slots_sz = new_sz; + } + map->init_slots[moff] = targ_map; + + pr_debug(".maps relo #%d: map '%s' slot [%d] points to map '%s'\n", + i, map->name, moff, name); + } + + return 0; +} static int bpf_object__collect_reloc(struct bpf_object *obj) { @@ -4876,21 +5130,17 @@ static int bpf_object__collect_reloc(struct bpf_object *obj) } if (idx == obj->efile.st_ops_shndx) { - err = bpf_object__collect_struct_ops_map_reloc(obj, - shdr, - data); - if (err) - return err; - continue; - } - - prog = bpf_object__find_prog_by_idx(obj, idx); - if (!prog) { - pr_warn("relocation failed: no section(%d)\n", idx); - return -LIBBPF_ERRNO__RELOC; + err = bpf_object__collect_st_ops_relos(obj, shdr, data); + } else if (idx == obj->efile.btf_maps_shndx) { + err = bpf_object__collect_map_relos(obj, shdr, data); + } else { + prog = bpf_object__find_prog_by_idx(obj, idx); + if (!prog) { + pr_warn("relocation failed: no prog in section(%d)\n", idx); + return -LIBBPF_ERRNO__RELOC; + } + err = bpf_program__collect_reloc(prog, shdr, data, obj); } - - err = bpf_program__collect_reloc(prog, shdr, data, obj); if (err) return err; } @@ -5955,6 +6205,40 @@ int bpf_object__pin(struct bpf_object *obj, const char *path) return 0; } +static void bpf_map__destroy(struct bpf_map *map) +{ + if (map->clear_priv) + map->clear_priv(map, map->priv); + map->priv = NULL; + map->clear_priv = NULL; + + if (map->inner_map) { + bpf_map__destroy(map->inner_map); + zfree(&map->inner_map); + } + + zfree(&map->init_slots); + map->init_slots_sz = 0; + + if (map->mmaped) { + munmap(map->mmaped, bpf_map_mmap_sz(map)); + map->mmaped = NULL; + } + + if (map->st_ops) { + zfree(&map->st_ops->data); + zfree(&map->st_ops->progs); + zfree(&map->st_ops->kern_func_off); + zfree(&map->st_ops); + } + + zfree(&map->name); + zfree(&map->pin_path); + + if (map->fd >= 0) + zclose(map->fd); +} + void bpf_object__close(struct bpf_object *obj) { size_t i; @@ -5970,29 +6254,8 @@ void bpf_object__close(struct bpf_object *obj) btf__free(obj->btf); btf_ext__free(obj->btf_ext); - for (i = 0; i < obj->nr_maps; i++) { - struct bpf_map *map = &obj->maps[i]; - - if (map->clear_priv) - map->clear_priv(map, map->priv); - map->priv = NULL; - map->clear_priv = NULL; - - if (map->mmaped) { - munmap(map->mmaped, bpf_map_mmap_sz(map)); - map->mmaped = NULL; - } - - if (map->st_ops) { - zfree(&map->st_ops->data); - zfree(&map->st_ops->progs); - zfree(&map->st_ops->kern_func_off); - zfree(&map->st_ops); - } - - zfree(&map->name); - zfree(&map->pin_path); - } + for (i = 0; i < obj->nr_maps; i++) + bpf_map__destroy(&obj->maps[i]); zfree(&obj->kconfig); zfree(&obj->externs); @@ -6516,9 +6779,8 @@ static struct bpf_map *find_struct_ops_map_by_offset(struct bpf_object *obj, } /* Collect the reloc from ELF and populate the st_ops->progs[] */ -static int bpf_object__collect_struct_ops_map_reloc(struct bpf_object *obj, - GElf_Shdr *shdr, - Elf_Data *data) +static int bpf_object__collect_st_ops_relos(struct bpf_object *obj, + GElf_Shdr *shdr, Elf_Data *data) { const struct btf_member *member; struct bpf_struct_ops *st_ops; @@ -6672,6 +6934,7 @@ int libbpf_find_vmlinux_btf_id(const char *name, enum bpf_attach_type attach_type) { struct btf *btf; + int err; btf = libbpf_find_kernel_btf(); if (IS_ERR(btf)) { @@ -6679,7 +6942,9 @@ int libbpf_find_vmlinux_btf_id(const char *name, return -EINVAL; } - return __find_vmlinux_btf_id(btf, name, attach_type); + err = __find_vmlinux_btf_id(btf, name, attach_type); + btf__free(btf); + return err; } static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd) @@ -7006,7 +7271,7 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, err = bpf_object__load(obj); if (err) { bpf_object__close(obj); - return -EINVAL; + return err; } *pobj = obj; diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index bb8831605b25..e03bd4db827e 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -254,3 +254,10 @@ LIBBPF_0.0.8 { bpf_program__set_lsm; bpf_set_link_xdp_fd_opts; } LIBBPF_0.0.7; + +LIBBPF_0.0.9 { + global: + bpf_enable_stats; + bpf_link_get_fd_by_id; + bpf_link_get_next_id; +} LIBBPF_0.0.8; diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index c30079c86998..3ff031972975 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -30,8 +30,6 @@ test_tcpnotify_user test_libbpf test_tcp_check_syncookie_user test_sysctl -test_hashmap -test_btf_dump test_current_pid_tgid_new_ns xdping test_cpp @@ -39,4 +37,4 @@ test_cpp /no_alu32 /bpf_gcc /tools - +/runqslower diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 7729892e0b04..3d942be23d09 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -20,9 +20,10 @@ CLANG ?= clang LLC ?= llc LLVM_OBJCOPY ?= llvm-objcopy BPF_GCC ?= $(shell command -v bpf-gcc;) -CFLAGS += -g -rdynamic -Wall -O2 $(GENFLAGS) -I$(CURDIR) \ - -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) -I$(TOOLSINCDIR) \ - -I$(APIDIR) \ +SAN_CFLAGS ?= +CFLAGS += -g -rdynamic -Wall -O2 $(GENFLAGS) $(SAN_CFLAGS) \ + -I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) \ + -I$(TOOLSINCDIR) -I$(APIDIR) \ -Dbpf_prog_load=bpf_prog_test_load \ -Dbpf_load_program=bpf_test_load_program LDLIBS += -lcap -lelf -lz -lrt -lpthread @@ -32,7 +33,7 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \ test_sock test_btf test_sockmap get_cgroup_id_user test_socket_cookie \ test_cgroup_storage \ - test_netcnt test_tcpnotify_user test_sock_fields test_sysctl test_hashmap \ + test_netcnt test_tcpnotify_user test_sock_fields test_sysctl \ test_progs-no_alu32 \ test_current_pid_tgid_new_ns @@ -141,7 +142,8 @@ VMLINUX_BTF := $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS)))) $(OUTPUT)/runqslower: $(BPFOBJ) $(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/runqslower \ OUTPUT=$(SCRATCH_DIR)/ VMLINUX_BTF=$(VMLINUX_BTF) \ - BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR) + BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR) && \ + cp $(SCRATCH_DIR)/runqslower $@ $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/test_stub.o $(BPFOBJ) @@ -241,7 +243,7 @@ define GCC_BPF_BUILD_RULE $(BPF_GCC) $3 $4 -O2 -c $1 -o $2 endef -SKEL_BLACKLIST := btf__% test_pinning_invalid.c +SKEL_BLACKLIST := btf__% test_pinning_invalid.c test_sk_assign.c # Set up extra TRUNNER_XXX "temporary" variables in the environment (relies on # $eval()) and pass control to DEFINE_TEST_RUNNER_RULES. @@ -323,7 +325,7 @@ $(TRUNNER_TEST_OBJS): $(TRUNNER_OUTPUT)/%.test.o: \ $(TRUNNER_BPF_SKELS) \ $$(BPFOBJ) | $(TRUNNER_OUTPUT) $$(call msg,TEST-OBJ,$(TRUNNER_BINARY),$$@) - cd $$(@D) && $$(CC) $$(CFLAGS) -c $(CURDIR)/$$< $$(LDLIBS) -o $$(@F) + cd $$(@D) && $$(CC) -I. $$(CFLAGS) -c $(CURDIR)/$$< $$(LDLIBS) -o $$(@F) $(TRUNNER_EXTRA_OBJS): $(TRUNNER_OUTPUT)/%.o: \ %.c \ diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c index f10029821e16..7afa4160416f 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c @@ -1,26 +1,30 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#define nr_iters 2 + void test_bpf_obj_id(void) { const __u64 array_magic_value = 0xfaceb00c; const __u32 array_key = 0; - const int nr_iters = 2; const char *file = "./test_obj_id.o"; const char *expected_prog_name = "test_obj_id"; const char *expected_map_name = "test_map_id"; const __u64 nsec_per_sec = 1000000000; - struct bpf_object *objs[nr_iters]; + struct bpf_object *objs[nr_iters] = {}; + struct bpf_link *links[nr_iters] = {}; + struct bpf_program *prog; int prog_fds[nr_iters], map_fds[nr_iters]; /* +1 to test for the info_len returned by kernel */ struct bpf_prog_info prog_infos[nr_iters + 1]; struct bpf_map_info map_infos[nr_iters + 1]; + struct bpf_link_info link_infos[nr_iters + 1]; /* Each prog only uses one map. +1 to test nr_map_ids * returned by kernel. */ __u32 map_ids[nr_iters + 1]; - char jited_insns[128], xlated_insns[128], zeros[128]; + char jited_insns[128], xlated_insns[128], zeros[128], tp_name[128]; __u32 i, next_id, info_len, nr_id_found, duration = 0; struct timespec real_time_ts, boot_time_ts; int err = 0; @@ -36,14 +40,15 @@ void test_bpf_obj_id(void) CHECK(err >= 0 || errno != ENOENT, "get-fd-by-notexist-map-id", "err %d errno %d\n", err, errno); - for (i = 0; i < nr_iters; i++) - objs[i] = NULL; + err = bpf_link_get_fd_by_id(0); + CHECK(err >= 0 || errno != ENOENT, + "get-fd-by-notexist-link-id", "err %d errno %d\n", err, errno); /* Check bpf_obj_get_info_by_fd() */ bzero(zeros, sizeof(zeros)); for (i = 0; i < nr_iters; i++) { now = time(NULL); - err = bpf_prog_load(file, BPF_PROG_TYPE_SOCKET_FILTER, + err = bpf_prog_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT, &objs[i], &prog_fds[i]); /* test_obj_id.o is a dumb prog. It should never fail * to load. @@ -60,6 +65,17 @@ void test_bpf_obj_id(void) if (CHECK_FAIL(err)) goto done; + prog = bpf_object__find_program_by_title(objs[i], + "raw_tp/sys_enter"); + if (CHECK_FAIL(!prog)) + goto done; + links[i] = bpf_program__attach(prog); + err = libbpf_get_error(links[i]); + if (CHECK(err, "prog_attach", "prog #%d, err %d\n", i, err)) { + links[i] = NULL; + goto done; + } + /* Check getting map info */ info_len = sizeof(struct bpf_map_info) * 2; bzero(&map_infos[i], info_len); @@ -107,7 +123,7 @@ void test_bpf_obj_id(void) load_time = (real_time_ts.tv_sec - boot_time_ts.tv_sec) + (prog_infos[i].load_time / nsec_per_sec); if (CHECK(err || - prog_infos[i].type != BPF_PROG_TYPE_SOCKET_FILTER || + prog_infos[i].type != BPF_PROG_TYPE_RAW_TRACEPOINT || info_len != sizeof(struct bpf_prog_info) || (env.jit_enabled && !prog_infos[i].jited_prog_len) || (env.jit_enabled && @@ -120,7 +136,11 @@ void test_bpf_obj_id(void) *(int *)(long)prog_infos[i].map_ids != map_infos[i].id || strcmp((char *)prog_infos[i].name, expected_prog_name), "get-prog-info(fd)", - "err %d errno %d i %d type %d(%d) info_len %u(%zu) jit_enabled %d jited_prog_len %u xlated_prog_len %u jited_prog %d xlated_prog %d load_time %lu(%lu) uid %u(%u) nr_map_ids %u(%u) map_id %u(%u) name %s(%s)\n", + "err %d errno %d i %d type %d(%d) info_len %u(%zu) " + "jit_enabled %d jited_prog_len %u xlated_prog_len %u " + "jited_prog %d xlated_prog %d load_time %lu(%lu) " + "uid %u(%u) nr_map_ids %u(%u) map_id %u(%u) " + "name %s(%s)\n", err, errno, i, prog_infos[i].type, BPF_PROG_TYPE_SOCKET_FILTER, info_len, sizeof(struct bpf_prog_info), @@ -135,6 +155,33 @@ void test_bpf_obj_id(void) *(int *)(long)prog_infos[i].map_ids, map_infos[i].id, prog_infos[i].name, expected_prog_name)) goto done; + + /* Check getting link info */ + info_len = sizeof(struct bpf_link_info) * 2; + bzero(&link_infos[i], info_len); + link_infos[i].raw_tracepoint.tp_name = (__u64)&tp_name; + link_infos[i].raw_tracepoint.tp_name_len = sizeof(tp_name); + err = bpf_obj_get_info_by_fd(bpf_link__fd(links[i]), + &link_infos[i], &info_len); + if (CHECK(err || + link_infos[i].type != BPF_LINK_TYPE_RAW_TRACEPOINT || + link_infos[i].prog_id != prog_infos[i].id || + link_infos[i].raw_tracepoint.tp_name != (__u64)&tp_name || + strcmp((char *)link_infos[i].raw_tracepoint.tp_name, + "sys_enter") || + info_len != sizeof(struct bpf_link_info), + "get-link-info(fd)", + "err %d errno %d info_len %u(%zu) type %d(%d) id %d " + "prog_id %d (%d) tp_name %s(%s)\n", + err, errno, + info_len, sizeof(struct bpf_link_info), + link_infos[i].type, BPF_LINK_TYPE_RAW_TRACEPOINT, + link_infos[i].id, + link_infos[i].prog_id, prog_infos[i].id, + (char *)link_infos[i].raw_tracepoint.tp_name, + "sys_enter")) + goto done; + } /* Check bpf_prog_get_next_id() */ @@ -247,7 +294,52 @@ void test_bpf_obj_id(void) "nr_id_found %u(%u)\n", nr_id_found, nr_iters); + /* Check bpf_link_get_next_id() */ + nr_id_found = 0; + next_id = 0; + while (!bpf_link_get_next_id(next_id, &next_id)) { + struct bpf_link_info link_info; + int link_fd, cmp_res; + + info_len = sizeof(link_info); + memset(&link_info, 0, info_len); + + link_fd = bpf_link_get_fd_by_id(next_id); + if (link_fd < 0 && errno == ENOENT) + /* The bpf_link is in the dead row */ + continue; + if (CHECK(link_fd < 0, "get-link-fd(next_id)", + "link_fd %d next_id %u errno %d\n", + link_fd, next_id, errno)) + break; + + for (i = 0; i < nr_iters; i++) + if (link_infos[i].id == next_id) + break; + + if (i == nr_iters) + continue; + + nr_id_found++; + + err = bpf_obj_get_info_by_fd(link_fd, &link_info, &info_len); + cmp_res = memcmp(&link_info, &link_infos[i], + offsetof(struct bpf_link_info, raw_tracepoint)); + CHECK(err || info_len != sizeof(link_info) || cmp_res, + "check get-link-info(next_id->fd)", + "err %d errno %d info_len %u(%zu) memcmp %d\n", + err, errno, info_len, sizeof(struct bpf_link_info), + cmp_res); + + close(link_fd); + } + CHECK(nr_id_found != nr_iters, + "check total link id found by get_next_id", + "nr_id_found %u(%u)\n", nr_id_found, nr_iters); + done: - for (i = 0; i < nr_iters; i++) + for (i = 0; i < nr_iters; i++) { + bpf_link__destroy(links[i]); bpf_object__close(objs[i]); + } } diff --git a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c new file mode 100644 index 000000000000..f7ee8fa377ad --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c @@ -0,0 +1,49 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include <test_progs.h> + +#include "test_btf_map_in_map.skel.h" + +void test_btf_map_in_map(void) +{ + int duration = 0, err, key = 0, val; + struct test_btf_map_in_map* skel; + + skel = test_btf_map_in_map__open_and_load(); + if (CHECK(!skel, "skel_open", "failed to open&load skeleton\n")) + return; + + err = test_btf_map_in_map__attach(skel); + if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) + goto cleanup; + + /* inner1 = input, inner2 = input + 1 */ + val = bpf_map__fd(skel->maps.inner_map1); + bpf_map_update_elem(bpf_map__fd(skel->maps.outer_arr), &key, &val, 0); + val = bpf_map__fd(skel->maps.inner_map2); + bpf_map_update_elem(bpf_map__fd(skel->maps.outer_hash), &key, &val, 0); + skel->bss->input = 1; + usleep(1); + + bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map1), &key, &val); + CHECK(val != 1, "inner1", "got %d != exp %d\n", val, 1); + bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map2), &key, &val); + CHECK(val != 2, "inner2", "got %d != exp %d\n", val, 2); + + /* inner1 = input + 1, inner2 = input */ + val = bpf_map__fd(skel->maps.inner_map2); + bpf_map_update_elem(bpf_map__fd(skel->maps.outer_arr), &key, &val, 0); + val = bpf_map__fd(skel->maps.inner_map1); + bpf_map_update_elem(bpf_map__fd(skel->maps.outer_hash), &key, &val, 0); + skel->bss->input = 3; + usleep(1); + + bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map1), &key, &val); + CHECK(val != 4, "inner1", "got %d != exp %d\n", val, 4); + bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map2), &key, &val); + CHECK(val != 3, "inner2", "got %d != exp %d\n", val, 3); + +cleanup: + test_btf_map_in_map__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/cls_redirect.c b/tools/testing/selftests/bpf/prog_tests/cls_redirect.c new file mode 100644 index 000000000000..f259085cca6a --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cls_redirect.c @@ -0,0 +1,456 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +// Copyright (c) 2020 Cloudflare + +#define _GNU_SOURCE + +#include <arpa/inet.h> +#include <string.h> + +#include <linux/pkt_cls.h> + +#include <test_progs.h> + +#include "progs/test_cls_redirect.h" +#include "test_cls_redirect.skel.h" + +#define ENCAP_IP INADDR_LOOPBACK +#define ENCAP_PORT (1234) + +struct addr_port { + in_port_t port; + union { + struct in_addr in_addr; + struct in6_addr in6_addr; + }; +}; + +struct tuple { + int family; + struct addr_port src; + struct addr_port dst; +}; + +static int start_server(const struct sockaddr *addr, socklen_t len, int type) +{ + int fd = socket(addr->sa_family, type, 0); + if (CHECK_FAIL(fd == -1)) + return -1; + if (CHECK_FAIL(bind(fd, addr, len) == -1)) + goto err; + if (type == SOCK_STREAM && CHECK_FAIL(listen(fd, 128) == -1)) + goto err; + + return fd; + +err: + close(fd); + return -1; +} + +static int connect_to_server(const struct sockaddr *addr, socklen_t len, + int type) +{ + int fd = socket(addr->sa_family, type, 0); + if (CHECK_FAIL(fd == -1)) + return -1; + if (CHECK_FAIL(connect(fd, addr, len))) + goto err; + + return fd; + +err: + close(fd); + return -1; +} + +static bool fill_addr_port(const struct sockaddr *sa, struct addr_port *ap) +{ + const struct sockaddr_in6 *in6; + const struct sockaddr_in *in; + + switch (sa->sa_family) { + case AF_INET: + in = (const struct sockaddr_in *)sa; + ap->in_addr = in->sin_addr; + ap->port = in->sin_port; + return true; + + case AF_INET6: + in6 = (const struct sockaddr_in6 *)sa; + ap->in6_addr = in6->sin6_addr; + ap->port = in6->sin6_port; + return true; + + default: + return false; + } +} + +static bool set_up_conn(const struct sockaddr *addr, socklen_t len, int type, + int *server, int *conn, struct tuple *tuple) +{ + struct sockaddr_storage ss; + socklen_t slen = sizeof(ss); + struct sockaddr *sa = (struct sockaddr *)&ss; + + *server = start_server(addr, len, type); + if (*server < 0) + return false; + + if (CHECK_FAIL(getsockname(*server, sa, &slen))) + goto close_server; + + *conn = connect_to_server(sa, slen, type); + if (*conn < 0) + goto close_server; + + /* We want to simulate packets arriving at conn, so we have to + * swap src and dst. + */ + slen = sizeof(ss); + if (CHECK_FAIL(getsockname(*conn, sa, &slen))) + goto close_conn; + + if (CHECK_FAIL(!fill_addr_port(sa, &tuple->dst))) + goto close_conn; + + slen = sizeof(ss); + if (CHECK_FAIL(getpeername(*conn, sa, &slen))) + goto close_conn; + + if (CHECK_FAIL(!fill_addr_port(sa, &tuple->src))) + goto close_conn; + + tuple->family = ss.ss_family; + return true; + +close_conn: + close(*conn); + *conn = -1; +close_server: + close(*server); + *server = -1; + return false; +} + +static socklen_t prepare_addr(struct sockaddr_storage *addr, int family) +{ + struct sockaddr_in *addr4; + struct sockaddr_in6 *addr6; + + switch (family) { + case AF_INET: + addr4 = (struct sockaddr_in *)addr; + memset(addr4, 0, sizeof(*addr4)); + addr4->sin_family = family; + addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK); + return sizeof(*addr4); + case AF_INET6: + addr6 = (struct sockaddr_in6 *)addr; + memset(addr6, 0, sizeof(*addr6)); + addr6->sin6_family = family; + addr6->sin6_addr = in6addr_loopback; + return sizeof(*addr6); + default: + fprintf(stderr, "Invalid family %d", family); + return 0; + } +} + +static bool was_decapsulated(struct bpf_prog_test_run_attr *tattr) +{ + return tattr->data_size_out < tattr->data_size_in; +} + +enum type { + UDP, + TCP, + __NR_KIND, +}; + +enum hops { + NO_HOPS, + ONE_HOP, +}; + +enum flags { + NONE, + SYN, + ACK, +}; + +enum conn { + KNOWN_CONN, + UNKNOWN_CONN, +}; + +enum result { + ACCEPT, + FORWARD, +}; + +struct test_cfg { + enum type type; + enum result result; + enum conn conn; + enum hops hops; + enum flags flags; +}; + +static int test_str(void *buf, size_t len, const struct test_cfg *test, + int family) +{ + const char *family_str, *type, *conn, *hops, *result, *flags; + + family_str = "IPv4"; + if (family == AF_INET6) + family_str = "IPv6"; + + type = "TCP"; + if (test->type == UDP) + type = "UDP"; + + conn = "known"; + if (test->conn == UNKNOWN_CONN) + conn = "unknown"; + + hops = "no hops"; + if (test->hops == ONE_HOP) + hops = "one hop"; + + result = "accept"; + if (test->result == FORWARD) + result = "forward"; + + flags = "none"; + if (test->flags == SYN) + flags = "SYN"; + else if (test->flags == ACK) + flags = "ACK"; + + return snprintf(buf, len, "%s %s %s %s (%s, flags: %s)", family_str, + type, result, conn, hops, flags); +} + +static struct test_cfg tests[] = { + { TCP, ACCEPT, UNKNOWN_CONN, NO_HOPS, SYN }, + { TCP, ACCEPT, UNKNOWN_CONN, NO_HOPS, ACK }, + { TCP, FORWARD, UNKNOWN_CONN, ONE_HOP, ACK }, + { TCP, ACCEPT, KNOWN_CONN, ONE_HOP, ACK }, + { UDP, ACCEPT, UNKNOWN_CONN, NO_HOPS, NONE }, + { UDP, FORWARD, UNKNOWN_CONN, ONE_HOP, NONE }, + { UDP, ACCEPT, KNOWN_CONN, ONE_HOP, NONE }, +}; + +static void encap_init(encap_headers_t *encap, uint8_t hop_count, uint8_t proto) +{ + const uint8_t hlen = + (sizeof(struct guehdr) / sizeof(uint32_t)) + hop_count; + *encap = (encap_headers_t){ + .eth = { .h_proto = htons(ETH_P_IP) }, + .ip = { + .ihl = 5, + .version = 4, + .ttl = IPDEFTTL, + .protocol = IPPROTO_UDP, + .daddr = htonl(ENCAP_IP) + }, + .udp = { + .dest = htons(ENCAP_PORT), + }, + .gue = { + .hlen = hlen, + .proto_ctype = proto + }, + .unigue = { + .hop_count = hop_count + }, + }; +} + +static size_t build_input(const struct test_cfg *test, void *const buf, + const struct tuple *tuple) +{ + in_port_t sport = tuple->src.port; + encap_headers_t encap; + struct iphdr ip; + struct ipv6hdr ipv6; + struct tcphdr tcp; + struct udphdr udp; + struct in_addr next_hop; + uint8_t *p = buf; + int proto; + + proto = IPPROTO_IPIP; + if (tuple->family == AF_INET6) + proto = IPPROTO_IPV6; + + encap_init(&encap, test->hops == ONE_HOP ? 1 : 0, proto); + p = mempcpy(p, &encap, sizeof(encap)); + + if (test->hops == ONE_HOP) { + next_hop = (struct in_addr){ .s_addr = htonl(0x7f000002) }; + p = mempcpy(p, &next_hop, sizeof(next_hop)); + } + + proto = IPPROTO_TCP; + if (test->type == UDP) + proto = IPPROTO_UDP; + + switch (tuple->family) { + case AF_INET: + ip = (struct iphdr){ + .ihl = 5, + .version = 4, + .ttl = IPDEFTTL, + .protocol = proto, + .saddr = tuple->src.in_addr.s_addr, + .daddr = tuple->dst.in_addr.s_addr, + }; + p = mempcpy(p, &ip, sizeof(ip)); + break; + case AF_INET6: + ipv6 = (struct ipv6hdr){ + .version = 6, + .hop_limit = IPDEFTTL, + .nexthdr = proto, + .saddr = tuple->src.in6_addr, + .daddr = tuple->dst.in6_addr, + }; + p = mempcpy(p, &ipv6, sizeof(ipv6)); + break; + default: + return 0; + } + + if (test->conn == UNKNOWN_CONN) + sport--; + + switch (test->type) { + case TCP: + tcp = (struct tcphdr){ + .source = sport, + .dest = tuple->dst.port, + }; + if (test->flags == SYN) + tcp.syn = true; + if (test->flags == ACK) + tcp.ack = true; + p = mempcpy(p, &tcp, sizeof(tcp)); + break; + case UDP: + udp = (struct udphdr){ + .source = sport, + .dest = tuple->dst.port, + }; + p = mempcpy(p, &udp, sizeof(udp)); + break; + default: + return 0; + } + + return (void *)p - buf; +} + +static void close_fds(int *fds, int n) +{ + int i; + + for (i = 0; i < n; i++) + if (fds[i] > 0) + close(fds[i]); +} + +void test_cls_redirect(void) +{ + struct test_cls_redirect *skel = NULL; + struct bpf_prog_test_run_attr tattr = {}; + int families[] = { AF_INET, AF_INET6 }; + struct sockaddr_storage ss; + struct sockaddr *addr; + socklen_t slen; + int i, j, err; + + int servers[__NR_KIND][ARRAY_SIZE(families)] = {}; + int conns[__NR_KIND][ARRAY_SIZE(families)] = {}; + struct tuple tuples[__NR_KIND][ARRAY_SIZE(families)]; + + skel = test_cls_redirect__open(); + if (CHECK_FAIL(!skel)) + return; + + skel->rodata->ENCAPSULATION_IP = htonl(ENCAP_IP); + skel->rodata->ENCAPSULATION_PORT = htons(ENCAP_PORT); + + if (CHECK_FAIL(test_cls_redirect__load(skel))) + goto cleanup; + + addr = (struct sockaddr *)&ss; + for (i = 0; i < ARRAY_SIZE(families); i++) { + slen = prepare_addr(&ss, families[i]); + if (CHECK_FAIL(!slen)) + goto cleanup; + + if (CHECK_FAIL(!set_up_conn(addr, slen, SOCK_DGRAM, + &servers[UDP][i], &conns[UDP][i], + &tuples[UDP][i]))) + goto cleanup; + + if (CHECK_FAIL(!set_up_conn(addr, slen, SOCK_STREAM, + &servers[TCP][i], &conns[TCP][i], + &tuples[TCP][i]))) + goto cleanup; + } + + tattr.prog_fd = bpf_program__fd(skel->progs.cls_redirect); + for (i = 0; i < ARRAY_SIZE(tests); i++) { + struct test_cfg *test = &tests[i]; + + for (j = 0; j < ARRAY_SIZE(families); j++) { + struct tuple *tuple = &tuples[test->type][j]; + char input[256]; + char tmp[256]; + + test_str(tmp, sizeof(tmp), test, tuple->family); + if (!test__start_subtest(tmp)) + continue; + + tattr.data_out = tmp; + tattr.data_size_out = sizeof(tmp); + + tattr.data_in = input; + tattr.data_size_in = build_input(test, input, tuple); + if (CHECK_FAIL(!tattr.data_size_in)) + continue; + + err = bpf_prog_test_run_xattr(&tattr); + if (CHECK_FAIL(err)) + continue; + + if (tattr.retval != TC_ACT_REDIRECT) { + PRINT_FAIL("expected TC_ACT_REDIRECT, got %d\n", + tattr.retval); + continue; + } + + switch (test->result) { + case ACCEPT: + if (CHECK_FAIL(!was_decapsulated(&tattr))) + continue; + break; + case FORWARD: + if (CHECK_FAIL(was_decapsulated(&tattr))) + continue; + break; + default: + PRINT_FAIL("unknown result %d\n", test->result); + continue; + } + } + } + +cleanup: + test_cls_redirect__destroy(skel); + close_fds((int *)servers, sizeof(servers) / sizeof(servers[0][0])); + close_fds((int *)conns, sizeof(conns) / sizeof(conns[0][0])); +} diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c index 31e177adbdf1..084ed26a7d78 100644 --- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c +++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c @@ -392,7 +392,7 @@ static struct core_reloc_test_case test_cases[] = { .input = STRUCT_TO_CHAR_PTR(core_reloc_existence___minimal) { .a = 42, }, - .input_len = sizeof(struct core_reloc_existence), + .input_len = sizeof(struct core_reloc_existence___minimal), .output = STRUCT_TO_CHAR_PTR(core_reloc_existence_output) { .a_exists = 1, .b_exists = 0, diff --git a/tools/testing/selftests/bpf/prog_tests/enable_stats.c b/tools/testing/selftests/bpf/prog_tests/enable_stats.c new file mode 100644 index 000000000000..2cb2085917e7 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/enable_stats.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include "test_enable_stats.skel.h" + +void test_enable_stats(void) +{ + struct test_enable_stats *skel; + int stats_fd, err, prog_fd; + struct bpf_prog_info info; + __u32 info_len = sizeof(info); + int duration = 0; + + skel = test_enable_stats__open_and_load(); + if (CHECK(!skel, "skel_open_and_load", "skeleton open/load failed\n")) + return; + + stats_fd = bpf_enable_stats(BPF_STATS_RUN_TIME); + if (CHECK(stats_fd < 0, "get_stats_fd", "failed %d\n", errno)) { + test_enable_stats__destroy(skel); + return; + } + + err = test_enable_stats__attach(skel); + if (CHECK(err, "attach_raw_tp", "err %d\n", err)) + goto cleanup; + + test_enable_stats__detach(skel); + + prog_fd = bpf_program__fd(skel->progs.test_enable_stats); + memset(&info, 0, info_len); + err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (CHECK(err, "get_prog_info", + "failed to get bpf_prog_info for fd %d\n", prog_fd)) + goto cleanup; + if (CHECK(info.run_time_ns == 0, "check_stats_enabled", + "failed to enable run_time_ns stats\n")) + goto cleanup; + + CHECK(info.run_cnt != skel->bss->count, "check_run_cnt_valid", + "invalid run_cnt stats\n"); + +cleanup: + test_enable_stats__destroy(skel); + close(stats_fd); +} diff --git a/tools/testing/selftests/bpf/test_hashmap.c b/tools/testing/selftests/bpf/prog_tests/hashmap.c index c490e012c23f..428d488830c6 100644 --- a/tools/testing/selftests/bpf/test_hashmap.c +++ b/tools/testing/selftests/bpf/prog_tests/hashmap.c @@ -5,26 +5,17 @@ * * Copyright (c) 2019 Facebook */ -#include <stdio.h> -#include <errno.h> -#include <linux/err.h> +#include "test_progs.h" #include "bpf/hashmap.h" -#define CHECK(condition, format...) ({ \ - int __ret = !!(condition); \ - if (__ret) { \ - fprintf(stderr, "%s:%d:FAIL ", __func__, __LINE__); \ - fprintf(stderr, format); \ - } \ - __ret; \ -}) +static int duration = 0; -size_t hash_fn(const void *k, void *ctx) +static size_t hash_fn(const void *k, void *ctx) { return (long)k; } -bool equal_fn(const void *a, const void *b, void *ctx) +static bool equal_fn(const void *a, const void *b, void *ctx) { return (long)a == (long)b; } @@ -49,53 +40,55 @@ static inline size_t exp_cap(size_t sz) #define ELEM_CNT 62 -int test_hashmap_generic(void) +static void test_hashmap_generic(void) { struct hashmap_entry *entry, *tmp; int err, bkt, found_cnt, i; long long found_msk; struct hashmap *map; - fprintf(stderr, "%s: ", __func__); - map = hashmap__new(hash_fn, equal_fn, NULL); - if (CHECK(IS_ERR(map), "failed to create map: %ld\n", PTR_ERR(map))) - return 1; + if (CHECK(IS_ERR(map), "hashmap__new", + "failed to create map: %ld\n", PTR_ERR(map))) + return; for (i = 0; i < ELEM_CNT; i++) { const void *oldk, *k = (const void *)(long)i; void *oldv, *v = (void *)(long)(1024 + i); err = hashmap__update(map, k, v, &oldk, &oldv); - if (CHECK(err != -ENOENT, "unexpected result: %d\n", err)) - return 1; + if (CHECK(err != -ENOENT, "hashmap__update", + "unexpected result: %d\n", err)) + goto cleanup; if (i % 2) { err = hashmap__add(map, k, v); } else { err = hashmap__set(map, k, v, &oldk, &oldv); - if (CHECK(oldk != NULL || oldv != NULL, + if (CHECK(oldk != NULL || oldv != NULL, "check_kv", "unexpected k/v: %p=%p\n", oldk, oldv)) - return 1; + goto cleanup; } - if (CHECK(err, "failed to add k/v %ld = %ld: %d\n", + if (CHECK(err, "elem_add", "failed to add k/v %ld = %ld: %d\n", (long)k, (long)v, err)) - return 1; + goto cleanup; - if (CHECK(!hashmap__find(map, k, &oldv), + if (CHECK(!hashmap__find(map, k, &oldv), "elem_find", "failed to find key %ld\n", (long)k)) - return 1; - if (CHECK(oldv != v, "found value is wrong: %ld\n", (long)oldv)) - return 1; + goto cleanup; + if (CHECK(oldv != v, "elem_val", + "found value is wrong: %ld\n", (long)oldv)) + goto cleanup; } - if (CHECK(hashmap__size(map) != ELEM_CNT, + if (CHECK(hashmap__size(map) != ELEM_CNT, "hashmap__size", "invalid map size: %zu\n", hashmap__size(map))) - return 1; + goto cleanup; if (CHECK(hashmap__capacity(map) != exp_cap(hashmap__size(map)), + "hashmap_cap", "unexpected map capacity: %zu\n", hashmap__capacity(map))) - return 1; + goto cleanup; found_msk = 0; hashmap__for_each_entry(map, entry, bkt) { @@ -103,42 +96,47 @@ int test_hashmap_generic(void) long v = (long)entry->value; found_msk |= 1ULL << k; - if (CHECK(v - k != 1024, "invalid k/v pair: %ld = %ld\n", k, v)) - return 1; + if (CHECK(v - k != 1024, "check_kv", + "invalid k/v pair: %ld = %ld\n", k, v)) + goto cleanup; } - if (CHECK(found_msk != (1ULL << ELEM_CNT) - 1, + if (CHECK(found_msk != (1ULL << ELEM_CNT) - 1, "elem_cnt", "not all keys iterated: %llx\n", found_msk)) - return 1; + goto cleanup; for (i = 0; i < ELEM_CNT; i++) { const void *oldk, *k = (const void *)(long)i; void *oldv, *v = (void *)(long)(256 + i); err = hashmap__add(map, k, v); - if (CHECK(err != -EEXIST, "unexpected add result: %d\n", err)) - return 1; + if (CHECK(err != -EEXIST, "hashmap__add", + "unexpected add result: %d\n", err)) + goto cleanup; if (i % 2) err = hashmap__update(map, k, v, &oldk, &oldv); else err = hashmap__set(map, k, v, &oldk, &oldv); - if (CHECK(err, "failed to update k/v %ld = %ld: %d\n", - (long)k, (long)v, err)) - return 1; - if (CHECK(!hashmap__find(map, k, &oldv), + if (CHECK(err, "elem_upd", + "failed to update k/v %ld = %ld: %d\n", + (long)k, (long)v, err)) + goto cleanup; + if (CHECK(!hashmap__find(map, k, &oldv), "elem_find", "failed to find key %ld\n", (long)k)) - return 1; - if (CHECK(oldv != v, "found value is wrong: %ld\n", (long)oldv)) - return 1; + goto cleanup; + if (CHECK(oldv != v, "elem_val", + "found value is wrong: %ld\n", (long)oldv)) + goto cleanup; } - if (CHECK(hashmap__size(map) != ELEM_CNT, + if (CHECK(hashmap__size(map) != ELEM_CNT, "hashmap__size", "invalid updated map size: %zu\n", hashmap__size(map))) - return 1; + goto cleanup; if (CHECK(hashmap__capacity(map) != exp_cap(hashmap__size(map)), + "hashmap__capacity", "unexpected map capacity: %zu\n", hashmap__capacity(map))) - return 1; + goto cleanup; found_msk = 0; hashmap__for_each_entry_safe(map, entry, tmp, bkt) { @@ -146,20 +144,21 @@ int test_hashmap_generic(void) long v = (long)entry->value; found_msk |= 1ULL << k; - if (CHECK(v - k != 256, + if (CHECK(v - k != 256, "elem_check", "invalid updated k/v pair: %ld = %ld\n", k, v)) - return 1; + goto cleanup; } - if (CHECK(found_msk != (1ULL << ELEM_CNT) - 1, + if (CHECK(found_msk != (1ULL << ELEM_CNT) - 1, "elem_cnt", "not all keys iterated after update: %llx\n", found_msk)) - return 1; + goto cleanup; found_cnt = 0; hashmap__for_each_key_entry(map, entry, (void *)0) { found_cnt++; } - if (CHECK(!found_cnt, "didn't find any entries for key 0\n")) - return 1; + if (CHECK(!found_cnt, "found_cnt", + "didn't find any entries for key 0\n")) + goto cleanup; found_msk = 0; found_cnt = 0; @@ -173,30 +172,31 @@ int test_hashmap_generic(void) found_cnt++; found_msk |= 1ULL << (long)k; - if (CHECK(!hashmap__delete(map, k, &oldk, &oldv), + if (CHECK(!hashmap__delete(map, k, &oldk, &oldv), "elem_del", "failed to delete k/v %ld = %ld\n", (long)k, (long)v)) - return 1; - if (CHECK(oldk != k || oldv != v, + goto cleanup; + if (CHECK(oldk != k || oldv != v, "check_old", "invalid deleted k/v: expected %ld = %ld, got %ld = %ld\n", (long)k, (long)v, (long)oldk, (long)oldv)) - return 1; - if (CHECK(hashmap__delete(map, k, &oldk, &oldv), + goto cleanup; + if (CHECK(hashmap__delete(map, k, &oldk, &oldv), "elem_del", "unexpectedly deleted k/v %ld = %ld\n", (long)oldk, (long)oldv)) - return 1; + goto cleanup; } - if (CHECK(!found_cnt || !found_msk, + if (CHECK(!found_cnt || !found_msk, "found_entries", "didn't delete any key entries\n")) - return 1; - if (CHECK(hashmap__size(map) != ELEM_CNT - found_cnt, + goto cleanup; + if (CHECK(hashmap__size(map) != ELEM_CNT - found_cnt, "elem_cnt", "invalid updated map size (already deleted: %d): %zu\n", found_cnt, hashmap__size(map))) - return 1; + goto cleanup; if (CHECK(hashmap__capacity(map) != exp_cap(hashmap__size(map)), + "hashmap__capacity", "unexpected map capacity: %zu\n", hashmap__capacity(map))) - return 1; + goto cleanup; hashmap__for_each_entry_safe(map, entry, tmp, bkt) { const void *oldk, *k; @@ -208,53 +208,56 @@ int test_hashmap_generic(void) found_cnt++; found_msk |= 1ULL << (long)k; - if (CHECK(!hashmap__delete(map, k, &oldk, &oldv), + if (CHECK(!hashmap__delete(map, k, &oldk, &oldv), "elem_del", "failed to delete k/v %ld = %ld\n", (long)k, (long)v)) - return 1; - if (CHECK(oldk != k || oldv != v, + goto cleanup; + if (CHECK(oldk != k || oldv != v, "elem_check", "invalid old k/v: expect %ld = %ld, got %ld = %ld\n", (long)k, (long)v, (long)oldk, (long)oldv)) - return 1; - if (CHECK(hashmap__delete(map, k, &oldk, &oldv), + goto cleanup; + if (CHECK(hashmap__delete(map, k, &oldk, &oldv), "elem_del", "unexpectedly deleted k/v %ld = %ld\n", (long)k, (long)v)) - return 1; + goto cleanup; } if (CHECK(found_cnt != ELEM_CNT || found_msk != (1ULL << ELEM_CNT) - 1, + "found_cnt", "not all keys were deleted: found_cnt:%d, found_msk:%llx\n", found_cnt, found_msk)) - return 1; - if (CHECK(hashmap__size(map) != 0, + goto cleanup; + if (CHECK(hashmap__size(map) != 0, "hashmap__size", "invalid updated map size (already deleted: %d): %zu\n", found_cnt, hashmap__size(map))) - return 1; + goto cleanup; found_cnt = 0; hashmap__for_each_entry(map, entry, bkt) { - CHECK(false, "unexpected map entries left: %ld = %ld\n", - (long)entry->key, (long)entry->value); - return 1; + CHECK(false, "elem_exists", + "unexpected map entries left: %ld = %ld\n", + (long)entry->key, (long)entry->value); + goto cleanup; } - hashmap__free(map); + hashmap__clear(map); hashmap__for_each_entry(map, entry, bkt) { - CHECK(false, "unexpected map entries left: %ld = %ld\n", - (long)entry->key, (long)entry->value); - return 1; + CHECK(false, "elem_exists", + "unexpected map entries left: %ld = %ld\n", + (long)entry->key, (long)entry->value); + goto cleanup; } - fprintf(stderr, "OK\n"); - return 0; +cleanup: + hashmap__free(map); } -size_t collision_hash_fn(const void *k, void *ctx) +static size_t collision_hash_fn(const void *k, void *ctx) { return 0; } -int test_hashmap_multimap(void) +static void test_hashmap_multimap(void) { void *k1 = (void *)0, *k2 = (void *)1; struct hashmap_entry *entry; @@ -262,121 +265,116 @@ int test_hashmap_multimap(void) long found_msk; int err, bkt; - fprintf(stderr, "%s: ", __func__); - /* force collisions */ map = hashmap__new(collision_hash_fn, equal_fn, NULL); - if (CHECK(IS_ERR(map), "failed to create map: %ld\n", PTR_ERR(map))) - return 1; - + if (CHECK(IS_ERR(map), "hashmap__new", + "failed to create map: %ld\n", PTR_ERR(map))) + return; /* set up multimap: * [0] -> 1, 2, 4; * [1] -> 8, 16, 32; */ err = hashmap__append(map, k1, (void *)1); - if (CHECK(err, "failed to add k/v: %d\n", err)) - return 1; + if (CHECK(err, "elem_add", "failed to add k/v: %d\n", err)) + goto cleanup; err = hashmap__append(map, k1, (void *)2); - if (CHECK(err, "failed to add k/v: %d\n", err)) - return 1; + if (CHECK(err, "elem_add", "failed to add k/v: %d\n", err)) + goto cleanup; err = hashmap__append(map, k1, (void *)4); - if (CHECK(err, "failed to add k/v: %d\n", err)) - return 1; + if (CHECK(err, "elem_add", "failed to add k/v: %d\n", err)) + goto cleanup; err = hashmap__append(map, k2, (void *)8); - if (CHECK(err, "failed to add k/v: %d\n", err)) - return 1; + if (CHECK(err, "elem_add", "failed to add k/v: %d\n", err)) + goto cleanup; err = hashmap__append(map, k2, (void *)16); - if (CHECK(err, "failed to add k/v: %d\n", err)) - return 1; + if (CHECK(err, "elem_add", "failed to add k/v: %d\n", err)) + goto cleanup; err = hashmap__append(map, k2, (void *)32); - if (CHECK(err, "failed to add k/v: %d\n", err)) - return 1; + if (CHECK(err, "elem_add", "failed to add k/v: %d\n", err)) + goto cleanup; - if (CHECK(hashmap__size(map) != 6, + if (CHECK(hashmap__size(map) != 6, "hashmap_size", "invalid map size: %zu\n", hashmap__size(map))) - return 1; + goto cleanup; /* verify global iteration still works and sees all values */ found_msk = 0; hashmap__for_each_entry(map, entry, bkt) { found_msk |= (long)entry->value; } - if (CHECK(found_msk != (1 << 6) - 1, + if (CHECK(found_msk != (1 << 6) - 1, "found_msk", "not all keys iterated: %lx\n", found_msk)) - return 1; + goto cleanup; /* iterate values for key 1 */ found_msk = 0; hashmap__for_each_key_entry(map, entry, k1) { found_msk |= (long)entry->value; } - if (CHECK(found_msk != (1 | 2 | 4), + if (CHECK(found_msk != (1 | 2 | 4), "found_msk", "invalid k1 values: %lx\n", found_msk)) - return 1; + goto cleanup; /* iterate values for key 2 */ found_msk = 0; hashmap__for_each_key_entry(map, entry, k2) { found_msk |= (long)entry->value; } - if (CHECK(found_msk != (8 | 16 | 32), + if (CHECK(found_msk != (8 | 16 | 32), "found_msk", "invalid k2 values: %lx\n", found_msk)) - return 1; + goto cleanup; - fprintf(stderr, "OK\n"); - return 0; +cleanup: + hashmap__free(map); } -int test_hashmap_empty() +static void test_hashmap_empty() { struct hashmap_entry *entry; int bkt; struct hashmap *map; void *k = (void *)0; - fprintf(stderr, "%s: ", __func__); - /* force collisions */ map = hashmap__new(hash_fn, equal_fn, NULL); - if (CHECK(IS_ERR(map), "failed to create map: %ld\n", PTR_ERR(map))) - return 1; + if (CHECK(IS_ERR(map), "hashmap__new", + "failed to create map: %ld\n", PTR_ERR(map))) + goto cleanup; - if (CHECK(hashmap__size(map) != 0, + if (CHECK(hashmap__size(map) != 0, "hashmap__size", "invalid map size: %zu\n", hashmap__size(map))) - return 1; - if (CHECK(hashmap__capacity(map) != 0, + goto cleanup; + if (CHECK(hashmap__capacity(map) != 0, "hashmap__capacity", "invalid map capacity: %zu\n", hashmap__capacity(map))) - return 1; - if (CHECK(hashmap__find(map, k, NULL), "unexpected find\n")) - return 1; - if (CHECK(hashmap__delete(map, k, NULL, NULL), "unexpected delete\n")) - return 1; + goto cleanup; + if (CHECK(hashmap__find(map, k, NULL), "elem_find", + "unexpected find\n")) + goto cleanup; + if (CHECK(hashmap__delete(map, k, NULL, NULL), "elem_del", + "unexpected delete\n")) + goto cleanup; hashmap__for_each_entry(map, entry, bkt) { - CHECK(false, "unexpected iterated entry\n"); - return 1; + CHECK(false, "elem_found", "unexpected iterated entry\n"); + goto cleanup; } hashmap__for_each_key_entry(map, entry, k) { - CHECK(false, "unexpected key entry\n"); - return 1; + CHECK(false, "key_found", "unexpected key entry\n"); + goto cleanup; } - fprintf(stderr, "OK\n"); - return 0; +cleanup: + hashmap__free(map); } -int main(int argc, char **argv) +void test_hashmap() { - bool failed = false; - - if (test_hashmap_generic()) - failed = true; - if (test_hashmap_multimap()) - failed = true; - if (test_hashmap_empty()) - failed = true; - - return failed; + if (test__start_subtest("generic")) + test_hashmap_generic(); + if (test__start_subtest("multimap")) + test_hashmap_multimap(); + if (test__start_subtest("empty")) + test_hashmap_empty(); } diff --git a/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c index 542240e16564..e74dc501b27f 100644 --- a/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c +++ b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c @@ -80,9 +80,6 @@ void test_ns_current_pid_tgid(void) "User pid/tgid %llu BPF pid/tgid %llu\n", id, bss.pid_tgid)) goto cleanup; cleanup: - if (!link) { - bpf_link__destroy(link); - link = NULL; - } + bpf_link__destroy(link); bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c index 1450ea2dd4cc..a122ce3b360e 100644 --- a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c +++ b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c @@ -6,6 +6,11 @@ #include <test_progs.h> #include "bpf/libbpf_internal.h" +/* AddressSanitizer sometimes crashes due to data dereference below, due to + * this being mmap()'ed memory. Disable instrumentation with + * no_sanitize_address attribute + */ +__attribute__((no_sanitize_address)) static void on_sample(void *ctx, int cpu, void *data, __u32 size) { int cpu_data = *(int *)data, duration = 0; diff --git a/tools/testing/selftests/bpf/prog_tests/sk_assign.c b/tools/testing/selftests/bpf/prog_tests/sk_assign.c index d572e1a2c297..47fa04adc147 100644 --- a/tools/testing/selftests/bpf/prog_tests/sk_assign.c +++ b/tools/testing/selftests/bpf/prog_tests/sk_assign.c @@ -20,6 +20,7 @@ #define CONNECT_PORT 4321 #define TEST_DADDR (0xC0A80203) #define NS_SELF "/proc/self/ns/net" +#define SERVER_MAP_PATH "/sys/fs/bpf/tc/globals/server_map" static const struct timeval timeo_sec = { .tv_sec = 3 }; static const size_t timeo_optlen = sizeof(timeo_sec); @@ -265,6 +266,7 @@ void test_sk_assign(void) TEST("ipv6 udp addr redir", AF_INET6, SOCK_DGRAM, true), }; int server = -1; + int server_map; int self_net; self_net = open(NS_SELF, O_RDONLY); @@ -278,9 +280,17 @@ void test_sk_assign(void) goto cleanup; } + server_map = bpf_obj_get(SERVER_MAP_PATH); + if (CHECK_FAIL(server_map < 0)) { + perror("Unable to open " SERVER_MAP_PATH); + goto cleanup; + } + for (int i = 0; i < ARRAY_SIZE(tests) && !READ_ONCE(stop); i++) { struct test_sk_cfg *test = &tests[i]; const struct sockaddr *addr; + const int zero = 0; + int err; if (!test__start_subtest(test->name)) continue; @@ -288,7 +298,13 @@ void test_sk_assign(void) addr = (const struct sockaddr *)test->addr; server = start_server(addr, test->len, test->type); if (server == -1) - goto cleanup; + goto close; + + err = bpf_map_update_elem(server_map, &zero, &server, BPF_ANY); + if (CHECK_FAIL(err)) { + perror("Unable to update server_map"); + goto close; + } /* connect to unbound ports */ prepare_addr(test->addr, test->family, CONNECT_PORT, @@ -302,7 +318,10 @@ void test_sk_assign(void) close: close(server); + close(server_map); cleanup: + if (CHECK_FAIL(unlink(SERVER_MAP_PATH))) + perror("Unable to unlink " SERVER_MAP_PATH); if (CHECK_FAIL(setns(self_net, CLONE_NEWNET))) perror("Failed to setns("NS_SELF")"); close(self_net); diff --git a/tools/testing/selftests/bpf/progs/connect4_prog.c b/tools/testing/selftests/bpf/progs/connect4_prog.c index ad3c498a8150..c2c85c31cffd 100644 --- a/tools/testing/selftests/bpf/progs/connect4_prog.c +++ b/tools/testing/selftests/bpf/progs/connect4_prog.c @@ -8,6 +8,7 @@ #include <linux/in.h> #include <linux/in6.h> #include <sys/socket.h> +#include <netinet/tcp.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> @@ -16,6 +17,10 @@ #define DST_REWRITE_IP4 0x7f000001U #define DST_REWRITE_PORT4 4444 +#ifndef TCP_CA_NAME_MAX +#define TCP_CA_NAME_MAX 16 +#endif + int _version SEC("version") = 1; __attribute__ ((noinline)) @@ -33,6 +38,43 @@ int do_bind(struct bpf_sock_addr *ctx) return 1; } +static __inline int verify_cc(struct bpf_sock_addr *ctx, + char expected[TCP_CA_NAME_MAX]) +{ + char buf[TCP_CA_NAME_MAX]; + int i; + + if (bpf_getsockopt(ctx, SOL_TCP, TCP_CONGESTION, &buf, sizeof(buf))) + return 1; + + for (i = 0; i < TCP_CA_NAME_MAX; i++) { + if (buf[i] != expected[i]) + return 1; + if (buf[i] == 0) + break; + } + + return 0; +} + +static __inline int set_cc(struct bpf_sock_addr *ctx) +{ + char reno[TCP_CA_NAME_MAX] = "reno"; + char cubic[TCP_CA_NAME_MAX] = "cubic"; + + if (bpf_setsockopt(ctx, SOL_TCP, TCP_CONGESTION, &reno, sizeof(reno))) + return 1; + if (verify_cc(ctx, reno)) + return 1; + + if (bpf_setsockopt(ctx, SOL_TCP, TCP_CONGESTION, &cubic, sizeof(cubic))) + return 1; + if (verify_cc(ctx, cubic)) + return 1; + + return 0; +} + SEC("cgroup/connect4") int connect_v4_prog(struct bpf_sock_addr *ctx) { @@ -66,6 +108,10 @@ int connect_v4_prog(struct bpf_sock_addr *ctx) bpf_sk_release(sk); + /* Rewrite congestion control. */ + if (ctx->type == SOCK_STREAM && set_cc(ctx)) + return 0; + /* Rewrite destination. */ ctx->user_ip4 = bpf_htonl(DST_REWRITE_IP4); ctx->user_port = bpf_htons(DST_REWRITE_PORT4); diff --git a/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c b/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c new file mode 100644 index 000000000000..e5093796be97 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c @@ -0,0 +1,76 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2020 Facebook */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct inner_map { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} inner_map1 SEC(".maps"), + inner_map2 SEC(".maps"); + +struct outer_arr { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, 3); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(int)); + /* it's possible to use anonymous struct as inner map definition here */ + __array(values, struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + /* changing max_entries to 2 will fail during load + * due to incompatibility with inner_map definition */ + __uint(max_entries, 1); + __type(key, int); + __type(value, int); + }); +} outer_arr SEC(".maps") = { + /* (void *) cast is necessary because we didn't use `struct inner_map` + * in __inner(values, ...) + * Actually, a conscious effort is required to screw up initialization + * of inner map slots, which is a great thing! + */ + .values = { (void *)&inner_map1, 0, (void *)&inner_map2 }, +}; + +struct outer_hash { + __uint(type, BPF_MAP_TYPE_HASH_OF_MAPS); + __uint(max_entries, 5); + __uint(key_size, sizeof(int)); + /* Here everything works flawlessly due to reuse of struct inner_map + * and compiler will complain at the attempt to use non-inner_map + * references below. This is great experience. + */ + __array(values, struct inner_map); +} outer_hash SEC(".maps") = { + .values = { + [0] = &inner_map2, + [4] = &inner_map1, + }, +}; + +int input = 0; + +SEC("raw_tp/sys_enter") +int handle__sys_enter(void *ctx) +{ + struct inner_map *inner_map; + int key = 0, val; + + inner_map = bpf_map_lookup_elem(&outer_arr, &key); + if (!inner_map) + return 1; + val = input; + bpf_map_update_elem(inner_map, &key, &val, 0); + + inner_map = bpf_map_lookup_elem(&outer_hash, &key); + if (!inner_map) + return 1; + val = input + 1; + bpf_map_update_elem(inner_map, &key, &val, 0); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.c b/tools/testing/selftests/bpf/progs/test_cls_redirect.c new file mode 100644 index 000000000000..1668b993eb86 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.c @@ -0,0 +1,1058 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +// Copyright (c) 2019, 2020 Cloudflare + +#include <stdbool.h> +#include <stddef.h> +#include <stdint.h> +#include <string.h> + +#include <linux/bpf.h> +#include <linux/icmp.h> +#include <linux/icmpv6.h> +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/pkt_cls.h> +#include <linux/tcp.h> +#include <linux/udp.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#include "test_cls_redirect.h" + +#define offsetofend(TYPE, MEMBER) \ + (offsetof(TYPE, MEMBER) + sizeof((((TYPE *)0)->MEMBER))) + +#define IP_OFFSET_MASK (0x1FFF) +#define IP_MF (0x2000) + +char _license[] SEC("license") = "Dual BSD/GPL"; + +/** + * Destination port and IP used for UDP encapsulation. + */ +static volatile const __be16 ENCAPSULATION_PORT; +static volatile const __be32 ENCAPSULATION_IP; + +typedef struct { + uint64_t processed_packets_total; + uint64_t l3_protocol_packets_total_ipv4; + uint64_t l3_protocol_packets_total_ipv6; + uint64_t l4_protocol_packets_total_tcp; + uint64_t l4_protocol_packets_total_udp; + uint64_t accepted_packets_total_syn; + uint64_t accepted_packets_total_syn_cookies; + uint64_t accepted_packets_total_last_hop; + uint64_t accepted_packets_total_icmp_echo_request; + uint64_t accepted_packets_total_established; + uint64_t forwarded_packets_total_gue; + uint64_t forwarded_packets_total_gre; + + uint64_t errors_total_unknown_l3_proto; + uint64_t errors_total_unknown_l4_proto; + uint64_t errors_total_malformed_ip; + uint64_t errors_total_fragmented_ip; + uint64_t errors_total_malformed_icmp; + uint64_t errors_total_unwanted_icmp; + uint64_t errors_total_malformed_icmp_pkt_too_big; + uint64_t errors_total_malformed_tcp; + uint64_t errors_total_malformed_udp; + uint64_t errors_total_icmp_echo_replies; + uint64_t errors_total_malformed_encapsulation; + uint64_t errors_total_encap_adjust_failed; + uint64_t errors_total_encap_buffer_too_small; + uint64_t errors_total_redirect_loop; +} metrics_t; + +typedef enum { + INVALID = 0, + UNKNOWN, + ECHO_REQUEST, + SYN, + SYN_COOKIE, + ESTABLISHED, +} verdict_t; + +typedef struct { + uint16_t src, dst; +} flow_ports_t; + +_Static_assert( + sizeof(flow_ports_t) != + offsetofend(struct bpf_sock_tuple, ipv4.dport) - + offsetof(struct bpf_sock_tuple, ipv4.sport) - 1, + "flow_ports_t must match sport and dport in struct bpf_sock_tuple"); +_Static_assert( + sizeof(flow_ports_t) != + offsetofend(struct bpf_sock_tuple, ipv6.dport) - + offsetof(struct bpf_sock_tuple, ipv6.sport) - 1, + "flow_ports_t must match sport and dport in struct bpf_sock_tuple"); + +typedef int ret_t; + +/* This is a bit of a hack. We need a return value which allows us to + * indicate that the regular flow of the program should continue, + * while allowing functions to use XDP_PASS and XDP_DROP, etc. + */ +static const ret_t CONTINUE_PROCESSING = -1; + +/* Convenience macro to call functions which return ret_t. + */ +#define MAYBE_RETURN(x) \ + do { \ + ret_t __ret = x; \ + if (__ret != CONTINUE_PROCESSING) \ + return __ret; \ + } while (0) + +/* Linux packet pointers are either aligned to NET_IP_ALIGN (aka 2 bytes), + * or not aligned if the arch supports efficient unaligned access. + * + * Since the verifier ensures that eBPF packet accesses follow these rules, + * we can tell LLVM to emit code as if we always had a larger alignment. + * It will yell at us if we end up on a platform where this is not valid. + */ +typedef uint8_t *net_ptr __attribute__((align_value(8))); + +typedef struct buf { + struct __sk_buff *skb; + net_ptr head; + /* NB: tail musn't have alignment other than 1, otherwise + * LLVM will go and eliminate code, e.g. when checking packet lengths. + */ + uint8_t *const tail; +} buf_t; + +static size_t buf_off(const buf_t *buf) +{ + /* Clang seems to optimize constructs like + * a - b + c + * if c is known: + * r? = c + * r? -= b + * r? += a + * + * This is a problem if a and b are packet pointers, + * since the verifier allows subtracting two pointers to + * get a scalar, but not a scalar and a pointer. + * + * Use inline asm to break this optimization. + */ + size_t off = (size_t)buf->head; + asm("%0 -= %1" : "+r"(off) : "r"(buf->skb->data)); + return off; +} + +static bool buf_copy(buf_t *buf, void *dst, size_t len) +{ + if (bpf_skb_load_bytes(buf->skb, buf_off(buf), dst, len)) { + return false; + } + + buf->head += len; + return true; +} + +static bool buf_skip(buf_t *buf, const size_t len) +{ + /* Check whether off + len is valid in the non-linear part. */ + if (buf_off(buf) + len > buf->skb->len) { + return false; + } + + buf->head += len; + return true; +} + +/* Returns a pointer to the start of buf, or NULL if len is + * larger than the remaining data. Consumes len bytes on a successful + * call. + * + * If scratch is not NULL, the function will attempt to load non-linear + * data via bpf_skb_load_bytes. On success, scratch is returned. + */ +static void *buf_assign(buf_t *buf, const size_t len, void *scratch) +{ + if (buf->head + len > buf->tail) { + if (scratch == NULL) { + return NULL; + } + + return buf_copy(buf, scratch, len) ? scratch : NULL; + } + + void *ptr = buf->head; + buf->head += len; + return ptr; +} + +static bool pkt_skip_ipv4_options(buf_t *buf, const struct iphdr *ipv4) +{ + if (ipv4->ihl <= 5) { + return true; + } + + return buf_skip(buf, (ipv4->ihl - 5) * 4); +} + +static bool ipv4_is_fragment(const struct iphdr *ip) +{ + uint16_t frag_off = ip->frag_off & bpf_htons(IP_OFFSET_MASK); + return (ip->frag_off & bpf_htons(IP_MF)) != 0 || frag_off > 0; +} + +static struct iphdr *pkt_parse_ipv4(buf_t *pkt, struct iphdr *scratch) +{ + struct iphdr *ipv4 = buf_assign(pkt, sizeof(*ipv4), scratch); + if (ipv4 == NULL) { + return NULL; + } + + if (ipv4->ihl < 5) { + return NULL; + } + + if (!pkt_skip_ipv4_options(pkt, ipv4)) { + return NULL; + } + + return ipv4; +} + +/* Parse the L4 ports from a packet, assuming a layout like TCP or UDP. */ +static bool pkt_parse_icmp_l4_ports(buf_t *pkt, flow_ports_t *ports) +{ + if (!buf_copy(pkt, ports, sizeof(*ports))) { + return false; + } + + /* Ports in the L4 headers are reversed, since we are parsing an ICMP + * payload which is going towards the eyeball. + */ + uint16_t dst = ports->src; + ports->src = ports->dst; + ports->dst = dst; + return true; +} + +static uint16_t pkt_checksum_fold(uint32_t csum) +{ + /* The highest reasonable value for an IPv4 header + * checksum requires two folds, so we just do that always. + */ + csum = (csum & 0xffff) + (csum >> 16); + csum = (csum & 0xffff) + (csum >> 16); + return (uint16_t)~csum; +} + +static void pkt_ipv4_checksum(struct iphdr *iph) +{ + iph->check = 0; + + /* An IP header without options is 20 bytes. Two of those + * are the checksum, which we always set to zero. Hence, + * the maximum accumulated value is 18 / 2 * 0xffff = 0x8fff7, + * which fits in 32 bit. + */ + _Static_assert(sizeof(struct iphdr) == 20, "iphdr must be 20 bytes"); + uint32_t acc = 0; + uint16_t *ipw = (uint16_t *)iph; + +#pragma clang loop unroll(full) + for (size_t i = 0; i < sizeof(struct iphdr) / 2; i++) { + acc += ipw[i]; + } + + iph->check = pkt_checksum_fold(acc); +} + +static bool pkt_skip_ipv6_extension_headers(buf_t *pkt, + const struct ipv6hdr *ipv6, + uint8_t *upper_proto, + bool *is_fragment) +{ + /* We understand five extension headers. + * https://tools.ietf.org/html/rfc8200#section-4.1 states that all + * headers should occur once, except Destination Options, which may + * occur twice. Hence we give up after 6 headers. + */ + struct { + uint8_t next; + uint8_t len; + } exthdr = { + .next = ipv6->nexthdr, + }; + *is_fragment = false; + +#pragma clang loop unroll(full) + for (int i = 0; i < 6; i++) { + switch (exthdr.next) { + case IPPROTO_FRAGMENT: + *is_fragment = true; + /* NB: We don't check that hdrlen == 0 as per spec. */ + /* fallthrough; */ + + case IPPROTO_HOPOPTS: + case IPPROTO_ROUTING: + case IPPROTO_DSTOPTS: + case IPPROTO_MH: + if (!buf_copy(pkt, &exthdr, sizeof(exthdr))) { + return false; + } + + /* hdrlen is in 8-octet units, and excludes the first 8 octets. */ + if (!buf_skip(pkt, + (exthdr.len + 1) * 8 - sizeof(exthdr))) { + return false; + } + + /* Decode next header */ + break; + + default: + /* The next header is not one of the known extension + * headers, treat it as the upper layer header. + * + * This handles IPPROTO_NONE. + * + * Encapsulating Security Payload (50) and Authentication + * Header (51) also end up here (and will trigger an + * unknown proto error later). They have a custom header + * format and seem too esoteric to care about. + */ + *upper_proto = exthdr.next; + return true; + } + } + + /* We never found an upper layer header. */ + return false; +} + +/* This function has to be inlined, because the verifier otherwise rejects it + * due to returning a pointer to the stack. This is technically correct, since + * scratch is allocated on the stack. However, this usage should be safe since + * it's the callers stack after all. + */ +static inline __attribute__((__always_inline__)) struct ipv6hdr * +pkt_parse_ipv6(buf_t *pkt, struct ipv6hdr *scratch, uint8_t *proto, + bool *is_fragment) +{ + struct ipv6hdr *ipv6 = buf_assign(pkt, sizeof(*ipv6), scratch); + if (ipv6 == NULL) { + return NULL; + } + + if (!pkt_skip_ipv6_extension_headers(pkt, ipv6, proto, is_fragment)) { + return NULL; + } + + return ipv6; +} + +/* Global metrics, per CPU + */ +struct bpf_map_def metrics_map SEC("maps") = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(unsigned int), + .value_size = sizeof(metrics_t), + .max_entries = 1, +}; + +static metrics_t *get_global_metrics(void) +{ + uint64_t key = 0; + return bpf_map_lookup_elem(&metrics_map, &key); +} + +static ret_t accept_locally(struct __sk_buff *skb, encap_headers_t *encap) +{ + const int payload_off = + sizeof(*encap) + + sizeof(struct in_addr) * encap->unigue.hop_count; + int32_t encap_overhead = payload_off - sizeof(struct ethhdr); + + // Changing the ethertype if the encapsulated packet is ipv6 + if (encap->gue.proto_ctype == IPPROTO_IPV6) { + encap->eth.h_proto = bpf_htons(ETH_P_IPV6); + } + + if (bpf_skb_adjust_room(skb, -encap_overhead, BPF_ADJ_ROOM_MAC, + BPF_F_ADJ_ROOM_FIXED_GSO)) { + return TC_ACT_SHOT; + } + + return bpf_redirect(skb->ifindex, BPF_F_INGRESS); +} + +static ret_t forward_with_gre(struct __sk_buff *skb, encap_headers_t *encap, + struct in_addr *next_hop, metrics_t *metrics) +{ + metrics->forwarded_packets_total_gre++; + + const int payload_off = + sizeof(*encap) + + sizeof(struct in_addr) * encap->unigue.hop_count; + int32_t encap_overhead = + payload_off - sizeof(struct ethhdr) - sizeof(struct iphdr); + int32_t delta = sizeof(struct gre_base_hdr) - encap_overhead; + uint16_t proto = ETH_P_IP; + + /* Loop protection: the inner packet's TTL is decremented as a safeguard + * against any forwarding loop. As the only interesting field is the TTL + * hop limit for IPv6, it is easier to use bpf_skb_load_bytes/bpf_skb_store_bytes + * as they handle the split packets if needed (no need for the data to be + * in the linear section). + */ + if (encap->gue.proto_ctype == IPPROTO_IPV6) { + proto = ETH_P_IPV6; + uint8_t ttl; + int rc; + + rc = bpf_skb_load_bytes( + skb, payload_off + offsetof(struct ipv6hdr, hop_limit), + &ttl, 1); + if (rc != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (ttl == 0) { + metrics->errors_total_redirect_loop++; + return TC_ACT_SHOT; + } + + ttl--; + rc = bpf_skb_store_bytes( + skb, payload_off + offsetof(struct ipv6hdr, hop_limit), + &ttl, 1, 0); + if (rc != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + } else { + uint8_t ttl; + int rc; + + rc = bpf_skb_load_bytes( + skb, payload_off + offsetof(struct iphdr, ttl), &ttl, + 1); + if (rc != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (ttl == 0) { + metrics->errors_total_redirect_loop++; + return TC_ACT_SHOT; + } + + /* IPv4 also has a checksum to patch. While the TTL is only one byte, + * this function only works for 2 and 4 bytes arguments (the result is + * the same). + */ + rc = bpf_l3_csum_replace( + skb, payload_off + offsetof(struct iphdr, check), ttl, + ttl - 1, 2); + if (rc != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + ttl--; + rc = bpf_skb_store_bytes( + skb, payload_off + offsetof(struct iphdr, ttl), &ttl, 1, + 0); + if (rc != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + } + + if (bpf_skb_adjust_room(skb, delta, BPF_ADJ_ROOM_NET, + BPF_F_ADJ_ROOM_FIXED_GSO)) { + metrics->errors_total_encap_adjust_failed++; + return TC_ACT_SHOT; + } + + if (bpf_skb_pull_data(skb, sizeof(encap_gre_t))) { + metrics->errors_total_encap_buffer_too_small++; + return TC_ACT_SHOT; + } + + buf_t pkt = { + .skb = skb, + .head = (uint8_t *)(long)skb->data, + .tail = (uint8_t *)(long)skb->data_end, + }; + + encap_gre_t *encap_gre = buf_assign(&pkt, sizeof(encap_gre_t), NULL); + if (encap_gre == NULL) { + metrics->errors_total_encap_buffer_too_small++; + return TC_ACT_SHOT; + } + + encap_gre->ip.protocol = IPPROTO_GRE; + encap_gre->ip.daddr = next_hop->s_addr; + encap_gre->ip.saddr = ENCAPSULATION_IP; + encap_gre->ip.tot_len = + bpf_htons(bpf_ntohs(encap_gre->ip.tot_len) + delta); + encap_gre->gre.flags = 0; + encap_gre->gre.protocol = bpf_htons(proto); + pkt_ipv4_checksum((void *)&encap_gre->ip); + + return bpf_redirect(skb->ifindex, 0); +} + +static ret_t forward_to_next_hop(struct __sk_buff *skb, encap_headers_t *encap, + struct in_addr *next_hop, metrics_t *metrics) +{ + /* swap L2 addresses */ + /* This assumes that packets are received from a router. + * So just swapping the MAC addresses here will make the packet go back to + * the router, which will send it to the appropriate machine. + */ + unsigned char temp[ETH_ALEN]; + memcpy(temp, encap->eth.h_dest, sizeof(temp)); + memcpy(encap->eth.h_dest, encap->eth.h_source, + sizeof(encap->eth.h_dest)); + memcpy(encap->eth.h_source, temp, sizeof(encap->eth.h_source)); + + if (encap->unigue.next_hop == encap->unigue.hop_count - 1 && + encap->unigue.last_hop_gre) { + return forward_with_gre(skb, encap, next_hop, metrics); + } + + metrics->forwarded_packets_total_gue++; + uint32_t old_saddr = encap->ip.saddr; + encap->ip.saddr = encap->ip.daddr; + encap->ip.daddr = next_hop->s_addr; + if (encap->unigue.next_hop < encap->unigue.hop_count) { + encap->unigue.next_hop++; + } + + /* Remove ip->saddr, add next_hop->s_addr */ + const uint64_t off = offsetof(typeof(*encap), ip.check); + int ret = bpf_l3_csum_replace(skb, off, old_saddr, next_hop->s_addr, 4); + if (ret < 0) { + return TC_ACT_SHOT; + } + + return bpf_redirect(skb->ifindex, 0); +} + +static ret_t skip_next_hops(buf_t *pkt, int n) +{ + switch (n) { + case 1: + if (!buf_skip(pkt, sizeof(struct in_addr))) + return TC_ACT_SHOT; + case 0: + return CONTINUE_PROCESSING; + + default: + return TC_ACT_SHOT; + } +} + +/* Get the next hop from the GLB header. + * + * Sets next_hop->s_addr to 0 if there are no more hops left. + * pkt is positioned just after the variable length GLB header + * iff the call is successful. + */ +static ret_t get_next_hop(buf_t *pkt, encap_headers_t *encap, + struct in_addr *next_hop) +{ + if (encap->unigue.next_hop > encap->unigue.hop_count) { + return TC_ACT_SHOT; + } + + /* Skip "used" next hops. */ + MAYBE_RETURN(skip_next_hops(pkt, encap->unigue.next_hop)); + + if (encap->unigue.next_hop == encap->unigue.hop_count) { + /* No more next hops, we are at the end of the GLB header. */ + next_hop->s_addr = 0; + return CONTINUE_PROCESSING; + } + + if (!buf_copy(pkt, next_hop, sizeof(*next_hop))) { + return TC_ACT_SHOT; + } + + /* Skip the remainig next hops (may be zero). */ + return skip_next_hops(pkt, encap->unigue.hop_count - + encap->unigue.next_hop - 1); +} + +/* Fill a bpf_sock_tuple to be used with the socket lookup functions. + * This is a kludge that let's us work around verifier limitations: + * + * fill_tuple(&t, foo, sizeof(struct iphdr), 123, 321) + * + * clang will substitue a costant for sizeof, which allows the verifier + * to track it's value. Based on this, it can figure out the constant + * return value, and calling code works while still being "generic" to + * IPv4 and IPv6. + */ +static uint64_t fill_tuple(struct bpf_sock_tuple *tuple, void *iph, + uint64_t iphlen, uint16_t sport, uint16_t dport) +{ + switch (iphlen) { + case sizeof(struct iphdr): { + struct iphdr *ipv4 = (struct iphdr *)iph; + tuple->ipv4.daddr = ipv4->daddr; + tuple->ipv4.saddr = ipv4->saddr; + tuple->ipv4.sport = sport; + tuple->ipv4.dport = dport; + return sizeof(tuple->ipv4); + } + + case sizeof(struct ipv6hdr): { + struct ipv6hdr *ipv6 = (struct ipv6hdr *)iph; + memcpy(&tuple->ipv6.daddr, &ipv6->daddr, + sizeof(tuple->ipv6.daddr)); + memcpy(&tuple->ipv6.saddr, &ipv6->saddr, + sizeof(tuple->ipv6.saddr)); + tuple->ipv6.sport = sport; + tuple->ipv6.dport = dport; + return sizeof(tuple->ipv6); + } + + default: + return 0; + } +} + +static verdict_t classify_tcp(struct __sk_buff *skb, + struct bpf_sock_tuple *tuple, uint64_t tuplen, + void *iph, struct tcphdr *tcp) +{ + struct bpf_sock *sk = + bpf_skc_lookup_tcp(skb, tuple, tuplen, BPF_F_CURRENT_NETNS, 0); + if (sk == NULL) { + return UNKNOWN; + } + + if (sk->state != BPF_TCP_LISTEN) { + bpf_sk_release(sk); + return ESTABLISHED; + } + + if (iph != NULL && tcp != NULL) { + /* Kludge: we've run out of arguments, but need the length of the ip header. */ + uint64_t iphlen = sizeof(struct iphdr); + if (tuplen == sizeof(tuple->ipv6)) { + iphlen = sizeof(struct ipv6hdr); + } + + if (bpf_tcp_check_syncookie(sk, iph, iphlen, tcp, + sizeof(*tcp)) == 0) { + bpf_sk_release(sk); + return SYN_COOKIE; + } + } + + bpf_sk_release(sk); + return UNKNOWN; +} + +static verdict_t classify_udp(struct __sk_buff *skb, + struct bpf_sock_tuple *tuple, uint64_t tuplen) +{ + struct bpf_sock *sk = + bpf_sk_lookup_udp(skb, tuple, tuplen, BPF_F_CURRENT_NETNS, 0); + if (sk == NULL) { + return UNKNOWN; + } + + if (sk->state == BPF_TCP_ESTABLISHED) { + bpf_sk_release(sk); + return ESTABLISHED; + } + + bpf_sk_release(sk); + return UNKNOWN; +} + +static verdict_t classify_icmp(struct __sk_buff *skb, uint8_t proto, + struct bpf_sock_tuple *tuple, uint64_t tuplen, + metrics_t *metrics) +{ + switch (proto) { + case IPPROTO_TCP: + return classify_tcp(skb, tuple, tuplen, NULL, NULL); + + case IPPROTO_UDP: + return classify_udp(skb, tuple, tuplen); + + default: + metrics->errors_total_malformed_icmp++; + return INVALID; + } +} + +static verdict_t process_icmpv4(buf_t *pkt, metrics_t *metrics) +{ + struct icmphdr icmp; + if (!buf_copy(pkt, &icmp, sizeof(icmp))) { + metrics->errors_total_malformed_icmp++; + return INVALID; + } + + /* We should never receive encapsulated echo replies. */ + if (icmp.type == ICMP_ECHOREPLY) { + metrics->errors_total_icmp_echo_replies++; + return INVALID; + } + + if (icmp.type == ICMP_ECHO) { + return ECHO_REQUEST; + } + + if (icmp.type != ICMP_DEST_UNREACH || icmp.code != ICMP_FRAG_NEEDED) { + metrics->errors_total_unwanted_icmp++; + return INVALID; + } + + struct iphdr _ip4; + const struct iphdr *ipv4 = pkt_parse_ipv4(pkt, &_ip4); + if (ipv4 == NULL) { + metrics->errors_total_malformed_icmp_pkt_too_big++; + return INVALID; + } + + /* The source address in the outer IP header is from the entity that + * originated the ICMP message. Use the original IP header to restore + * the correct flow tuple. + */ + struct bpf_sock_tuple tuple; + tuple.ipv4.saddr = ipv4->daddr; + tuple.ipv4.daddr = ipv4->saddr; + + if (!pkt_parse_icmp_l4_ports(pkt, (flow_ports_t *)&tuple.ipv4.sport)) { + metrics->errors_total_malformed_icmp_pkt_too_big++; + return INVALID; + } + + return classify_icmp(pkt->skb, ipv4->protocol, &tuple, + sizeof(tuple.ipv4), metrics); +} + +static verdict_t process_icmpv6(buf_t *pkt, metrics_t *metrics) +{ + struct icmp6hdr icmp6; + if (!buf_copy(pkt, &icmp6, sizeof(icmp6))) { + metrics->errors_total_malformed_icmp++; + return INVALID; + } + + /* We should never receive encapsulated echo replies. */ + if (icmp6.icmp6_type == ICMPV6_ECHO_REPLY) { + metrics->errors_total_icmp_echo_replies++; + return INVALID; + } + + if (icmp6.icmp6_type == ICMPV6_ECHO_REQUEST) { + return ECHO_REQUEST; + } + + if (icmp6.icmp6_type != ICMPV6_PKT_TOOBIG) { + metrics->errors_total_unwanted_icmp++; + return INVALID; + } + + bool is_fragment; + uint8_t l4_proto; + struct ipv6hdr _ipv6; + const struct ipv6hdr *ipv6 = + pkt_parse_ipv6(pkt, &_ipv6, &l4_proto, &is_fragment); + if (ipv6 == NULL) { + metrics->errors_total_malformed_icmp_pkt_too_big++; + return INVALID; + } + + if (is_fragment) { + metrics->errors_total_fragmented_ip++; + return INVALID; + } + + /* Swap source and dest addresses. */ + struct bpf_sock_tuple tuple; + memcpy(&tuple.ipv6.saddr, &ipv6->daddr, sizeof(tuple.ipv6.saddr)); + memcpy(&tuple.ipv6.daddr, &ipv6->saddr, sizeof(tuple.ipv6.daddr)); + + if (!pkt_parse_icmp_l4_ports(pkt, (flow_ports_t *)&tuple.ipv6.sport)) { + metrics->errors_total_malformed_icmp_pkt_too_big++; + return INVALID; + } + + return classify_icmp(pkt->skb, l4_proto, &tuple, sizeof(tuple.ipv6), + metrics); +} + +static verdict_t process_tcp(buf_t *pkt, void *iph, uint64_t iphlen, + metrics_t *metrics) +{ + metrics->l4_protocol_packets_total_tcp++; + + struct tcphdr _tcp; + struct tcphdr *tcp = buf_assign(pkt, sizeof(_tcp), &_tcp); + if (tcp == NULL) { + metrics->errors_total_malformed_tcp++; + return INVALID; + } + + if (tcp->syn) { + return SYN; + } + + struct bpf_sock_tuple tuple; + uint64_t tuplen = + fill_tuple(&tuple, iph, iphlen, tcp->source, tcp->dest); + return classify_tcp(pkt->skb, &tuple, tuplen, iph, tcp); +} + +static verdict_t process_udp(buf_t *pkt, void *iph, uint64_t iphlen, + metrics_t *metrics) +{ + metrics->l4_protocol_packets_total_udp++; + + struct udphdr _udp; + struct udphdr *udph = buf_assign(pkt, sizeof(_udp), &_udp); + if (udph == NULL) { + metrics->errors_total_malformed_udp++; + return INVALID; + } + + struct bpf_sock_tuple tuple; + uint64_t tuplen = + fill_tuple(&tuple, iph, iphlen, udph->source, udph->dest); + return classify_udp(pkt->skb, &tuple, tuplen); +} + +static verdict_t process_ipv4(buf_t *pkt, metrics_t *metrics) +{ + metrics->l3_protocol_packets_total_ipv4++; + + struct iphdr _ip4; + struct iphdr *ipv4 = pkt_parse_ipv4(pkt, &_ip4); + if (ipv4 == NULL) { + metrics->errors_total_malformed_ip++; + return INVALID; + } + + if (ipv4->version != 4) { + metrics->errors_total_malformed_ip++; + return INVALID; + } + + if (ipv4_is_fragment(ipv4)) { + metrics->errors_total_fragmented_ip++; + return INVALID; + } + + switch (ipv4->protocol) { + case IPPROTO_ICMP: + return process_icmpv4(pkt, metrics); + + case IPPROTO_TCP: + return process_tcp(pkt, ipv4, sizeof(*ipv4), metrics); + + case IPPROTO_UDP: + return process_udp(pkt, ipv4, sizeof(*ipv4), metrics); + + default: + metrics->errors_total_unknown_l4_proto++; + return INVALID; + } +} + +static verdict_t process_ipv6(buf_t *pkt, metrics_t *metrics) +{ + metrics->l3_protocol_packets_total_ipv6++; + + uint8_t l4_proto; + bool is_fragment; + struct ipv6hdr _ipv6; + struct ipv6hdr *ipv6 = + pkt_parse_ipv6(pkt, &_ipv6, &l4_proto, &is_fragment); + if (ipv6 == NULL) { + metrics->errors_total_malformed_ip++; + return INVALID; + } + + if (ipv6->version != 6) { + metrics->errors_total_malformed_ip++; + return INVALID; + } + + if (is_fragment) { + metrics->errors_total_fragmented_ip++; + return INVALID; + } + + switch (l4_proto) { + case IPPROTO_ICMPV6: + return process_icmpv6(pkt, metrics); + + case IPPROTO_TCP: + return process_tcp(pkt, ipv6, sizeof(*ipv6), metrics); + + case IPPROTO_UDP: + return process_udp(pkt, ipv6, sizeof(*ipv6), metrics); + + default: + metrics->errors_total_unknown_l4_proto++; + return INVALID; + } +} + +SEC("classifier/cls_redirect") +int cls_redirect(struct __sk_buff *skb) +{ + metrics_t *metrics = get_global_metrics(); + if (metrics == NULL) { + return TC_ACT_SHOT; + } + + metrics->processed_packets_total++; + + /* Pass bogus packets as long as we're not sure they're + * destined for us. + */ + if (skb->protocol != bpf_htons(ETH_P_IP)) { + return TC_ACT_OK; + } + + encap_headers_t *encap; + + /* Make sure that all encapsulation headers are available in + * the linear portion of the skb. This makes it easy to manipulate them. + */ + if (bpf_skb_pull_data(skb, sizeof(*encap))) { + return TC_ACT_OK; + } + + buf_t pkt = { + .skb = skb, + .head = (uint8_t *)(long)skb->data, + .tail = (uint8_t *)(long)skb->data_end, + }; + + encap = buf_assign(&pkt, sizeof(*encap), NULL); + if (encap == NULL) { + return TC_ACT_OK; + } + + if (encap->ip.ihl != 5) { + /* We never have any options. */ + return TC_ACT_OK; + } + + if (encap->ip.daddr != ENCAPSULATION_IP || + encap->ip.protocol != IPPROTO_UDP) { + return TC_ACT_OK; + } + + /* TODO Check UDP length? */ + if (encap->udp.dest != ENCAPSULATION_PORT) { + return TC_ACT_OK; + } + + /* We now know that the packet is destined to us, we can + * drop bogus ones. + */ + if (ipv4_is_fragment((void *)&encap->ip)) { + metrics->errors_total_fragmented_ip++; + return TC_ACT_SHOT; + } + + if (encap->gue.variant != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (encap->gue.control != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (encap->gue.flags != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (encap->gue.hlen != + sizeof(encap->unigue) / 4 + encap->unigue.hop_count) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (encap->unigue.version != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (encap->unigue.reserved != 0) { + return TC_ACT_SHOT; + } + + struct in_addr next_hop; + MAYBE_RETURN(get_next_hop(&pkt, encap, &next_hop)); + + if (next_hop.s_addr == 0) { + metrics->accepted_packets_total_last_hop++; + return accept_locally(skb, encap); + } + + verdict_t verdict; + switch (encap->gue.proto_ctype) { + case IPPROTO_IPIP: + verdict = process_ipv4(&pkt, metrics); + break; + + case IPPROTO_IPV6: + verdict = process_ipv6(&pkt, metrics); + break; + + default: + metrics->errors_total_unknown_l3_proto++; + return TC_ACT_SHOT; + } + + switch (verdict) { + case INVALID: + /* metrics have already been bumped */ + return TC_ACT_SHOT; + + case UNKNOWN: + return forward_to_next_hop(skb, encap, &next_hop, metrics); + + case ECHO_REQUEST: + metrics->accepted_packets_total_icmp_echo_request++; + break; + + case SYN: + if (encap->unigue.forward_syn) { + return forward_to_next_hop(skb, encap, &next_hop, + metrics); + } + + metrics->accepted_packets_total_syn++; + break; + + case SYN_COOKIE: + metrics->accepted_packets_total_syn_cookies++; + break; + + case ESTABLISHED: + metrics->accepted_packets_total_established++; + break; + } + + return accept_locally(skb, encap); +} diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.h b/tools/testing/selftests/bpf/progs/test_cls_redirect.h new file mode 100644 index 000000000000..76eab0aacba0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ +/* Copyright 2019, 2020 Cloudflare */ + +#include <stdbool.h> +#include <stddef.h> +#include <stdint.h> +#include <string.h> + +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/udp.h> + +struct gre_base_hdr { + uint16_t flags; + uint16_t protocol; +} __attribute__((packed)); + +struct guehdr { +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + uint8_t hlen : 5, control : 1, variant : 2; +#else + uint8_t variant : 2, control : 1, hlen : 5; +#endif + uint8_t proto_ctype; + uint16_t flags; +}; + +struct unigue { +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + uint8_t _r : 2, last_hop_gre : 1, forward_syn : 1, version : 4; +#else + uint8_t version : 4, forward_syn : 1, last_hop_gre : 1, _r : 2; +#endif + uint8_t reserved; + uint8_t next_hop; + uint8_t hop_count; + // Next hops go here +} __attribute__((packed)); + +typedef struct { + struct ethhdr eth; + struct iphdr ip; + struct gre_base_hdr gre; +} __attribute__((packed)) encap_gre_t; + +typedef struct { + struct ethhdr eth; + struct iphdr ip; + struct udphdr udp; + struct guehdr gue; + struct unigue unigue; +} __attribute__((packed)) encap_headers_t; diff --git a/tools/testing/selftests/bpf/progs/test_enable_stats.c b/tools/testing/selftests/bpf/progs/test_enable_stats.c new file mode 100644 index 000000000000..01a002ade529 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_enable_stats.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include <linux/types.h> +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +__u64 count = 0; + +SEC("raw_tracepoint/sys_enter") +int test_enable_stats(void *ctx) +{ + count += 1; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_obj_id.c b/tools/testing/selftests/bpf/progs/test_obj_id.c index 98b9de2fafd0..ded71b3ff6b4 100644 --- a/tools/testing/selftests/bpf/progs/test_obj_id.c +++ b/tools/testing/selftests/bpf/progs/test_obj_id.c @@ -3,16 +3,8 @@ */ #include <stddef.h> #include <linux/bpf.h> -#include <linux/pkt_cls.h> #include <bpf/bpf_helpers.h> -/* It is a dumb bpf program such that it must have no - * issue to be loaded since testing the verifier is - * not the focus here. - */ - -int _version SEC("version") = 1; - struct { __uint(type, BPF_MAP_TYPE_ARRAY); __uint(max_entries, 1); @@ -20,13 +12,13 @@ struct { __type(value, __u64); } test_map_id SEC(".maps"); -SEC("test_obj_id_dummy") -int test_obj_id(struct __sk_buff *skb) +SEC("raw_tp/sys_enter") +int test_obj_id(void *ctx) { __u32 key = 0; __u64 *value; value = bpf_map_lookup_elem(&test_map_id, &key); - return TC_ACT_OK; + return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_sk_assign.c b/tools/testing/selftests/bpf/progs/test_sk_assign.c index 8f530843b4da..1ecd987005d2 100644 --- a/tools/testing/selftests/bpf/progs/test_sk_assign.c +++ b/tools/testing/selftests/bpf/progs/test_sk_assign.c @@ -16,6 +16,26 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> +/* Pin map under /sys/fs/bpf/tc/globals/<map name> */ +#define PIN_GLOBAL_NS 2 + +/* Must match struct bpf_elf_map layout from iproute2 */ +struct { + __u32 type; + __u32 size_key; + __u32 size_value; + __u32 max_elem; + __u32 flags; + __u32 id; + __u32 pinning; +} server_map SEC("maps") = { + .type = BPF_MAP_TYPE_SOCKMAP, + .size_key = sizeof(int), + .size_value = sizeof(__u64), + .max_elem = 1, + .pinning = PIN_GLOBAL_NS, +}; + int _version SEC("version") = 1; char _license[] SEC("license") = "GPL"; @@ -72,7 +92,9 @@ handle_udp(struct __sk_buff *skb, struct bpf_sock_tuple *tuple, bool ipv4) { struct bpf_sock_tuple ln = {0}; struct bpf_sock *sk; + const int zero = 0; size_t tuple_len; + __be16 dport; int ret; tuple_len = ipv4 ? sizeof(tuple->ipv4) : sizeof(tuple->ipv6); @@ -83,32 +105,11 @@ handle_udp(struct __sk_buff *skb, struct bpf_sock_tuple *tuple, bool ipv4) if (sk) goto assign; - if (ipv4) { - if (tuple->ipv4.dport != bpf_htons(4321)) - return TC_ACT_OK; - - ln.ipv4.daddr = bpf_htonl(0x7f000001); - ln.ipv4.dport = bpf_htons(1234); - - sk = bpf_sk_lookup_udp(skb, &ln, sizeof(ln.ipv4), - BPF_F_CURRENT_NETNS, 0); - } else { - if (tuple->ipv6.dport != bpf_htons(4321)) - return TC_ACT_OK; - - /* Upper parts of daddr are already zero. */ - ln.ipv6.daddr[3] = bpf_htonl(0x1); - ln.ipv6.dport = bpf_htons(1234); - - sk = bpf_sk_lookup_udp(skb, &ln, sizeof(ln.ipv6), - BPF_F_CURRENT_NETNS, 0); - } + dport = ipv4 ? tuple->ipv4.dport : tuple->ipv6.dport; + if (dport != bpf_htons(4321)) + return TC_ACT_OK; - /* workaround: We can't do a single socket lookup here, because then - * the compiler will likely spill tuple_len to the stack. This makes it - * lose all bounds information in the verifier, which then rejects the - * call as unsafe. - */ + sk = bpf_map_lookup_elem(&server_map, &zero); if (!sk) return TC_ACT_SHOT; @@ -123,7 +124,9 @@ handle_tcp(struct __sk_buff *skb, struct bpf_sock_tuple *tuple, bool ipv4) { struct bpf_sock_tuple ln = {0}; struct bpf_sock *sk; + const int zero = 0; size_t tuple_len; + __be16 dport; int ret; tuple_len = ipv4 ? sizeof(tuple->ipv4) : sizeof(tuple->ipv6); @@ -137,32 +140,11 @@ handle_tcp(struct __sk_buff *skb, struct bpf_sock_tuple *tuple, bool ipv4) bpf_sk_release(sk); } - if (ipv4) { - if (tuple->ipv4.dport != bpf_htons(4321)) - return TC_ACT_OK; + dport = ipv4 ? tuple->ipv4.dport : tuple->ipv6.dport; + if (dport != bpf_htons(4321)) + return TC_ACT_OK; - ln.ipv4.daddr = bpf_htonl(0x7f000001); - ln.ipv4.dport = bpf_htons(1234); - - sk = bpf_skc_lookup_tcp(skb, &ln, sizeof(ln.ipv4), - BPF_F_CURRENT_NETNS, 0); - } else { - if (tuple->ipv6.dport != bpf_htons(4321)) - return TC_ACT_OK; - - /* Upper parts of daddr are already zero. */ - ln.ipv6.daddr[3] = bpf_htonl(0x1); - ln.ipv6.dport = bpf_htons(1234); - - sk = bpf_skc_lookup_tcp(skb, &ln, sizeof(ln.ipv6), - BPF_F_CURRENT_NETNS, 0); - } - - /* workaround: We can't do a single socket lookup here, because then - * the compiler will likely spill tuple_len to the stack. This makes it - * lose all bounds information in the verifier, which then rejects the - * call as unsafe. - */ + sk = bpf_map_lookup_elem(&server_map, &zero); if (!sk) return TC_ACT_SHOT; diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c index 2d0b0b82a78a..50525235380e 100644 --- a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c +++ b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c @@ -45,7 +45,7 @@ int sysctl_tcp_mem(struct bpf_sysctl *ctx) unsigned long tcp_mem[3] = {0, 0, 0}; char value[MAX_VALUE_STR_LEN]; unsigned char i, off = 0; - int ret; + volatile int ret; if (ctx->write) return 0; diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index b521e0a512b6..93970ec1c9e9 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -351,6 +351,7 @@ int extract_build_id(char *build_id, size_t size) len = size; memcpy(build_id, line, len); build_id[len] = '\0'; + free(line); return 0; err: fclose(fp); @@ -420,6 +421,18 @@ static int libbpf_print_fn(enum libbpf_print_level level, return 0; } +static void free_str_set(const struct str_set *set) +{ + int i; + + if (!set) + return; + + for (i = 0; i < set->cnt; i++) + free((void *)set->strs[i]); + free(set->strs); +} + static int parse_str_list(const char *s, struct str_set *set) { char *input, *state = NULL, *next, **tmp, **strs = NULL; @@ -756,11 +769,11 @@ int main(int argc, char **argv) fprintf(stdout, "Summary: %d/%d PASSED, %d SKIPPED, %d FAILED\n", env.succ_cnt, env.sub_succ_cnt, env.skip_cnt, env.fail_cnt); - free(env.test_selector.blacklist.strs); - free(env.test_selector.whitelist.strs); + free_str_set(&env.test_selector.blacklist); + free_str_set(&env.test_selector.whitelist); free(env.test_selector.num_set); - free(env.subtest_selector.blacklist.strs); - free(env.subtest_selector.whitelist.strs); + free_str_set(&env.subtest_selector.blacklist); + free_str_set(&env.subtest_selector.whitelist); free(env.subtest_selector.num_set); return env.fail_cnt ? EXIT_FAILURE : EXIT_SUCCESS; diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index f4aff6b8284b..10188cc8e9e0 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -105,6 +105,13 @@ struct ipv6_packet { } __packed; extern struct ipv6_packet pkt_v6; +#define PRINT_FAIL(format...) \ + ({ \ + test__fail(); \ + fprintf(stdout, "%s:FAIL:%d ", __func__, __LINE__); \ + fprintf(stdout, ##format); \ + }) + #define _CHECK(condition, tag, duration, format...) ({ \ int __ret = !!(condition); \ int __save_errno = errno; \ diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 87eaa49609a0..21a1ce219c1c 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -50,7 +50,7 @@ #define MAX_INSNS BPF_MAXINSNS #define MAX_TEST_INSNS 1000000 #define MAX_FIXUPS 8 -#define MAX_NR_MAPS 19 +#define MAX_NR_MAPS 20 #define MAX_TEST_RUNS 8 #define POINTER_VALUE 0xcafe4all #define TEST_DATA_LEN 64 @@ -86,6 +86,7 @@ struct bpf_test { int fixup_map_array_small[MAX_FIXUPS]; int fixup_sk_storage_map[MAX_FIXUPS]; int fixup_map_event_output[MAX_FIXUPS]; + int fixup_map_reuseport_array[MAX_FIXUPS]; const char *errstr; const char *errstr_unpriv; uint32_t insn_processed; @@ -637,6 +638,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, int *fixup_map_array_small = test->fixup_map_array_small; int *fixup_sk_storage_map = test->fixup_sk_storage_map; int *fixup_map_event_output = test->fixup_map_event_output; + int *fixup_map_reuseport_array = test->fixup_map_reuseport_array; if (test->fill_helper) { test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn)); @@ -806,6 +808,14 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, fixup_map_event_output++; } while (*fixup_map_event_output); } + if (*fixup_map_reuseport_array) { + map_fds[19] = __create_map(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, + sizeof(u32), sizeof(u64), 1, 0); + do { + prog[*fixup_map_reuseport_array].imm = map_fds[19]; + fixup_map_reuseport_array++; + } while (*fixup_map_reuseport_array); + } } static int set_admin(bool admin) @@ -943,7 +953,12 @@ static void do_test_single(struct bpf_test *test, bool unpriv, attr.insns = prog; attr.insns_cnt = prog_len; attr.license = "GPL"; - attr.log_level = verbose || expected_ret == VERBOSE_ACCEPT ? 1 : 4; + if (verbose) + attr.log_level = 1; + else if (expected_ret == VERBOSE_ACCEPT) + attr.log_level = 2; + else + attr.log_level = 4; attr.prog_flags = pflags; fd_prog = bpf_load_program_xattr(&attr, bpf_vlog, sizeof(bpf_vlog)); diff --git a/tools/testing/selftests/bpf/verifier/event_output.c b/tools/testing/selftests/bpf/verifier/event_output.c index 130553e19eca..99f8f582c02b 100644 --- a/tools/testing/selftests/bpf/verifier/event_output.c +++ b/tools/testing/selftests/bpf/verifier/event_output.c @@ -92,3 +92,27 @@ .result = ACCEPT, .retval = 1, }, +{ + "perfevent for cgroup dev", + .insns = { __PERF_EVENT_INSNS__ }, + .prog_type = BPF_PROG_TYPE_CGROUP_DEVICE, + .fixup_map_event_output = { 4 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "perfevent for cgroup sysctl", + .insns = { __PERF_EVENT_INSNS__ }, + .prog_type = BPF_PROG_TYPE_CGROUP_SYSCTL, + .fixup_map_event_output = { 4 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "perfevent for cgroup sockopt", + .insns = { __PERF_EVENT_INSNS__ }, + .prog_type = BPF_PROG_TYPE_CGROUP_SOCKOPT, + .fixup_map_event_output = { 4 }, + .result = ACCEPT, + .retval = 1, +}, diff --git a/tools/testing/selftests/bpf/verifier/prevent_map_lookup.c b/tools/testing/selftests/bpf/verifier/prevent_map_lookup.c index da7a4b37cb98..fc4e301260f6 100644 --- a/tools/testing/selftests/bpf/verifier/prevent_map_lookup.c +++ b/tools/testing/selftests/bpf/verifier/prevent_map_lookup.c @@ -1,34 +1,4 @@ { - "prevent map lookup in sockmap", - .insns = { - BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), - BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), - BPF_LD_MAP_FD(BPF_REG_1, 0), - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_EXIT_INSN(), - }, - .fixup_map_sockmap = { 3 }, - .result = REJECT, - .errstr = "cannot pass map_type 15 into func bpf_map_lookup_elem", - .prog_type = BPF_PROG_TYPE_SOCK_OPS, -}, -{ - "prevent map lookup in sockhash", - .insns = { - BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), - BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), - BPF_LD_MAP_FD(BPF_REG_1, 0), - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_EXIT_INSN(), - }, - .fixup_map_sockhash = { 3 }, - .result = REJECT, - .errstr = "cannot pass map_type 18 into func bpf_map_lookup_elem", - .prog_type = BPF_PROG_TYPE_SOCK_OPS, -}, -{ "prevent map lookup in stack trace", .insns = { BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), diff --git a/tools/testing/selftests/bpf/verifier/sock.c b/tools/testing/selftests/bpf/verifier/sock.c index 9ed192e14f5f..0bc51ad9e0fb 100644 --- a/tools/testing/selftests/bpf/verifier/sock.c +++ b/tools/testing/selftests/bpf/verifier/sock.c @@ -516,3 +516,118 @@ .prog_type = BPF_PROG_TYPE_XDP, .result = ACCEPT, }, +{ + "bpf_map_lookup_elem(sockmap, &key)", + .insns = { + BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_sockmap = { 3 }, + .prog_type = BPF_PROG_TYPE_SK_SKB, + .result = REJECT, + .errstr = "Unreleased reference id=2 alloc_insn=5", +}, +{ + "bpf_map_lookup_elem(sockhash, &key)", + .insns = { + BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_sockhash = { 3 }, + .prog_type = BPF_PROG_TYPE_SK_SKB, + .result = REJECT, + .errstr = "Unreleased reference id=2 alloc_insn=5", +}, +{ + "bpf_map_lookup_elem(sockmap, &key); sk->type [fullsock field]; bpf_sk_release(sk)", + .insns = { + BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, type)), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + }, + .fixup_map_sockmap = { 3 }, + .prog_type = BPF_PROG_TYPE_SK_SKB, + .result = ACCEPT, +}, +{ + "bpf_map_lookup_elem(sockhash, &key); sk->type [fullsock field]; bpf_sk_release(sk)", + .insns = { + BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, type)), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + }, + .fixup_map_sockhash = { 3 }, + .prog_type = BPF_PROG_TYPE_SK_SKB, + .result = ACCEPT, +}, +{ + "bpf_sk_select_reuseport(ctx, reuseport_array, &key, flags)", + .insns = { + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -4), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_EMIT_CALL(BPF_FUNC_sk_select_reuseport), + BPF_EXIT_INSN(), + }, + .fixup_map_reuseport_array = { 4 }, + .prog_type = BPF_PROG_TYPE_SK_REUSEPORT, + .result = ACCEPT, +}, +{ + "bpf_sk_select_reuseport(ctx, sockmap, &key, flags)", + .insns = { + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -4), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_EMIT_CALL(BPF_FUNC_sk_select_reuseport), + BPF_EXIT_INSN(), + }, + .fixup_map_sockmap = { 4 }, + .prog_type = BPF_PROG_TYPE_SK_REUSEPORT, + .result = ACCEPT, +}, +{ + "bpf_sk_select_reuseport(ctx, sockhash, &key, flags)", + .insns = { + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -4), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_EMIT_CALL(BPF_FUNC_sk_select_reuseport), + BPF_EXIT_INSN(), + }, + .fixup_map_sockmap = { 4 }, + .prog_type = BPF_PROG_TYPE_SK_REUSEPORT, + .result = ACCEPT, +}, |