diff options
| author | David S. Miller <davem@davemloft.net> | 2020-06-01 15:53:08 -0700 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2020-06-01 15:53:08 -0700 |
| commit | 9a25c1df24a6fea9dc79eec950453c4e00f707fd (patch) | |
| tree | 1188078f9838a3b6a60a3923ed31df142ffc8ed6 /tools | |
| parent | efd7ed0f5f2d07ccbb1853c5d46656cdfa1371fb (diff) | |
| parent | cf51abcded837ef209faa03a62b2ea44e45995e8 (diff) | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Alexei Starovoitov says:
====================
pull-request: bpf-next 2020-06-01
The following pull-request contains BPF updates for your *net-next* tree.
We've added 55 non-merge commits during the last 1 day(s) which contain
a total of 91 files changed, 4986 insertions(+), 463 deletions(-).
The main changes are:
1) Add rx_queue_mapping to bpf_sock from Amritha.
2) Add BPF ring buffer, from Andrii.
3) Attach and run programs through devmap, from David.
4) Allow SO_BINDTODEVICE opt in bpf_setsockopt, from Ferenc.
5) link based flow_dissector, from Jakub.
6) Use tracing helpers for lsm programs, from Jiri.
7) Several sk_msg fixes and extensions, from John.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'tools')
51 files changed, 3127 insertions, 260 deletions
diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index 41a1346934a1..faac8189b285 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -553,7 +553,7 @@ static int do_dump(int argc, char **argv) btf = btf__parse_elf(*argv, NULL); if (IS_ERR(btf)) { - err = PTR_ERR(btf); + err = -PTR_ERR(btf); btf = NULL; p_err("failed to load BTF from %s: %s", *argv, strerror(err)); @@ -951,9 +951,9 @@ static int do_help(int argc, char **argv) } fprintf(stderr, - "Usage: %s btf { show | list } [id BTF_ID]\n" - " %s btf dump BTF_SRC [format FORMAT]\n" - " %s btf help\n" + "Usage: %1$s %2$s { show | list } [id BTF_ID]\n" + " %1$s %2$s dump BTF_SRC [format FORMAT]\n" + " %1$s %2$s help\n" "\n" " BTF_SRC := { id BTF_ID | prog PROG | map MAP [{key | value | kv | all}] | file FILE }\n" " FORMAT := { raw | c }\n" @@ -961,7 +961,7 @@ static int do_help(int argc, char **argv) " " HELP_SPEC_PROGRAM "\n" " " HELP_SPEC_OPTIONS "\n" "", - bin_name, bin_name, bin_name); + bin_name, "btf"); return 0; } diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c index 27931db421d8..d901cc1b904a 100644 --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@ -491,20 +491,18 @@ static int do_help(int argc, char **argv) } fprintf(stderr, - "Usage: %s %s { show | list } CGROUP [**effective**]\n" - " %s %s tree [CGROUP_ROOT] [**effective**]\n" - " %s %s attach CGROUP ATTACH_TYPE PROG [ATTACH_FLAGS]\n" - " %s %s detach CGROUP ATTACH_TYPE PROG\n" - " %s %s help\n" + "Usage: %1$s %2$s { show | list } CGROUP [**effective**]\n" + " %1$s %2$s tree [CGROUP_ROOT] [**effective**]\n" + " %1$s %2$s attach CGROUP ATTACH_TYPE PROG [ATTACH_FLAGS]\n" + " %1$s %2$s detach CGROUP ATTACH_TYPE PROG\n" + " %1$s %2$s help\n" "\n" HELP_SPEC_ATTACH_TYPES "\n" " " HELP_SPEC_ATTACH_FLAGS "\n" " " HELP_SPEC_PROGRAM "\n" " " HELP_SPEC_OPTIONS "\n" "", - bin_name, argv[-2], - bin_name, argv[-2], bin_name, argv[-2], - bin_name, argv[-2], bin_name, argv[-2]); + bin_name, argv[-2]); return 0; } diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index 1b73e63274b5..768bf77df886 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -758,11 +758,29 @@ static void section_misc(const char *define_prefix, __u32 ifindex) print_end_section(); } +#ifdef USE_LIBCAP +#define capability(c) { c, false, #c } +#define capability_msg(a, i) a[i].set ? "" : a[i].name, a[i].set ? "" : ", " +#endif + static int handle_perms(void) { #ifdef USE_LIBCAP - cap_value_t cap_list[1] = { CAP_SYS_ADMIN }; - bool has_sys_admin_cap = false; + struct { + cap_value_t cap; + bool set; + char name[14]; /* strlen("CAP_SYS_ADMIN") */ + } bpf_caps[] = { + capability(CAP_SYS_ADMIN), +#ifdef CAP_BPF + capability(CAP_BPF), + capability(CAP_NET_ADMIN), + capability(CAP_PERFMON), +#endif + }; + cap_value_t cap_list[ARRAY_SIZE(bpf_caps)]; + unsigned int i, nb_bpf_caps = 0; + bool cap_sys_admin_only = true; cap_flag_value_t val; int res = -1; cap_t caps; @@ -774,35 +792,64 @@ static int handle_perms(void) 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; +#ifdef CAP_BPF + if (CAP_IS_SUPPORTED(CAP_BPF)) + cap_sys_admin_only = false; +#endif - 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; + for (i = 0; i < ARRAY_SIZE(bpf_caps); i++) { + const char *cap_name = bpf_caps[i].name; + cap_value_t cap = bpf_caps[i].cap; + + if (cap_get_flag(caps, cap, CAP_EFFECTIVE, &val)) { + p_err("bug: failed to retrieve %s status: %s", cap_name, + strerror(errno)); + goto exit_free; + } + + if (val == CAP_SET) { + bpf_caps[i].set = true; + cap_list[nb_bpf_caps++] = cap; + } + + if (cap_sys_admin_only) + /* System does not know about CAP_BPF, meaning that + * CAP_SYS_ADMIN is the only capability required. We + * just checked it, break. + */ + break; } - if ((run_as_unprivileged && !has_sys_admin_cap) || - (!run_as_unprivileged && has_sys_admin_cap)) { + if ((run_as_unprivileged && !nb_bpf_caps) || + (!run_as_unprivileged && nb_bpf_caps == ARRAY_SIZE(bpf_caps)) || + (!run_as_unprivileged && cap_sys_admin_only && nb_bpf_caps)) { /* We are all good, exit now */ res = 0; goto exit_free; } - /* if (run_as_unprivileged && has_sys_admin_cap), drop CAP_SYS_ADMIN */ + if (!run_as_unprivileged) { + if (cap_sys_admin_only) + p_err("missing %s, required for full feature probing; run as root or use 'unprivileged'", + bpf_caps[0].name); + else + p_err("missing %s%s%s%s%s%s%s%srequired for full feature probing; run as root or use 'unprivileged'", + capability_msg(bpf_caps, 0), + capability_msg(bpf_caps, 1), + capability_msg(bpf_caps, 2), + capability_msg(bpf_caps, 3)); + goto exit_free; + } - if (cap_set_flag(caps, CAP_EFFECTIVE, ARRAY_SIZE(cap_list), cap_list, + /* if (run_as_unprivileged && nb_bpf_caps > 0), drop capabilities. */ + if (cap_set_flag(caps, CAP_EFFECTIVE, nb_bpf_caps, cap_list, CAP_CLEAR)) { - p_err("bug: failed to clear CAP_SYS_ADMIN from capabilities"); + p_err("bug: failed to clear capabilities: %s", strerror(errno)); goto exit_free; } if (cap_set_proc(caps)) { - p_err("failed to drop CAP_SYS_ADMIN: %s", strerror(errno)); + p_err("failed to drop capabilities: %s", strerror(errno)); goto exit_free; } @@ -817,7 +864,7 @@ exit_free: return res; #else - /* Detection assumes user has sufficient privileges (CAP_SYS_ADMIN). + /* Detection assumes user has specific privileges. * We do not use libpcap so let's approximate, and restrict usage to * root user only. */ @@ -901,7 +948,7 @@ static int do_probe(int argc, char **argv) } } - /* Full feature detection requires CAP_SYS_ADMIN privilege. + /* Full feature detection requires specific privileges. * Let's approximate, and warn if user is not root. */ if (handle_perms()) @@ -937,12 +984,12 @@ static int do_help(int argc, char **argv) } fprintf(stderr, - "Usage: %s %s probe [COMPONENT] [full] [unprivileged] [macros [prefix PREFIX]]\n" - " %s %s help\n" + "Usage: %1$s %2$s probe [COMPONENT] [full] [unprivileged] [macros [prefix PREFIX]]\n" + " %1$s %2$s help\n" "\n" " COMPONENT := { kernel | dev NAME }\n" "", - bin_name, argv[-2], bin_name, argv[-2]); + bin_name, argv[-2]); return 0; } diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c index 0e5f0236cc76..a3c4bb86c05a 100644 --- a/tools/bpf/bpftool/gen.c +++ b/tools/bpf/bpftool/gen.c @@ -586,12 +586,12 @@ static int do_help(int argc, char **argv) } fprintf(stderr, - "Usage: %1$s gen skeleton FILE\n" - " %1$s gen help\n" + "Usage: %1$s %2$s skeleton FILE\n" + " %1$s %2$s help\n" "\n" " " HELP_SPEC_OPTIONS "\n" "", - bin_name); + bin_name, "gen"); return 0; } diff --git a/tools/bpf/bpftool/iter.c b/tools/bpf/bpftool/iter.c index eb5987a0c3b6..33240fcc6319 100644 --- a/tools/bpf/bpftool/iter.c +++ b/tools/bpf/bpftool/iter.c @@ -68,10 +68,10 @@ close_obj: static int do_help(int argc, char **argv) { fprintf(stderr, - "Usage: %s %s pin OBJ PATH\n" - " %s %s help\n" - "\n", - bin_name, argv[-2], bin_name, argv[-2]); + "Usage: %1$s %2$s pin OBJ PATH\n" + " %1$s %2$s help\n" + "", + bin_name, "iter"); return 0; } diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c index b6a0b35c78ae..fca57ee8fafe 100644 --- a/tools/bpf/bpftool/link.c +++ b/tools/bpf/bpftool/link.c @@ -17,6 +17,7 @@ static const char * const link_type_name[] = { [BPF_LINK_TYPE_TRACING] = "tracing", [BPF_LINK_TYPE_CGROUP] = "cgroup", [BPF_LINK_TYPE_ITER] = "iter", + [BPF_LINK_TYPE_NETNS] = "netns", }; static int link_parse_fd(int *argc, char ***argv) @@ -62,6 +63,15 @@ show_link_header_json(struct bpf_link_info *info, json_writer_t *wtr) jsonw_uint_field(json_wtr, "prog_id", info->prog_id); } +static void show_link_attach_type_json(__u32 attach_type, json_writer_t *wtr) +{ + if (attach_type < ARRAY_SIZE(attach_type_name)) + jsonw_string_field(wtr, "attach_type", + attach_type_name[attach_type]); + else + jsonw_uint_field(wtr, "attach_type", attach_type); +} + static int get_prog_info(int prog_id, struct bpf_prog_info *info) { __u32 len = sizeof(*info); @@ -105,22 +115,18 @@ static int show_link_close_json(int fd, struct bpf_link_info *info) 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); + show_link_attach_type_json(info->tracing.attach_type, + json_wtr); 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); + show_link_attach_type_json(info->cgroup.attach_type, json_wtr); + break; + case BPF_LINK_TYPE_NETNS: + jsonw_uint_field(json_wtr, "netns_ino", + info->netns.netns_ino); + show_link_attach_type_json(info->netns.attach_type, json_wtr); break; default: break; @@ -153,6 +159,14 @@ static void show_link_header_plain(struct bpf_link_info *info) printf("prog %u ", info->prog_id); } +static void show_link_attach_type_plain(__u32 attach_type) +{ + if (attach_type < ARRAY_SIZE(attach_type_name)) + printf("attach_type %s ", attach_type_name[attach_type]); + else + printf("attach_type %u ", attach_type); +} + static int show_link_close_plain(int fd, struct bpf_link_info *info) { struct bpf_prog_info prog_info; @@ -176,19 +190,15 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info) 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); + show_link_attach_type_plain(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); + show_link_attach_type_plain(info->cgroup.attach_type); + break; + case BPF_LINK_TYPE_NETNS: + printf("\n\tnetns_ino %u ", info->netns.netns_ino); + show_link_attach_type_plain(info->netns.attach_type); break; default: break; @@ -312,7 +322,6 @@ static int do_help(int argc, char **argv) " %1$s %2$s help\n" "\n" " " HELP_SPEC_LINK "\n" - " " HELP_SPEC_PROGRAM "\n" " " HELP_SPEC_OPTIONS "\n" "", bin_name, argv[-2]); diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index 85cbe9a19170..c5fac8068ba1 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -1561,24 +1561,24 @@ static int do_help(int argc, char **argv) } fprintf(stderr, - "Usage: %s %s { show | list } [MAP]\n" - " %s %s create FILE type TYPE key KEY_SIZE value VALUE_SIZE \\\n" - " entries MAX_ENTRIES name NAME [flags FLAGS] \\\n" - " [dev NAME]\n" - " %s %s dump MAP\n" - " %s %s update MAP [key DATA] [value VALUE] [UPDATE_FLAGS]\n" - " %s %s lookup MAP [key DATA]\n" - " %s %s getnext MAP [key DATA]\n" - " %s %s delete MAP key DATA\n" - " %s %s pin MAP FILE\n" - " %s %s event_pipe MAP [cpu N index M]\n" - " %s %s peek MAP\n" - " %s %s push MAP value VALUE\n" - " %s %s pop MAP\n" - " %s %s enqueue MAP value VALUE\n" - " %s %s dequeue MAP\n" - " %s %s freeze MAP\n" - " %s %s help\n" + "Usage: %1$s %2$s { show | list } [MAP]\n" + " %1$s %2$s create FILE type TYPE key KEY_SIZE value VALUE_SIZE \\\n" + " entries MAX_ENTRIES name NAME [flags FLAGS] \\\n" + " [dev NAME]\n" + " %1$s %2$s dump MAP\n" + " %1$s %2$s update MAP [key DATA] [value VALUE] [UPDATE_FLAGS]\n" + " %1$s %2$s lookup MAP [key DATA]\n" + " %1$s %2$s getnext MAP [key DATA]\n" + " %1$s %2$s delete MAP key DATA\n" + " %1$s %2$s pin MAP FILE\n" + " %1$s %2$s event_pipe MAP [cpu N index M]\n" + " %1$s %2$s peek MAP\n" + " %1$s %2$s push MAP value VALUE\n" + " %1$s %2$s pop MAP\n" + " %1$s %2$s enqueue MAP value VALUE\n" + " %1$s %2$s dequeue MAP\n" + " %1$s %2$s freeze MAP\n" + " %1$s %2$s help\n" "\n" " " HELP_SPEC_MAP "\n" " DATA := { [hex] BYTES }\n" @@ -1593,11 +1593,6 @@ static int do_help(int argc, char **argv) " queue | stack | sk_storage | struct_ops }\n" " " HELP_SPEC_OPTIONS "\n" "", - bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], - bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], - bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], - bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], - bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2]); return 0; diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c index c5e3895b7c8b..56c3a2bae3ef 100644 --- a/tools/bpf/bpftool/net.c +++ b/tools/bpf/bpftool/net.c @@ -458,10 +458,10 @@ static int do_help(int argc, char **argv) } fprintf(stderr, - "Usage: %s %s { show | list } [dev <devname>]\n" - " %s %s attach ATTACH_TYPE PROG dev <devname> [ overwrite ]\n" - " %s %s detach ATTACH_TYPE dev <devname>\n" - " %s %s help\n" + "Usage: %1$s %2$s { show | list } [dev <devname>]\n" + " %1$s %2$s attach ATTACH_TYPE PROG dev <devname> [ overwrite ]\n" + " %1$s %2$s detach ATTACH_TYPE dev <devname>\n" + " %1$s %2$s help\n" "\n" " " HELP_SPEC_PROGRAM "\n" " ATTACH_TYPE := { xdp | xdpgeneric | xdpdrv | xdpoffload }\n" @@ -470,8 +470,8 @@ static int do_help(int argc, char **argv) " For progs attached to cgroups, use \"bpftool cgroup\"\n" " to dump program attachments. For program types\n" " sk_{filter,skb,msg,reuseport} and lwt/seg6, please\n" - " consult iproute2.\n", - bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], + " consult iproute2.\n" + "", bin_name, argv[-2]); return 0; diff --git a/tools/bpf/bpftool/perf.c b/tools/bpf/bpftool/perf.c index 3341aa14acda..ad23934819c7 100644 --- a/tools/bpf/bpftool/perf.c +++ b/tools/bpf/bpftool/perf.c @@ -231,7 +231,7 @@ static int do_show(int argc, char **argv) static int do_help(int argc, char **argv) { fprintf(stderr, - "Usage: %s %s { show | list | help }\n" + "Usage: %1$s %2$s { show | list | help }\n" "", bin_name, argv[-2]); diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 245f941fdbcf..a5eff83496f2 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -1984,24 +1984,24 @@ static int do_help(int argc, char **argv) } fprintf(stderr, - "Usage: %s %s { show | list } [PROG]\n" - " %s %s dump xlated PROG [{ file FILE | opcodes | visual | linum }]\n" - " %s %s dump jited PROG [{ file FILE | opcodes | linum }]\n" - " %s %s pin PROG FILE\n" - " %s %s { load | loadall } OBJ PATH \\\n" + "Usage: %1$s %2$s { show | list } [PROG]\n" + " %1$s %2$s dump xlated PROG [{ file FILE | opcodes | visual | linum }]\n" + " %1$s %2$s dump jited PROG [{ file FILE | opcodes | linum }]\n" + " %1$s %2$s pin PROG FILE\n" + " %1$s %2$s { load | loadall } OBJ PATH \\\n" " [type TYPE] [dev NAME] \\\n" " [map { idx IDX | name NAME } MAP]\\\n" " [pinmaps MAP_DIR]\n" - " %s %s attach PROG ATTACH_TYPE [MAP]\n" - " %s %s detach PROG ATTACH_TYPE [MAP]\n" - " %s %s run PROG \\\n" + " %1$s %2$s attach PROG ATTACH_TYPE [MAP]\n" + " %1$s %2$s detach PROG ATTACH_TYPE [MAP]\n" + " %1$s %2$s run PROG \\\n" " data_in FILE \\\n" " [data_out FILE [data_size_out L]] \\\n" " [ctx_in FILE [ctx_out FILE [ctx_size_out M]]] \\\n" " [repeat N]\n" - " %s %s profile PROG [duration DURATION] METRICs\n" - " %s %s tracelog\n" - " %s %s help\n" + " %1$s %2$s profile PROG [duration DURATION] METRICs\n" + " %1$s %2$s tracelog\n" + " %1$s %2$s help\n" "\n" " " HELP_SPEC_MAP "\n" " " HELP_SPEC_PROGRAM "\n" @@ -2022,10 +2022,7 @@ static int do_help(int argc, char **argv) " METRIC := { cycles | instructions | l1d_loads | llc_misses }\n" " " HELP_SPEC_OPTIONS "\n" "", - bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], - bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], - bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], - bin_name, argv[-2], bin_name, argv[-2]); + bin_name, argv[-2]); return 0; } diff --git a/tools/bpf/bpftool/struct_ops.c b/tools/bpf/bpftool/struct_ops.c index e17738479edc..b58b91f62ffb 100644 --- a/tools/bpf/bpftool/struct_ops.c +++ b/tools/bpf/bpftool/struct_ops.c @@ -566,16 +566,15 @@ static int do_help(int argc, char **argv) } fprintf(stderr, - "Usage: %s %s { show | list } [STRUCT_OPS_MAP]\n" - " %s %s dump [STRUCT_OPS_MAP]\n" - " %s %s register OBJ\n" - " %s %s unregister STRUCT_OPS_MAP\n" - " %s %s help\n" + "Usage: %1$s %2$s { show | list } [STRUCT_OPS_MAP]\n" + " %1$s %2$s dump [STRUCT_OPS_MAP]\n" + " %1$s %2$s register OBJ\n" + " %1$s %2$s unregister STRUCT_OPS_MAP\n" + " %1$s %2$s help\n" "\n" " OPTIONS := { {-j|--json} [{-p|--pretty}] }\n" - " STRUCT_OPS_MAP := [ id STRUCT_OPS_MAP_ID | name STRUCT_OPS_MAP_NAME ]\n", - bin_name, argv[-2], bin_name, argv[-2], - bin_name, argv[-2], bin_name, argv[-2], + " STRUCT_OPS_MAP := [ id STRUCT_OPS_MAP_ID | name STRUCT_OPS_MAP_NAME ]\n" + "", bin_name, argv[-2]); return 0; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 97e1fd19ff58..b9ed9f14f2a2 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -147,6 +147,7 @@ enum bpf_map_type { BPF_MAP_TYPE_SK_STORAGE, BPF_MAP_TYPE_DEVMAP_HASH, BPF_MAP_TYPE_STRUCT_OPS, + BPF_MAP_TYPE_RINGBUF, }; /* Note that tracing related programs such as @@ -224,6 +225,7 @@ enum bpf_attach_type { BPF_CGROUP_INET6_GETPEERNAME, BPF_CGROUP_INET4_GETSOCKNAME, BPF_CGROUP_INET6_GETSOCKNAME, + BPF_XDP_DEVMAP, __MAX_BPF_ATTACH_TYPE }; @@ -235,6 +237,7 @@ enum bpf_link_type { BPF_LINK_TYPE_TRACING = 2, BPF_LINK_TYPE_CGROUP = 3, BPF_LINK_TYPE_ITER = 4, + BPF_LINK_TYPE_NETNS = 5, MAX_BPF_LINK_TYPE, }; @@ -3157,6 +3160,59 @@ union bpf_attr { * **bpf_sk_cgroup_id**\ (). * Return * The id is returned or 0 in case the id could not be retrieved. + * + * void *bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags) + * Description + * Copy *size* bytes from *data* into a ring buffer *ringbuf*. + * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of + * new data availability is sent. + * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of + * new data availability is sent unconditionally. + * Return + * 0, on success; + * < 0, on error. + * + * void *bpf_ringbuf_reserve(void *ringbuf, u64 size, u64 flags) + * Description + * Reserve *size* bytes of payload in a ring buffer *ringbuf*. + * Return + * Valid pointer with *size* bytes of memory available; NULL, + * otherwise. + * + * void bpf_ringbuf_submit(void *data, u64 flags) + * Description + * Submit reserved ring buffer sample, pointed to by *data*. + * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of + * new data availability is sent. + * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of + * new data availability is sent unconditionally. + * Return + * Nothing. Always succeeds. + * + * void bpf_ringbuf_discard(void *data, u64 flags) + * Description + * Discard reserved ring buffer sample, pointed to by *data*. + * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of + * new data availability is sent. + * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of + * new data availability is sent unconditionally. + * Return + * Nothing. Always succeeds. + * + * u64 bpf_ringbuf_query(void *ringbuf, u64 flags) + * Description + * Query various characteristics of provided ring buffer. What + * exactly is queries is determined by *flags*: + * - BPF_RB_AVAIL_DATA - amount of data not yet consumed; + * - BPF_RB_RING_SIZE - the size of ring buffer; + * - BPF_RB_CONS_POS - consumer position (can wrap around); + * - BPF_RB_PROD_POS - producer(s) position (can wrap around); + * Data returned is just a momentary snapshots of actual values + * and could be inaccurate, so this facility should be used to + * power heuristics and for reporting, not to make 100% correct + * calculation. + * Return + * Requested value, or 0, if flags are not recognized. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3288,7 +3344,12 @@ union bpf_attr { FN(seq_printf), \ FN(seq_write), \ FN(sk_cgroup_id), \ - FN(sk_ancestor_cgroup_id), + FN(sk_ancestor_cgroup_id), \ + FN(ringbuf_output), \ + FN(ringbuf_reserve), \ + FN(ringbuf_submit), \ + FN(ringbuf_discard), \ + FN(ringbuf_query), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -3398,6 +3459,29 @@ enum { BPF_F_GET_BRANCH_RECORDS_SIZE = (1ULL << 0), }; +/* BPF_FUNC_bpf_ringbuf_commit, BPF_FUNC_bpf_ringbuf_discard, and + * BPF_FUNC_bpf_ringbuf_output flags. + */ +enum { + BPF_RB_NO_WAKEUP = (1ULL << 0), + BPF_RB_FORCE_WAKEUP = (1ULL << 1), +}; + +/* BPF_FUNC_bpf_ringbuf_query flags */ +enum { + BPF_RB_AVAIL_DATA = 0, + BPF_RB_RING_SIZE = 1, + BPF_RB_CONS_POS = 2, + BPF_RB_PROD_POS = 3, +}; + +/* BPF ring buffer constants */ +enum { + BPF_RINGBUF_BUSY_BIT = (1U << 31), + BPF_RINGBUF_DISCARD_BIT = (1U << 30), + BPF_RINGBUF_HDR_SZ = 8, +}; + /* Mode for BPF_FUNC_skb_adjust_room helper. */ enum bpf_adj_room_mode { BPF_ADJ_ROOM_NET, @@ -3530,6 +3614,7 @@ struct bpf_sock { __u32 dst_ip4; __u32 dst_ip6[4]; __u32 state; + __s32 rx_queue_mapping; }; struct bpf_tcp_sock { @@ -3623,6 +3708,8 @@ struct xdp_md { /* Below access go through struct xdp_rxq_info */ __u32 ingress_ifindex; /* rxq->dev->ifindex */ __u32 rx_queue_index; /* rxq->queue_index */ + + __u32 egress_ifindex; /* txq->dev->ifindex */ }; enum sk_action { @@ -3645,6 +3732,8 @@ struct sk_msg_md { __u32 remote_port; /* Stored in network byte order */ __u32 local_port; /* stored in host byte order */ __u32 size; /* Total size of sk_msg */ + + __bpf_md_ptr(struct bpf_sock *, sk); /* current socket */ }; struct sk_reuseport_md { @@ -3751,6 +3840,10 @@ struct bpf_link_info { __u64 cgroup_id; __u32 attach_type; } cgroup; + struct { + __u32 netns_ino; + __u32 attach_type; + } netns; }; } __attribute__((aligned(8))); diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build index e3962cfbc9a6..190366d05588 100644 --- a/tools/lib/bpf/Build +++ b/tools/lib/bpf/Build @@ -1,3 +1,3 @@ libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o \ netlink.o bpf_prog_linfo.o libbpf_probes.o xsk.o hashmap.o \ - btf_dump.o + btf_dump.o ringbuf.o diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index aee7f1a83c77..bf8ed134cb8a 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -151,7 +151,7 @@ GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN_SHARED) | \ sed 's/\[.*\]//' | \ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \ sort -u | wc -l) -VERSIONED_SYM_COUNT = $(shell readelf -s --wide $(OUTPUT)libbpf.so | \ +VERSIONED_SYM_COUNT = $(shell readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l) CMD_TARGETS = $(LIB_TARGET) $(PC_FILE) @@ -218,7 +218,7 @@ check_abi: $(OUTPUT)libbpf.so sed 's/\[.*\]//' | \ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'| \ sort -u > $(OUTPUT)libbpf_global_syms.tmp; \ - readelf -s --wide $(OUTPUT)libbpf.so | \ + readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | \ sort -u > $(OUTPUT)libbpf_versioned_syms.tmp; \ diff -u $(OUTPUT)libbpf_global_syms.tmp \ @@ -264,7 +264,7 @@ install_pkgconfig: $(PC_FILE) $(call QUIET_INSTALL, $(PC_FILE)) \ $(call do_install,$(PC_FILE),$(libdir_SQ)/pkgconfig,644) -install: install_lib install_pkgconfig +install: install_lib install_pkgconfig install_headers ### Cleaning rules diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index fa04cbe547ed..7f01be2b88b8 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -6657,6 +6657,8 @@ static const struct bpf_sec_def section_defs[] = { .expected_attach_type = BPF_TRACE_ITER, .is_attach_btf = true, .attach_fn = attach_iter), + BPF_EAPROG_SEC("xdp_devmap", BPF_PROG_TYPE_XDP, + BPF_XDP_DEVMAP), BPF_PROG_SEC("xdp", BPF_PROG_TYPE_XDP), BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT), BPF_PROG_SEC("lwt_in", BPF_PROG_TYPE_LWT_IN), @@ -7894,8 +7896,9 @@ static struct bpf_link *attach_iter(const struct bpf_sec_def *sec, return bpf_program__attach_iter(prog, NULL); } -struct bpf_link * -bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd) +static struct bpf_link * +bpf_program__attach_fd(struct bpf_program *prog, int target_fd, + const char *target_name) { enum bpf_attach_type attach_type; char errmsg[STRERR_BUFSIZE]; @@ -7915,12 +7918,12 @@ bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd) link->detach = &bpf_link__detach_fd; attach_type = bpf_program__get_expected_attach_type(prog); - link_fd = bpf_link_create(prog_fd, cgroup_fd, attach_type, NULL); + link_fd = bpf_link_create(prog_fd, target_fd, attach_type, NULL); if (link_fd < 0) { link_fd = -errno; free(link); - pr_warn("program '%s': failed to attach to cgroup: %s\n", - bpf_program__title(prog, false), + pr_warn("program '%s': failed to attach to %s: %s\n", + bpf_program__title(prog, false), target_name, libbpf_strerror_r(link_fd, errmsg, sizeof(errmsg))); return ERR_PTR(link_fd); } @@ -7929,6 +7932,18 @@ bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd) } struct bpf_link * +bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd) +{ + return bpf_program__attach_fd(prog, cgroup_fd, "cgroup"); +} + +struct bpf_link * +bpf_program__attach_netns(struct bpf_program *prog, int netns_fd) +{ + return bpf_program__attach_fd(prog, netns_fd, "netns"); +} + +struct bpf_link * bpf_program__attach_iter(struct bpf_program *prog, const struct bpf_iter_attach_opts *opts) { @@ -8137,9 +8152,12 @@ void perf_buffer__free(struct perf_buffer *pb) if (!pb) return; if (pb->cpu_bufs) { - for (i = 0; i < pb->cpu_cnt && pb->cpu_bufs[i]; i++) { + for (i = 0; i < pb->cpu_cnt; i++) { struct perf_cpu_buf *cpu_buf = pb->cpu_bufs[i]; + if (!cpu_buf) + continue; + bpf_map_delete_elem(pb->map_fd, &cpu_buf->map_key); perf_buffer__free_cpu_buf(pb, cpu_buf); } @@ -8456,6 +8474,25 @@ int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms) return cnt < 0 ? -errno : cnt; } +int perf_buffer__consume(struct perf_buffer *pb) +{ + int i, err; + + for (i = 0; i < pb->cpu_cnt; i++) { + struct perf_cpu_buf *cpu_buf = pb->cpu_bufs[i]; + + if (!cpu_buf) + continue; + + err = perf_buffer__process_records(pb, cpu_buf); + if (err) { + pr_warn("error while processing records: %d\n", err); + return err; + } + } + return 0; +} + struct bpf_prog_info_array_desc { int array_offset; /* e.g. offset of jited_prog_insns */ int count_offset; /* e.g. offset of jited_prog_len */ diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 8ea69558f0a8..334437af3014 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -253,6 +253,8 @@ LIBBPF_API struct bpf_link * bpf_program__attach_lsm(struct bpf_program *prog); LIBBPF_API struct bpf_link * bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd); +LIBBPF_API struct bpf_link * +bpf_program__attach_netns(struct bpf_program *prog, int netns_fd); struct bpf_map; @@ -478,6 +480,27 @@ LIBBPF_API int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags); LIBBPF_API int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, size_t info_size, __u32 flags); +/* Ring buffer APIs */ +struct ring_buffer; + +typedef int (*ring_buffer_sample_fn)(void *ctx, void *data, size_t size); + +struct ring_buffer_opts { + size_t sz; /* size of this struct, for forward/backward compatiblity */ +}; + +#define ring_buffer_opts__last_field sz + +LIBBPF_API struct ring_buffer * +ring_buffer__new(int map_fd, ring_buffer_sample_fn sample_cb, void *ctx, + const struct ring_buffer_opts *opts); +LIBBPF_API void ring_buffer__free(struct ring_buffer *rb); +LIBBPF_API int ring_buffer__add(struct ring_buffer *rb, int map_fd, + ring_buffer_sample_fn sample_cb, void *ctx); +LIBBPF_API int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms); +LIBBPF_API int ring_buffer__consume(struct ring_buffer *rb); + +/* Perf buffer APIs */ struct perf_buffer; typedef void (*perf_buffer_sample_fn)(void *ctx, int cpu, @@ -533,6 +556,7 @@ perf_buffer__new_raw(int map_fd, size_t page_cnt, LIBBPF_API void perf_buffer__free(struct perf_buffer *pb); LIBBPF_API int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms); +LIBBPF_API int perf_buffer__consume(struct perf_buffer *pb); typedef enum bpf_perf_event_ret (*bpf_perf_event_print_t)(struct perf_event_header *hdr, diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 0133d469d30b..f732c77b7ed0 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -262,4 +262,11 @@ LIBBPF_0.0.9 { bpf_link_get_fd_by_id; bpf_link_get_next_id; bpf_program__attach_iter; + bpf_program__attach_netns; + perf_buffer__consume; + ring_buffer__add; + ring_buffer__consume; + ring_buffer__free; + ring_buffer__new; + ring_buffer__poll; } LIBBPF_0.0.8; diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index 2c92059c0c90..10cd8d1891f5 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -238,6 +238,11 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) if (btf_fd < 0) return false; break; + case BPF_MAP_TYPE_RINGBUF: + key_size = 0; + value_size = 0; + max_entries = 4096; + break; case BPF_MAP_TYPE_UNSPEC: case BPF_MAP_TYPE_HASH: case BPF_MAP_TYPE_ARRAY: diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c new file mode 100644 index 000000000000..4fc6c6cbb4eb --- /dev/null +++ b/tools/lib/bpf/ringbuf.c @@ -0,0 +1,288 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* + * Ring buffer operations. + * + * Copyright (C) 2020 Facebook, Inc. + */ +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif +#include <stdlib.h> +#include <stdio.h> +#include <errno.h> +#include <unistd.h> +#include <linux/err.h> +#include <linux/bpf.h> +#include <asm/barrier.h> +#include <sys/mman.h> +#include <sys/epoll.h> +#include <tools/libc_compat.h> + +#include "libbpf.h" +#include "libbpf_internal.h" +#include "bpf.h" + +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + +struct ring { + ring_buffer_sample_fn sample_cb; + void *ctx; + void *data; + unsigned long *consumer_pos; + unsigned long *producer_pos; + unsigned long mask; + int map_fd; +}; + +struct ring_buffer { + struct epoll_event *events; + struct ring *rings; + size_t page_size; + int epoll_fd; + int ring_cnt; +}; + +static void ringbuf_unmap_ring(struct ring_buffer *rb, struct ring *r) +{ + if (r->consumer_pos) { + munmap(r->consumer_pos, rb->page_size); + r->consumer_pos = NULL; + } + if (r->producer_pos) { + munmap(r->producer_pos, rb->page_size + 2 * (r->mask + 1)); + r->producer_pos = NULL; + } +} + +/* Add extra RINGBUF maps to this ring buffer manager */ +int ring_buffer__add(struct ring_buffer *rb, int map_fd, + ring_buffer_sample_fn sample_cb, void *ctx) +{ + struct bpf_map_info info; + __u32 len = sizeof(info); + struct epoll_event *e; + struct ring *r; + void *tmp; + int err; + + memset(&info, 0, sizeof(info)); + + err = bpf_obj_get_info_by_fd(map_fd, &info, &len); + if (err) { + err = -errno; + pr_warn("ringbuf: failed to get map info for fd=%d: %d\n", + map_fd, err); + return err; + } + + if (info.type != BPF_MAP_TYPE_RINGBUF) { + pr_warn("ringbuf: map fd=%d is not BPF_MAP_TYPE_RINGBUF\n", + map_fd); + return -EINVAL; + } + + tmp = reallocarray(rb->rings, rb->ring_cnt + 1, sizeof(*rb->rings)); + if (!tmp) + return -ENOMEM; + rb->rings = tmp; + + tmp = reallocarray(rb->events, rb->ring_cnt + 1, sizeof(*rb->events)); + if (!tmp) + return -ENOMEM; + rb->events = tmp; + + r = &rb->rings[rb->ring_cnt]; + memset(r, 0, sizeof(*r)); + + r->map_fd = map_fd; + r->sample_cb = sample_cb; + r->ctx = ctx; + r->mask = info.max_entries - 1; + + /* Map writable consumer page */ + tmp = mmap(NULL, rb->page_size, PROT_READ | PROT_WRITE, MAP_SHARED, + map_fd, 0); + if (tmp == MAP_FAILED) { + err = -errno; + pr_warn("ringbuf: failed to mmap consumer page for map fd=%d: %d\n", + map_fd, err); + return err; + } + r->consumer_pos = tmp; + + /* Map read-only producer page and data pages. We map twice as big + * data size to allow simple reading of samples that wrap around the + * end of a ring buffer. See kernel implementation for details. + * */ + tmp = mmap(NULL, rb->page_size + 2 * info.max_entries, PROT_READ, + MAP_SHARED, map_fd, rb->page_size); + if (tmp == MAP_FAILED) { + err = -errno; + ringbuf_unmap_ring(rb, r); + pr_warn("ringbuf: failed to mmap data pages for map fd=%d: %d\n", + map_fd, err); + return err; + } + r->producer_pos = tmp; + r->data = tmp + rb->page_size; + + e = &rb->events[rb->ring_cnt]; + memset(e, 0, sizeof(*e)); + + e->events = EPOLLIN; + e->data.fd = rb->ring_cnt; + if (epoll_ctl(rb->epoll_fd, EPOLL_CTL_ADD, map_fd, e) < 0) { + err = -errno; + ringbuf_unmap_ring(rb, r); + pr_warn("ringbuf: failed to epoll add map fd=%d: %d\n", + map_fd, err); + return err; + } + + rb->ring_cnt++; + return 0; +} + +void ring_buffer__free(struct ring_buffer *rb) +{ + int i; + + if (!rb) + return; + + for (i = 0; i < rb->ring_cnt; ++i) + ringbuf_unmap_ring(rb, &rb->rings[i]); + if (rb->epoll_fd >= 0) + close(rb->epoll_fd); + + free(rb->events); + free(rb->rings); + free(rb); +} + +struct ring_buffer * +ring_buffer__new(int map_fd, ring_buffer_sample_fn sample_cb, void *ctx, + const struct ring_buffer_opts *opts) +{ + struct ring_buffer *rb; + int err; + + if (!OPTS_VALID(opts, ring_buffer_opts)) + return NULL; + + rb = calloc(1, sizeof(*rb)); + if (!rb) + return NULL; + + rb->page_size = getpagesize(); + + rb->epoll_fd = epoll_create1(EPOLL_CLOEXEC); + if (rb->epoll_fd < 0) { + err = -errno; + pr_warn("ringbuf: failed to create epoll instance: %d\n", err); + goto err_out; + } + + err = ring_buffer__add(rb, map_fd, sample_cb, ctx); + if (err) + goto err_out; + + return rb; + +err_out: + ring_buffer__free(rb); + return NULL; +} + +static inline int roundup_len(__u32 len) +{ + /* clear out top 2 bits (discard and busy, if set) */ + len <<= 2; + len >>= 2; + /* add length prefix */ + len += BPF_RINGBUF_HDR_SZ; + /* round up to 8 byte alignment */ + return (len + 7) / 8 * 8; +} + +static int ringbuf_process_ring(struct ring* r) +{ + int *len_ptr, len, err, cnt = 0; + unsigned long cons_pos, prod_pos; + bool got_new_data; + void *sample; + + cons_pos = smp_load_acquire(r->consumer_pos); + do { + got_new_data = false; + prod_pos = smp_load_acquire(r->producer_pos); + while (cons_pos < prod_pos) { + len_ptr = r->data + (cons_pos & r->mask); + len = smp_load_acquire(len_ptr); + + /* sample not committed yet, bail out for now */ + if (len & BPF_RINGBUF_BUSY_BIT) + goto done; + + got_new_data = true; + cons_pos += roundup_len(len); + + if ((len & BPF_RINGBUF_DISCARD_BIT) == 0) { + sample = (void *)len_ptr + BPF_RINGBUF_HDR_SZ; + err = r->sample_cb(r->ctx, sample, len); + if (err) { + /* update consumer pos and bail out */ + smp_store_release(r->consumer_pos, + cons_pos); + return err; + } + cnt++; + } + + smp_store_release(r->consumer_pos, cons_pos); + } + } while (got_new_data); +done: + return cnt; +} + +/* Consume available ring buffer(s) data without event polling. + * Returns number of records consumed across all registered ring buffers, or + * negative number if any of the callbacks return error. + */ +int ring_buffer__consume(struct ring_buffer *rb) +{ + int i, err, res = 0; + + for (i = 0; i < rb->ring_cnt; i++) { + struct ring *ring = &rb->rings[i]; + + err = ringbuf_process_ring(ring); + if (err < 0) + return err; + res += err; + } + return res; +} + +/* Poll for available data and consume records, if any are available. + * Returns number of records consumed, or negative number, if any of the + * registered callbacks returned error. + */ +int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms) +{ + int i, cnt, err, res = 0; + + cnt = epoll_wait(rb->epoll_fd, rb->events, rb->ring_cnt, timeout_ms); + for (i = 0; i < cnt; i++) { + __u32 ring_id = rb->events[i].data.fd; + struct ring *ring = &rb->rings[ring_id]; + + err = ringbuf_process_ring(ring); + if (err < 0) + return err; + res += cnt; + } + return cnt < 0 ? -errno : res; +} diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index e716e931d0c9..3ce548eff8a8 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -413,12 +413,15 @@ $(OUTPUT)/bench_%.o: benchs/bench_%.c bench.h $(CC) $(CFLAGS) -c $(filter %.c,$^) $(LDLIBS) -o $@ $(OUTPUT)/bench_rename.o: $(OUTPUT)/test_overhead.skel.h $(OUTPUT)/bench_trigger.o: $(OUTPUT)/trigger_bench.skel.h +$(OUTPUT)/bench_ringbufs.o: $(OUTPUT)/ringbuf_bench.skel.h \ + $(OUTPUT)/perfbuf_bench.skel.h $(OUTPUT)/bench.o: bench.h testing_helpers.h $(OUTPUT)/bench: LDLIBS += -lm $(OUTPUT)/bench: $(OUTPUT)/bench.o $(OUTPUT)/testing_helpers.o \ $(OUTPUT)/bench_count.o \ $(OUTPUT)/bench_rename.o \ - $(OUTPUT)/bench_trigger.o + $(OUTPUT)/bench_trigger.o \ + $(OUTPUT)/bench_ringbufs.o $(call msg,BINARY,,$@) $(CC) $(LDFLAGS) -o $@ $(filter %.a %.o,$^) $(LDLIBS) diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c index 14390689ef90..944ad4721c83 100644 --- a/tools/testing/selftests/bpf/bench.c +++ b/tools/testing/selftests/bpf/bench.c @@ -130,6 +130,13 @@ static const struct argp_option opts[] = { {}, }; +extern struct argp bench_ringbufs_argp; + +static const struct argp_child bench_parsers[] = { + { &bench_ringbufs_argp, 0, "Ring buffers benchmark", 0 }, + {}, +}; + static error_t parse_arg(int key, char *arg, struct argp_state *state) { static int pos_args; @@ -208,6 +215,7 @@ static void parse_cmdline_args(int argc, char **argv) .options = opts, .parser = parse_arg, .doc = argp_program_doc, + .children = bench_parsers, }; if (argp_parse(&argp, argc, argv, 0, NULL, NULL)) exit(1); @@ -310,6 +318,10 @@ extern const struct bench bench_trig_rawtp; extern const struct bench bench_trig_kprobe; extern const struct bench bench_trig_fentry; extern const struct bench bench_trig_fmodret; +extern const struct bench bench_rb_libbpf; +extern const struct bench bench_rb_custom; +extern const struct bench bench_pb_libbpf; +extern const struct bench bench_pb_custom; static const struct bench *benchs[] = { &bench_count_global, @@ -327,6 +339,10 @@ static const struct bench *benchs[] = { &bench_trig_kprobe, &bench_trig_fentry, &bench_trig_fmodret, + &bench_rb_libbpf, + &bench_rb_custom, + &bench_pb_libbpf, + &bench_pb_custom, }; static void setup_benchmark() diff --git a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c new file mode 100644 index 000000000000..da87c7f31891 --- /dev/null +++ b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c @@ -0,0 +1,566 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include <asm/barrier.h> +#include <linux/perf_event.h> +#include <linux/ring_buffer.h> +#include <sys/epoll.h> +#include <sys/mman.h> +#include <argp.h> +#include <stdlib.h> +#include "bench.h" +#include "ringbuf_bench.skel.h" +#include "perfbuf_bench.skel.h" + +static struct { + bool back2back; + int batch_cnt; + bool sampled; + int sample_rate; + int ringbuf_sz; /* per-ringbuf, in bytes */ + bool ringbuf_use_output; /* use slower output API */ + int perfbuf_sz; /* per-CPU size, in pages */ +} args = { + .back2back = false, + .batch_cnt = 500, + .sampled = false, + .sample_rate = 500, + .ringbuf_sz = 512 * 1024, + .ringbuf_use_output = false, + .perfbuf_sz = 128, +}; + +enum { + ARG_RB_BACK2BACK = 2000, + ARG_RB_USE_OUTPUT = 2001, + ARG_RB_BATCH_CNT = 2002, + ARG_RB_SAMPLED = 2003, + ARG_RB_SAMPLE_RATE = 2004, +}; + +static const struct argp_option opts[] = { + { "rb-b2b", ARG_RB_BACK2BACK, NULL, 0, "Back-to-back mode"}, + { "rb-use-output", ARG_RB_USE_OUTPUT, NULL, 0, "Use bpf_ringbuf_output() instead of bpf_ringbuf_reserve()"}, + { "rb-batch-cnt", ARG_RB_BATCH_CNT, "CNT", 0, "Set BPF-side record batch count"}, + { "rb-sampled", ARG_RB_SAMPLED, NULL, 0, "Notification sampling"}, + { "rb-sample-rate", ARG_RB_SAMPLE_RATE, "RATE", 0, "Notification sample rate"}, + {}, +}; + +static error_t parse_arg(int key, char *arg, struct argp_state *state) +{ + switch (key) { + case ARG_RB_BACK2BACK: + args.back2back = true; + break; + case ARG_RB_USE_OUTPUT: + args.ringbuf_use_output = true; + break; + case ARG_RB_BATCH_CNT: + args.batch_cnt = strtol(arg, NULL, 10); + if (args.batch_cnt < 0) { + fprintf(stderr, "Invalid batch count."); + argp_usage(state); + } + break; + case ARG_RB_SAMPLED: + args.sampled = true; + break; + case ARG_RB_SAMPLE_RATE: + args.sample_rate = strtol(arg, NULL, 10); + if (args.sample_rate < 0) { + fprintf(stderr, "Invalid perfbuf sample rate."); + argp_usage(state); + } + break; + default: + return ARGP_ERR_UNKNOWN; + } + return 0; +} + +/* exported into benchmark runner */ +const struct argp bench_ringbufs_argp = { + .options = opts, + .parser = parse_arg, +}; + +/* RINGBUF-LIBBPF benchmark */ + +static struct counter buf_hits; + +static inline void bufs_trigger_batch() +{ + (void)syscall(__NR_getpgid); +} + +static void bufs_validate() +{ + if (env.consumer_cnt != 1) { + fprintf(stderr, "rb-libbpf benchmark doesn't support multi-consumer!\n"); + exit(1); + } + + if (args.back2back && env.producer_cnt > 1) { + fprintf(stderr, "back-to-back mode makes sense only for single-producer case!\n"); + exit(1); + } +} + +static void *bufs_sample_producer(void *input) +{ + if (args.back2back) { + /* initial batch to get everything started */ + bufs_trigger_batch(); + return NULL; + } + + while (true) + bufs_trigger_batch(); + return NULL; +} + +static struct ringbuf_libbpf_ctx { + struct ringbuf_bench *skel; + struct ring_buffer *ringbuf; +} ringbuf_libbpf_ctx; + +static void ringbuf_libbpf_measure(struct bench_res *res) +{ + struct ringbuf_libbpf_ctx *ctx = &ringbuf_libbpf_ctx; + + res->hits = atomic_swap(&buf_hits.value, 0); + res->drops = atomic_swap(&ctx->skel->bss->dropped, 0); +} + +static struct ringbuf_bench *ringbuf_setup_skeleton() +{ + struct ringbuf_bench *skel; + + setup_libbpf(); + + skel = ringbuf_bench__open(); + if (!skel) { + fprintf(stderr, "failed to open skeleton\n"); + exit(1); + } + + skel->rodata->batch_cnt = args.batch_cnt; + skel->rodata->use_output = args.ringbuf_use_output ? 1 : 0; + + if (args.sampled) + /* record data + header take 16 bytes */ + skel->rodata->wakeup_data_size = args.sample_rate * 16; + + bpf_map__resize(skel->maps.ringbuf, args.ringbuf_sz); + + if (ringbuf_bench__load(skel)) { + fprintf(stderr, "failed to load skeleton\n"); + exit(1); + } + + return skel; +} + +static int buf_process_sample(void *ctx, void *data, size_t len) +{ + atomic_inc(&buf_hits.value); + return 0; +} + +static void ringbuf_libbpf_setup() +{ + struct ringbuf_libbpf_ctx *ctx = &ringbuf_libbpf_ctx; + struct bpf_link *link; + + ctx->skel = ringbuf_setup_skeleton(); + ctx->ringbuf = ring_buffer__new(bpf_map__fd(ctx->skel->maps.ringbuf), + buf_process_sample, NULL, NULL); + if (!ctx->ringbuf) { + fprintf(stderr, "failed to create ringbuf\n"); + exit(1); + } + + link = bpf_program__attach(ctx->skel->progs.bench_ringbuf); + if (IS_ERR(link)) { + fprintf(stderr, "failed to attach program!\n"); + exit(1); + } +} + +static void *ringbuf_libbpf_consumer(void *input) +{ + struct ringbuf_libbpf_ctx *ctx = &ringbuf_libbpf_ctx; + + while (ring_buffer__poll(ctx->ringbuf, -1) >= 0) { + if (args.back2back) + bufs_trigger_batch(); + } + fprintf(stderr, "ringbuf polling failed!\n"); + return NULL; +} + +/* RINGBUF-CUSTOM benchmark */ +struct ringbuf_custom { + __u64 *consumer_pos; + __u64 *producer_pos; + __u64 mask; + void *data; + int map_fd; +}; + +static struct ringbuf_custom_ctx { + struct ringbuf_bench *skel; + struct ringbuf_custom ringbuf; + int epoll_fd; + struct epoll_event event; +} ringbuf_custom_ctx; + +static void ringbuf_custom_measure(struct bench_res *res) +{ + struct ringbuf_custom_ctx *ctx = &ringbuf_custom_ctx; + + res->hits = atomic_swap(&buf_hits.value, 0); + res->drops = atomic_swap(&ctx->skel->bss->dropped, 0); +} + +static void ringbuf_custom_setup() +{ + struct ringbuf_custom_ctx *ctx = &ringbuf_custom_ctx; + const size_t page_size = getpagesize(); + struct bpf_link *link; + struct ringbuf_custom *r; + void *tmp; + int err; + + ctx->skel = ringbuf_setup_skeleton(); + + ctx->epoll_fd = epoll_create1(EPOLL_CLOEXEC); + if (ctx->epoll_fd < 0) { + fprintf(stderr, "failed to create epoll fd: %d\n", -errno); + exit(1); + } + + r = &ctx->ringbuf; + r->map_fd = bpf_map__fd(ctx->skel->maps.ringbuf); + r->mask = args.ringbuf_sz - 1; + + /* Map writable consumer page */ + tmp = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED, + r->map_fd, 0); + if (tmp == MAP_FAILED) { + fprintf(stderr, "failed to mmap consumer page: %d\n", -errno); + exit(1); + } + r->consumer_pos = tmp; + + /* Map read-only producer page and data pages. */ + tmp = mmap(NULL, page_size + 2 * args.ringbuf_sz, PROT_READ, MAP_SHARED, + r->map_fd, page_size); + if (tmp == MAP_FAILED) { + fprintf(stderr, "failed to mmap data pages: %d\n", -errno); + exit(1); + } + r->producer_pos = tmp; + r->data = tmp + page_size; + + ctx->event.events = EPOLLIN; + err = epoll_ctl(ctx->epoll_fd, EPOLL_CTL_ADD, r->map_fd, &ctx->event); + if (err < 0) { + fprintf(stderr, "failed to epoll add ringbuf: %d\n", -errno); + exit(1); + } + + link = bpf_program__attach(ctx->skel->progs.bench_ringbuf); + if (IS_ERR(link)) { + fprintf(stderr, "failed to attach program\n"); + exit(1); + } +} + +#define RINGBUF_BUSY_BIT (1 << 31) +#define RINGBUF_DISCARD_BIT (1 << 30) +#define RINGBUF_META_LEN 8 + +static inline int roundup_len(__u32 len) +{ + /* clear out top 2 bits */ + len <<= 2; + len >>= 2; + /* add length prefix */ + len += RINGBUF_META_LEN; + /* round up to 8 byte alignment */ + return (len + 7) / 8 * 8; +} + +static void ringbuf_custom_process_ring(struct ringbuf_custom *r) +{ + unsigned long cons_pos, prod_pos; + int *len_ptr, len; + bool got_new_data; + + cons_pos = smp_load_acquire(r->consumer_pos); + while (true) { + got_new_data = false; + prod_pos = smp_load_acquire(r->producer_pos); + while (cons_pos < prod_pos) { + len_ptr = r->data + (cons_pos & r->mask); + len = smp_load_acquire(len_ptr); + + /* sample not committed yet, bail out for now */ + if (len & RINGBUF_BUSY_BIT) + return; + + got_new_data = true; + cons_pos += roundup_len(len); + + atomic_inc(&buf_hits.value); + } + if (got_new_data) + smp_store_release(r->consumer_pos, cons_pos); + else + break; + }; +} + +static void *ringbuf_custom_consumer(void *input) +{ + struct ringbuf_custom_ctx *ctx = &ringbuf_custom_ctx; + int cnt; + + do { + if (args.back2back) + bufs_trigger_batch(); + cnt = epoll_wait(ctx->epoll_fd, &ctx->event, 1, -1); + if (cnt > 0) + ringbuf_custom_process_ring(&ctx->ringbuf); + } while (cnt >= 0); + fprintf(stderr, "ringbuf polling failed!\n"); + return 0; +} + +/* PERFBUF-LIBBPF benchmark */ +static struct perfbuf_libbpf_ctx { + struct perfbuf_bench *skel; + struct perf_buffer *perfbuf; +} perfbuf_libbpf_ctx; + +static void perfbuf_measure(struct bench_res *res) +{ + struct perfbuf_libbpf_ctx *ctx = &perfbuf_libbpf_ctx; + + res->hits = atomic_swap(&buf_hits.value, 0); + res->drops = atomic_swap(&ctx->skel->bss->dropped, 0); +} + +static struct perfbuf_bench *perfbuf_setup_skeleton() +{ + struct perfbuf_bench *skel; + + setup_libbpf(); + + skel = perfbuf_bench__open(); + if (!skel) { + fprintf(stderr, "failed to open skeleton\n"); + exit(1); + } + + skel->rodata->batch_cnt = args.batch_cnt; + + if (perfbuf_bench__load(skel)) { + fprintf(stderr, "failed to load skeleton\n"); + exit(1); + } + + return skel; +} + +static enum bpf_perf_event_ret +perfbuf_process_sample_raw(void *input_ctx, int cpu, + struct perf_event_header *e) +{ + switch (e->type) { + case PERF_RECORD_SAMPLE: + atomic_inc(&buf_hits.value); + break; + case PERF_RECORD_LOST: + break; + default: + return LIBBPF_PERF_EVENT_ERROR; + } + return LIBBPF_PERF_EVENT_CONT; +} + +static void perfbuf_libbpf_setup() +{ + struct perfbuf_libbpf_ctx *ctx = &perfbuf_libbpf_ctx; + struct perf_event_attr attr; + struct perf_buffer_raw_opts pb_opts = { + .event_cb = perfbuf_process_sample_raw, + .ctx = (void *)(long)0, + .attr = &attr, + }; + struct bpf_link *link; + + ctx->skel = perfbuf_setup_skeleton(); + + memset(&attr, 0, sizeof(attr)); + attr.config = PERF_COUNT_SW_BPF_OUTPUT, + attr.type = PERF_TYPE_SOFTWARE; + attr.sample_type = PERF_SAMPLE_RAW; + /* notify only every Nth sample */ + if (args.sampled) { + attr.sample_period = args.sample_rate; + attr.wakeup_events = args.sample_rate; + } else { + attr.sample_period = 1; + attr.wakeup_events = 1; + } + + if (args.sample_rate > args.batch_cnt) { + fprintf(stderr, "sample rate %d is too high for given batch count %d\n", + args.sample_rate, args.batch_cnt); + exit(1); + } + + ctx->perfbuf = perf_buffer__new_raw(bpf_map__fd(ctx->skel->maps.perfbuf), + args.perfbuf_sz, &pb_opts); + if (!ctx->perfbuf) { + fprintf(stderr, "failed to create perfbuf\n"); + exit(1); + } + + link = bpf_program__attach(ctx->skel->progs.bench_perfbuf); + if (IS_ERR(link)) { + fprintf(stderr, "failed to attach program\n"); + exit(1); + } +} + +static void *perfbuf_libbpf_consumer(void *input) +{ + struct perfbuf_libbpf_ctx *ctx = &perfbuf_libbpf_ctx; + + while (perf_buffer__poll(ctx->perfbuf, -1) >= 0) { + if (args.back2back) + bufs_trigger_batch(); + } + fprintf(stderr, "perfbuf polling failed!\n"); + return NULL; +} + +/* PERFBUF-CUSTOM benchmark */ + +/* copies of internal libbpf definitions */ +struct perf_cpu_buf { + struct perf_buffer *pb; + void *base; /* mmap()'ed memory */ + void *buf; /* for reconstructing segmented data */ + size_t buf_size; + int fd; + int cpu; + int map_key; +}; + +struct perf_buffer { + perf_buffer_event_fn event_cb; + perf_buffer_sample_fn sample_cb; + perf_buffer_lost_fn lost_cb; + void *ctx; /* passed into callbacks */ + + size_t page_size; + size_t mmap_size; + struct perf_cpu_buf **cpu_bufs; + struct epoll_event *events; + int cpu_cnt; /* number of allocated CPU buffers */ + int epoll_fd; /* perf event FD */ + int map_fd; /* BPF_MAP_TYPE_PERF_EVENT_ARRAY BPF map FD */ +}; + +static void *perfbuf_custom_consumer(void *input) +{ + struct perfbuf_libbpf_ctx *ctx = &perfbuf_libbpf_ctx; + struct perf_buffer *pb = ctx->perfbuf; + struct perf_cpu_buf *cpu_buf; + struct perf_event_mmap_page *header; + size_t mmap_mask = pb->mmap_size - 1; + struct perf_event_header *ehdr; + __u64 data_head, data_tail; + size_t ehdr_size; + void *base; + int i, cnt; + + while (true) { + if (args.back2back) + bufs_trigger_batch(); + cnt = epoll_wait(pb->epoll_fd, pb->events, pb->cpu_cnt, -1); + if (cnt <= 0) { + fprintf(stderr, "perf epoll failed: %d\n", -errno); + exit(1); + } + + for (i = 0; i < cnt; ++i) { + cpu_buf = pb->events[i].data.ptr; + header = cpu_buf->base; + base = ((void *)header) + pb->page_size; + + data_head = ring_buffer_read_head(header); + data_tail = header->data_tail; + while (data_head != data_tail) { + ehdr = base + (data_tail & mmap_mask); + ehdr_size = ehdr->size; + + if (ehdr->type == PERF_RECORD_SAMPLE) + atomic_inc(&buf_hits.value); + + data_tail += ehdr_size; + } + ring_buffer_write_tail(header, data_tail); + } + } + return NULL; +} + +const struct bench bench_rb_libbpf = { + .name = "rb-libbpf", + .validate = bufs_validate, + .setup = ringbuf_libbpf_setup, + .producer_thread = bufs_sample_producer, + .consumer_thread = ringbuf_libbpf_consumer, + .measure = ringbuf_libbpf_measure, + .report_progress = hits_drops_report_progress, + .report_final = hits_drops_report_final, +}; + +const struct bench bench_rb_custom = { + .name = "rb-custom", + .validate = bufs_validate, + .setup = ringbuf_custom_setup, + .producer_thread = bufs_sample_producer, + .consumer_thread = ringbuf_custom_consumer, + .measure = ringbuf_custom_measure, + .report_progress = hits_drops_report_progress, + .report_final = hits_drops_report_final, +}; + +const struct bench bench_pb_libbpf = { + .name = "pb-libbpf", + .validate = bufs_validate, + .setup = perfbuf_libbpf_setup, + .producer_thread = bufs_sample_producer, + .consumer_thread = perfbuf_libbpf_consumer, + .measure = perfbuf_measure, + .report_progress = hits_drops_report_progress, + .report_final = hits_drops_report_final, +}; + +const struct bench bench_pb_custom = { + .name = "pb-custom", + .validate = bufs_validate, + .setup = perfbuf_libbpf_setup, + .producer_thread = bufs_sample_producer, + .consumer_thread = perfbuf_custom_consumer, + .measure = perfbuf_measure, + .report_progress = hits_drops_report_progress, + .report_final = hits_drops_report_final, +}; + diff --git a/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh b/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh new file mode 100755 index 000000000000..af4aa04caba6 --- /dev/null +++ b/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh @@ -0,0 +1,75 @@ +#!/bin/bash + +set -eufo pipefail + +RUN_BENCH="sudo ./bench -w3 -d10 -a" + +function hits() +{ + echo "$*" | sed -E "s/.*hits\s+([0-9]+\.[0-9]+ ± [0-9]+\.[0-9]+M\/s).*/\1/" +} + +function drops() +{ + echo "$*" | sed -E "s/.*drops\s+([0-9]+\.[0-9]+ ± [0-9]+\.[0-9]+M\/s).*/\1/" +} + +function header() +{ + local len=${#1} + + printf "\n%s\n" "$1" + for i in $(seq 1 $len); do printf '='; done + printf '\n' +} + +function summarize() +{ + bench="$1" + summary=$(echo $2 | tail -n1) + printf "%-20s %s (drops %s)\n" "$bench" "$(hits $summary)" "$(drops $summary)" +} + +header "Single-producer, parallel producer" +for b in rb-libbpf rb-custom pb-libbpf pb-custom; do + summarize $b "$($RUN_BENCH $b)" +done + +header "Single-producer, parallel producer, sampled notification" +for b in rb-libbpf rb-custom pb-libbpf pb-custom; do + summarize $b "$($RUN_BENCH --rb-sampled $b)" +done + +header "Single-producer, back-to-back mode" +for b in rb-libbpf rb-custom pb-libbpf pb-custom; do + summarize $b "$($RUN_BENCH --rb-b2b $b)" + summarize $b-sampled "$($RUN_BENCH --rb-sampled --rb-b2b $b)" +done + +header "Ringbuf back-to-back, effect of sample rate" +for b in 1 5 10 25 50 100 250 500 1000 2000 3000; do + summarize "rb-sampled-$b" "$($RUN_BENCH --rb-b2b --rb-batch-cnt $b --rb-sampled --rb-sample-rate $b rb-custom)" +done +header "Perfbuf back-to-back, effect of sample rate" +for b in 1 5 10 25 50 100 250 500 1000 2000 3000; do + summarize "pb-sampled-$b" "$($RUN_BENCH --rb-b2b --rb-batch-cnt $b --rb-sampled --rb-sample-rate $b pb-custom)" +done + +header "Ringbuf back-to-back, reserve+commit vs output" +summarize "reserve" "$($RUN_BENCH --rb-b2b rb-custom)" +summarize "output" "$($RUN_BENCH --rb-b2b --rb-use-output rb-custom)" + +header "Ringbuf sampled, reserve+commit vs output" +summarize "reserve-sampled" "$($RUN_BENCH --rb-sampled rb-custom)" +summarize "output-sampled" "$($RUN_BENCH --rb-sampled --rb-use-output rb-custom)" + +header "Single-producer, consumer/producer competing on the same CPU, low batch count" +for b in rb-libbpf rb-custom pb-libbpf pb-custom; do + summarize $b "$($RUN_BENCH --rb-batch-cnt 1 --rb-sample-rate 1 --prod-affinity 0 --cons-affinity 0 $b)" +done + +header "Ringbuf, multi-producer contention" +for b in 1 2 3 4 8 12 16 20 24 28 32 36 40 44 48 52; do + summarize "rb-libbpf nr_prod $b" "$($RUN_BENCH -p$b --rb-batch-cnt 50 rb-libbpf)" +done + diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index 2301c4d3ecec..ea14e3ece812 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -6,6 +6,8 @@ #include <linux/if_tun.h> #include <sys/uio.h> +#include "bpf_flow.skel.h" + #ifndef IP_MF #define IP_MF 0x2000 #endif @@ -101,6 +103,7 @@ struct test { #define VLAN_HLEN 4 +static __u32 duration; struct test tests[] = { { .name = "ipv4", @@ -444,17 +447,130 @@ static int ifup(const char *ifname) return 0; } +static int init_prog_array(struct bpf_object *obj, struct bpf_map *prog_array) +{ + int i, err, map_fd, prog_fd; + struct bpf_program *prog; + char prog_name[32]; + + map_fd = bpf_map__fd(prog_array); + if (map_fd < 0) + return -1; + + for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + snprintf(prog_name, sizeof(prog_name), "flow_dissector/%i", i); + + prog = bpf_object__find_program_by_title(obj, prog_name); + if (!prog) + return -1; + + prog_fd = bpf_program__fd(prog); + if (prog_fd < 0) + return -1; + + err = bpf_map_update_elem(map_fd, &i, &prog_fd, BPF_ANY); + if (err) + return -1; + } + return 0; +} + +static void run_tests_skb_less(int tap_fd, struct bpf_map *keys) +{ + int i, err, keys_fd; + + keys_fd = bpf_map__fd(keys); + if (CHECK(keys_fd < 0, "bpf_map__fd", "err %d\n", keys_fd)) + return; + + for (i = 0; i < ARRAY_SIZE(tests); i++) { + /* Keep in sync with 'flags' from eth_get_headlen. */ + __u32 eth_get_headlen_flags = + BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG; + struct bpf_prog_test_run_attr tattr = {}; + struct bpf_flow_keys flow_keys = {}; + __u32 key = (__u32)(tests[i].keys.sport) << 16 | + tests[i].keys.dport; + + /* For skb-less case we can't pass input flags; run + * only the tests that have a matching set of flags. + */ + + if (tests[i].flags != eth_get_headlen_flags) + continue; + + err = tx_tap(tap_fd, &tests[i].pkt, sizeof(tests[i].pkt)); + CHECK(err < 0, "tx_tap", "err %d errno %d\n", err, errno); + + err = bpf_map_lookup_elem(keys_fd, &key, &flow_keys); + CHECK_ATTR(err, tests[i].name, "bpf_map_lookup_elem %d\n", err); + + CHECK_ATTR(err, tests[i].name, "skb-less err %d\n", err); + CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys); + + err = bpf_map_delete_elem(keys_fd, &key); + CHECK_ATTR(err, tests[i].name, "bpf_map_delete_elem %d\n", err); + } +} + +static void test_skb_less_prog_attach(struct bpf_flow *skel, int tap_fd) +{ + int err, prog_fd; + + prog_fd = bpf_program__fd(skel->progs._dissect); + if (CHECK(prog_fd < 0, "bpf_program__fd", "err %d\n", prog_fd)) + return; + + err = bpf_prog_attach(prog_fd, 0, BPF_FLOW_DISSECTOR, 0); + if (CHECK(err, "bpf_prog_attach", "err %d errno %d\n", err, errno)) + return; + + run_tests_skb_less(tap_fd, skel->maps.last_dissection); + + err = bpf_prog_detach(prog_fd, BPF_FLOW_DISSECTOR); + CHECK(err, "bpf_prog_detach", "err %d errno %d\n", err, errno); +} + +static void test_skb_less_link_create(struct bpf_flow *skel, int tap_fd) +{ + struct bpf_link *link; + int err, net_fd; + + net_fd = open("/proc/self/ns/net", O_RDONLY); + if (CHECK(net_fd < 0, "open(/proc/self/ns/net)", "err %d\n", errno)) + return; + + link = bpf_program__attach_netns(skel->progs._dissect, net_fd); + if (CHECK(IS_ERR(link), "attach_netns", "err %ld\n", PTR_ERR(link))) + goto out_close; + + run_tests_skb_less(tap_fd, skel->maps.last_dissection); + + err = bpf_link__destroy(link); + CHECK(err, "bpf_link__destroy", "err %d\n", err); +out_close: + close(net_fd); +} + void test_flow_dissector(void) { int i, err, prog_fd, keys_fd = -1, tap_fd; - struct bpf_object *obj; - __u32 duration = 0; + struct bpf_flow *skel; - err = bpf_flow_load(&obj, "./bpf_flow.o", "flow_dissector", - "jmp_table", "last_dissection", &prog_fd, &keys_fd); - if (CHECK_FAIL(err)) + skel = bpf_flow__open_and_load(); + if (CHECK(!skel, "skel", "failed to open/load skeleton\n")) return; + prog_fd = bpf_program__fd(skel->progs._dissect); + if (CHECK(prog_fd < 0, "bpf_program__fd", "err %d\n", prog_fd)) + goto out_destroy_skel; + keys_fd = bpf_map__fd(skel->maps.last_dissection); + if (CHECK(keys_fd < 0, "bpf_map__fd", "err %d\n", keys_fd)) + goto out_destroy_skel; + err = init_prog_array(skel->obj, skel->maps.jmp_table); + if (CHECK(err, "init_prog_array", "err %d\n", err)) + goto out_destroy_skel; + for (i = 0; i < ARRAY_SIZE(tests); i++) { struct bpf_flow_keys flow_keys; struct bpf_prog_test_run_attr tattr = { @@ -487,43 +603,17 @@ void test_flow_dissector(void) * via BPF map in this case. */ - err = bpf_prog_attach(prog_fd, 0, BPF_FLOW_DISSECTOR, 0); - CHECK(err, "bpf_prog_attach", "err %d errno %d\n", err, errno); - tap_fd = create_tap("tap0"); CHECK(tap_fd < 0, "create_tap", "tap_fd %d errno %d\n", tap_fd, errno); err = ifup("tap0"); CHECK(err, "ifup", "err %d errno %d\n", err, errno); - for (i = 0; i < ARRAY_SIZE(tests); i++) { - /* Keep in sync with 'flags' from eth_get_headlen. */ - __u32 eth_get_headlen_flags = - BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG; - struct bpf_prog_test_run_attr tattr = {}; - struct bpf_flow_keys flow_keys = {}; - __u32 key = (__u32)(tests[i].keys.sport) << 16 | - tests[i].keys.dport; - - /* For skb-less case we can't pass input flags; run - * only the tests that have a matching set of flags. - */ - - if (tests[i].flags != eth_get_headlen_flags) - continue; - - err = tx_tap(tap_fd, &tests[i].pkt, sizeof(tests[i].pkt)); - CHECK(err < 0, "tx_tap", "err %d errno %d\n", err, errno); - - err = bpf_map_lookup_elem(keys_fd, &key, &flow_keys); - CHECK_ATTR(err, tests[i].name, "bpf_map_lookup_elem %d\n", err); - - CHECK_ATTR(err, tests[i].name, "skb-less err %d\n", err); - CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys); - - err = bpf_map_delete_elem(keys_fd, &key); - CHECK_ATTR(err, tests[i].name, "bpf_map_delete_elem %d\n", err); - } + /* Test direct prog attachment */ + test_skb_less_prog_attach(skel, tap_fd); + /* Test indirect prog attachment via link */ + test_skb_less_link_create(skel, tap_fd); - bpf_prog_detach(prog_fd, BPF_FLOW_DISSECTOR); - bpf_object__close(obj); + close(tap_fd); +out_destroy_skel: + bpf_flow__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c index 1f51ba66b98b..15cb554a66d8 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c @@ -11,6 +11,7 @@ #include <fcntl.h> #include <sched.h> #include <stdbool.h> +#include <sys/stat.h> #include <unistd.h> #include <linux/bpf.h> @@ -18,21 +19,30 @@ #include "test_progs.h" -static bool is_attached(int netns) +static int init_net = -1; + +static __u32 query_attached_prog_id(int netns) { - __u32 cnt; + __u32 prog_ids[1] = {}; + __u32 prog_cnt = ARRAY_SIZE(prog_ids); int err; - err = bpf_prog_query(netns, BPF_FLOW_DISSECTOR, 0, NULL, NULL, &cnt); + err = bpf_prog_query(netns, BPF_FLOW_DISSECTOR, 0, NULL, + prog_ids, &prog_cnt); if (CHECK_FAIL(err)) { perror("bpf_prog_query"); - return true; /* fail-safe */ + return 0; } - return cnt > 0; + return prog_cnt == 1 ? prog_ids[0] : 0; +} + +static bool prog_is_attached(int netns) +{ + return query_attached_prog_id(netns) > 0; } -static int load_prog(void) +static int load_prog(enum bpf_prog_type type) { struct bpf_insn prog[] = { BPF_MOV64_IMM(BPF_REG_0, BPF_OK), @@ -40,61 +50,566 @@ static int load_prog(void) }; int fd; - fd = bpf_load_program(BPF_PROG_TYPE_FLOW_DISSECTOR, prog, - ARRAY_SIZE(prog), "GPL", 0, NULL, 0); + fd = bpf_load_program(type, prog, ARRAY_SIZE(prog), "GPL", 0, NULL, 0); if (CHECK_FAIL(fd < 0)) perror("bpf_load_program"); return fd; } -static void do_flow_dissector_reattach(void) +static __u32 query_prog_id(int prog) { - int prog_fd[2] = { -1, -1 }; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); int err; - prog_fd[0] = load_prog(); - if (prog_fd[0] < 0) - return; + err = bpf_obj_get_info_by_fd(prog, &info, &info_len); + if (CHECK_FAIL(err || info_len != sizeof(info))) { + perror("bpf_obj_get_info_by_fd"); + return 0; + } - prog_fd[1] = load_prog(); - if (prog_fd[1] < 0) - goto out_close; + return info.id; +} + +static int unshare_net(int old_net) +{ + int err, new_net; - err = bpf_prog_attach(prog_fd[0], 0, BPF_FLOW_DISSECTOR, 0); + err = unshare(CLONE_NEWNET); if (CHECK_FAIL(err)) { - perror("bpf_prog_attach-0"); - goto out_close; + perror("unshare(CLONE_NEWNET)"); + return -1; + } + new_net = open("/proc/self/ns/net", O_RDONLY); + if (CHECK_FAIL(new_net < 0)) { + perror("open(/proc/self/ns/net)"); + setns(old_net, CLONE_NEWNET); + return -1; } + return new_net; +} + +static void test_prog_attach_prog_attach(int netns, int prog1, int prog2) +{ + int err; + + err = bpf_prog_attach(prog1, 0, BPF_FLOW_DISSECTOR, 0); + if (CHECK_FAIL(err)) { + perror("bpf_prog_attach(prog1)"); + return; + } + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); /* Expect success when attaching a different program */ - err = bpf_prog_attach(prog_fd[1], 0, BPF_FLOW_DISSECTOR, 0); + err = bpf_prog_attach(prog2, 0, BPF_FLOW_DISSECTOR, 0); if (CHECK_FAIL(err)) { - perror("bpf_prog_attach-1"); + perror("bpf_prog_attach(prog2) #1"); goto out_detach; } + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog2)); /* Expect failure when attaching the same program twice */ - err = bpf_prog_attach(prog_fd[1], 0, BPF_FLOW_DISSECTOR, 0); + err = bpf_prog_attach(prog2, 0, BPF_FLOW_DISSECTOR, 0); if (CHECK_FAIL(!err || errno != EINVAL)) - perror("bpf_prog_attach-2"); + perror("bpf_prog_attach(prog2) #2"); + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog2)); out_detach: err = bpf_prog_detach(0, BPF_FLOW_DISSECTOR); if (CHECK_FAIL(err)) perror("bpf_prog_detach"); + CHECK_FAIL(prog_is_attached(netns)); +} + +static void test_link_create_link_create(int netns, int prog1, int prog2) +{ + DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts); + int link1, link2; + + link1 = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &opts); + if (CHECK_FAIL(link < 0)) { + perror("bpf_link_create(prog1)"); + return; + } + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); + + /* Expect failure creating link when another link exists */ + errno = 0; + link2 = bpf_link_create(prog2, netns, BPF_FLOW_DISSECTOR, &opts); + if (CHECK_FAIL(link2 != -1 || errno != E2BIG)) + perror("bpf_prog_attach(prog2) expected E2BIG"); + if (link2 != -1) + close(link2); + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); + + close(link1); + CHECK_FAIL(prog_is_attached(netns)); +} + +static void test_prog_attach_link_create(int netns, int prog1, int prog2) +{ + DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts); + int err, link; + + err = bpf_prog_attach(prog1, -1, BPF_FLOW_DISSECTOR, 0); + if (CHECK_FAIL(err)) { + perror("bpf_prog_attach(prog1)"); + return; + } + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); + + /* Expect failure creating link when prog attached */ + errno = 0; + link = bpf_link_create(prog2, netns, BPF_FLOW_DISSECTOR, &opts); + if (CHECK_FAIL(link != -1 || errno != EEXIST)) + perror("bpf_link_create(prog2) expected EEXIST"); + if (link != -1) + close(link); + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); + + err = bpf_prog_detach(-1, BPF_FLOW_DISSECTOR); + if (CHECK_FAIL(err)) + perror("bpf_prog_detach"); + CHECK_FAIL(prog_is_attached(netns)); +} + +static void test_link_create_prog_attach(int netns, int prog1, int prog2) +{ + DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts); + int err, link; + + link = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &opts); + if (CHECK_FAIL(link < 0)) { + perror("bpf_link_create(prog1)"); + return; + } + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); + + /* Expect failure attaching prog when link exists */ + errno = 0; + err = bpf_prog_attach(prog2, -1, BPF_FLOW_DISSECTOR, 0); + if (CHECK_FAIL(!err || errno != EEXIST)) + perror("bpf_prog_attach(prog2) expected EEXIST"); + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); + + close(link); + CHECK_FAIL(prog_is_attached(netns)); +} + +static void test_link_create_prog_detach(int netns, int prog1, int prog2) +{ + DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts); + int err, link; + + link = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &opts); + if (CHECK_FAIL(link < 0)) { + perror("bpf_link_create(prog1)"); + return; + } + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); + + /* Expect failure detaching prog when link exists */ + errno = 0; + err = bpf_prog_detach(-1, BPF_FLOW_DISSECTOR); + if (CHECK_FAIL(!err || errno != EINVAL)) + perror("bpf_prog_detach expected EINVAL"); + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); + + close(link); + CHECK_FAIL(prog_is_attached(netns)); +} + +static void test_prog_attach_detach_query(int netns, int prog1, int prog2) +{ + int err; + + err = bpf_prog_attach(prog1, 0, BPF_FLOW_DISSECTOR, 0); + if (CHECK_FAIL(err)) { + perror("bpf_prog_attach(prog1)"); + return; + } + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); + + err = bpf_prog_detach(0, BPF_FLOW_DISSECTOR); + if (CHECK_FAIL(err)) { + perror("bpf_prog_detach"); + return; + } + + /* Expect no prog attached after successful detach */ + CHECK_FAIL(prog_is_attached(netns)); +} + +static void test_link_create_close_query(int netns, int prog1, int prog2) +{ + DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts); + int link; + + link = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &opts); + if (CHECK_FAIL(link < 0)) { + perror("bpf_link_create(prog1)"); + return; + } + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); + + close(link); + /* Expect no prog attached after closing last link FD */ + CHECK_FAIL(prog_is_attached(netns)); +} + +static void test_link_update_no_old_prog(int netns, int prog1, int prog2) +{ + DECLARE_LIBBPF_OPTS(bpf_link_create_opts, create_opts); + DECLARE_LIBBPF_OPTS(bpf_link_update_opts, update_opts); + int err, link; + + link = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &create_opts); + if (CHECK_FAIL(link < 0)) { + perror("bpf_link_create(prog1)"); + return; + } + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); + + /* Expect success replacing the prog when old prog not specified */ + update_opts.flags = 0; + update_opts.old_prog_fd = 0; + err = bpf_link_update(link, prog2, &update_opts); + if (CHECK_FAIL(err)) + perror("bpf_link_update"); + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog2)); + + close(link); + CHECK_FAIL(prog_is_attached(netns)); +} + +static void test_link_update_replace_old_prog(int netns, int prog1, int prog2) +{ + DECLARE_LIBBPF_OPTS(bpf_link_create_opts, create_opts); + DECLARE_LIBBPF_OPTS(bpf_link_update_opts, update_opts); + int err, link; + link = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &create_opts); + if (CHECK_FAIL(link < 0)) { + perror("bpf_link_create(prog1)"); + return; + } + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); + + /* Expect success F_REPLACE and old prog specified to succeed */ + update_opts.flags = BPF_F_REPLACE; + update_opts.old_prog_fd = prog1; + err = bpf_link_update(link, prog2, &update_opts); + if (CHECK_FAIL(err)) + perror("bpf_link_update"); + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog2)); + + close(link); + CHECK_FAIL(prog_is_attached(netns)); +} + +static void test_link_update_invalid_opts(int netns, int prog1, int prog2) +{ + DECLARE_LIBBPF_OPTS(bpf_link_create_opts, create_opts); + DECLARE_LIBBPF_OPTS(bpf_link_update_opts, update_opts); + int err, link; + + link = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &create_opts); + if (CHECK_FAIL(link < 0)) { + perror("bpf_link_create(prog1)"); + return; + } + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); + + /* Expect update to fail w/ old prog FD but w/o F_REPLACE*/ + errno = 0; + update_opts.flags = 0; + update_opts.old_prog_fd = prog1; + err = bpf_link_update(link, prog2, &update_opts); + if (CHECK_FAIL(!err || errno != EINVAL)) { + perror("bpf_link_update expected EINVAL"); + goto out_close; + } + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); + + /* Expect update to fail on old prog FD mismatch */ + errno = 0; + update_opts.flags = BPF_F_REPLACE; + update_opts.old_prog_fd = prog2; + err = bpf_link_update(link, prog2, &update_opts); + if (CHECK_FAIL(!err || errno != EPERM)) { + perror("bpf_link_update expected EPERM"); + goto out_close; + } + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); + + /* Expect update to fail for invalid old prog FD */ + errno = 0; + update_opts.flags = BPF_F_REPLACE; + update_opts.old_prog_fd = -1; + err = bpf_link_update(link, prog2, &update_opts); + if (CHECK_FAIL(!err || errno != EBADF)) { + perror("bpf_link_update expected EBADF"); + goto out_close; + } + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); + + /* Expect update to fail with invalid flags */ + errno = 0; + update_opts.flags = BPF_F_ALLOW_MULTI; + update_opts.old_prog_fd = 0; + err = bpf_link_update(link, prog2, &update_opts); + if (CHECK_FAIL(!err || errno != EINVAL)) + perror("bpf_link_update expected EINVAL"); + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); + +out_close: + close(link); + CHECK_FAIL(prog_is_attached(netns)); +} + +static void test_link_update_invalid_prog(int netns, int prog1, int prog2) +{ + DECLARE_LIBBPF_OPTS(bpf_link_create_opts, create_opts); + DECLARE_LIBBPF_OPTS(bpf_link_update_opts, update_opts); + int err, link, prog3; + + link = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &create_opts); + if (CHECK_FAIL(link < 0)) { + perror("bpf_link_create(prog1)"); + return; + } + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); + + /* Expect failure when new prog FD is not valid */ + errno = 0; + update_opts.flags = 0; + update_opts.old_prog_fd = 0; + err = bpf_link_update(link, -1, &update_opts); + if (CHECK_FAIL(!err || errno != EBADF)) { + perror("bpf_link_update expected EINVAL"); + goto out_close_link; + } + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); + + prog3 = load_prog(BPF_PROG_TYPE_SOCKET_FILTER); + if (prog3 < 0) + goto out_close_link; + + /* Expect failure when new prog FD type doesn't match */ + errno = 0; + update_opts.flags = 0; + update_opts.old_prog_fd = 0; + err = bpf_link_update(link, prog3, &update_opts); + if (CHECK_FAIL(!err || errno != EINVAL)) + perror("bpf_link_update expected EINVAL"); + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); + + close(prog3); +out_close_link: + close(link); + CHECK_FAIL(prog_is_attached(netns)); +} + +static void test_link_update_netns_gone(int netns, int prog1, int prog2) +{ + DECLARE_LIBBPF_OPTS(bpf_link_create_opts, create_opts); + DECLARE_LIBBPF_OPTS(bpf_link_update_opts, update_opts); + int err, link, old_net; + + old_net = netns; + netns = unshare_net(old_net); + if (netns < 0) + return; + + link = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &create_opts); + if (CHECK_FAIL(link < 0)) { + perror("bpf_link_create(prog1)"); + return; + } + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); + + close(netns); + err = setns(old_net, CLONE_NEWNET); + if (CHECK_FAIL(err)) { + perror("setns(CLONE_NEWNET)"); + close(link); + return; + } + + /* Expect failure when netns destroyed */ + errno = 0; + update_opts.flags = 0; + update_opts.old_prog_fd = 0; + err = bpf_link_update(link, prog2, &update_opts); + if (CHECK_FAIL(!err || errno != ENOLINK)) + perror("bpf_link_update"); + + close(link); +} + +static void test_link_get_info(int netns, int prog1, int prog2) +{ + DECLARE_LIBBPF_OPTS(bpf_link_create_opts, create_opts); + DECLARE_LIBBPF_OPTS(bpf_link_update_opts, update_opts); + struct bpf_link_info info = {}; + struct stat netns_stat = {}; + __u32 info_len, link_id; + int err, link, old_net; + + old_net = netns; + netns = unshare_net(old_net); + if (netns < 0) + return; + + err = fstat(netns, &netns_stat); + if (CHECK_FAIL(err)) { + perror("stat(netns)"); + goto out_resetns; + } + + link = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &create_opts); + if (CHECK_FAIL(link < 0)) { + perror("bpf_link_create(prog1)"); + goto out_resetns; + } + + info_len = sizeof(info); + err = bpf_obj_get_info_by_fd(link, &info, &info_len); + if (CHECK_FAIL(err)) { + perror("bpf_obj_get_info"); + goto out_unlink; + } + CHECK_FAIL(info_len != sizeof(info)); + + /* Expect link info to be sane and match prog and netns details */ + CHECK_FAIL(info.type != BPF_LINK_TYPE_NETNS); + CHECK_FAIL(info.id == 0); + CHECK_FAIL(info.prog_id != query_prog_id(prog1)); + CHECK_FAIL(info.netns.netns_ino != netns_stat.st_ino); + CHECK_FAIL(info.netns.attach_type != BPF_FLOW_DISSECTOR); + + update_opts.flags = 0; + update_opts.old_prog_fd = 0; + err = bpf_link_update(link, prog2, &update_opts); + if (CHECK_FAIL(err)) { + perror("bpf_link_update(prog2)"); + goto out_unlink; + } + + link_id = info.id; + info_len = sizeof(info); + err = bpf_obj_get_info_by_fd(link, &info, &info_len); + if (CHECK_FAIL(err)) { + perror("bpf_obj_get_info"); + goto out_unlink; + } + CHECK_FAIL(info_len != sizeof(info)); + + /* Expect no info change after update except in prog id */ + CHECK_FAIL(info.type != BPF_LINK_TYPE_NETNS); + CHECK_FAIL(info.id != link_id); + CHECK_FAIL(info.prog_id != query_prog_id(prog2)); + CHECK_FAIL(info.netns.netns_ino != netns_stat.st_ino); + CHECK_FAIL(info.netns.attach_type != BPF_FLOW_DISSECTOR); + + /* Leave netns link is attached to and close last FD to it */ + err = setns(old_net, CLONE_NEWNET); + if (CHECK_FAIL(err)) { + perror("setns(NEWNET)"); + goto out_unlink; + } + close(netns); + old_net = -1; + netns = -1; + + info_len = sizeof(info); + err = bpf_obj_get_info_by_fd(link, &info, &info_len); + if (CHECK_FAIL(err)) { + perror("bpf_obj_get_info"); + goto out_unlink; + } + CHECK_FAIL(info_len != sizeof(info)); + + /* Expect netns_ino to change to 0 */ + CHECK_FAIL(info.type != BPF_LINK_TYPE_NETNS); + CHECK_FAIL(info.id != link_id); + CHECK_FAIL(info.prog_id != query_prog_id(prog2)); + CHECK_FAIL(info.netns.netns_ino != 0); + CHECK_FAIL(info.netns.attach_type != BPF_FLOW_DISSECTOR); + +out_unlink: + close(link); +out_resetns: + if (old_net != -1) + setns(old_net, CLONE_NEWNET); + if (netns != -1) + close(netns); +} + +static void run_tests(int netns) +{ + struct test { + const char *test_name; + void (*test_func)(int netns, int prog1, int prog2); + } tests[] = { + { "prog attach, prog attach", + test_prog_attach_prog_attach }, + { "link create, link create", + test_link_create_link_create }, + { "prog attach, link create", + test_prog_attach_link_create }, + { "link create, prog attach", + test_link_create_prog_attach }, + { "link create, prog detach", + test_link_create_prog_detach }, + { "prog attach, detach, query", + test_prog_attach_detach_query }, + { "link create, close, query", + test_link_create_close_query }, + { "link update no old prog", + test_link_update_no_old_prog }, + { "link update with replace old prog", + test_link_update_replace_old_prog }, + { "link update invalid opts", + test_link_update_invalid_opts }, + { "link update invalid prog", + test_link_update_invalid_prog }, + { "link update netns gone", + test_link_update_netns_gone }, + { "link get info", + test_link_get_info }, + }; + int i, progs[2] = { -1, -1 }; + char test_name[80]; + + for (i = 0; i < ARRAY_SIZE(progs); i++) { + progs[i] = load_prog(BPF_PROG_TYPE_FLOW_DISSECTOR); + if (progs[i] < 0) + goto out_close; + } + + for (i = 0; i < ARRAY_SIZE(tests); i++) { + snprintf(test_name, sizeof(test_name), + "flow dissector %s%s", + tests[i].test_name, + netns == init_net ? " (init_net)" : ""); + if (test__start_subtest(test_name)) + tests[i].test_func(netns, progs[0], progs[1]); + } out_close: - close(prog_fd[1]); - close(prog_fd[0]); + for (i = 0; i < ARRAY_SIZE(progs); i++) { + if (progs[i] != -1) + CHECK_FAIL(close(progs[i])); + } } void test_flow_dissector_reattach(void) { - int init_net, self_net, err; + int err, new_net, saved_net; - self_net = open("/proc/self/ns/net", O_RDONLY); - if (CHECK_FAIL(self_net < 0)) { + saved_net = open("/proc/self/ns/net", O_RDONLY); + if (CHECK_FAIL(saved_net < 0)) { perror("open(/proc/self/ns/net"); return; } @@ -111,30 +626,29 @@ void test_flow_dissector_reattach(void) goto out_close; } - if (is_attached(init_net)) { + if (prog_is_attached(init_net)) { test__skip(); printf("Can't test with flow dissector attached to init_net\n"); goto out_setns; } /* First run tests in root network namespace */ - do_flow_dissector_reattach(); + run_tests(init_net); /* Then repeat tests in a non-root namespace */ - err = unshare(CLONE_NEWNET); - if (CHECK_FAIL(err)) { - perror("unshare(CLONE_NEWNET)"); + new_net = unshare_net(init_net); + if (new_net < 0) goto out_setns; - } - do_flow_dissector_reattach(); + run_tests(new_net); + close(new_net); out_setns: /* Move back to netns we started in. */ - err = setns(self_net, CLONE_NEWNET); + err = setns(saved_net, CLONE_NEWNET); if (CHECK_FAIL(err)) perror("setns(/proc/self/ns/net)"); out_close: close(init_net); - close(self_net); + close(saved_net); } diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c new file mode 100644 index 000000000000..bb8541f240e2 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c @@ -0,0 +1,211 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include <linux/compiler.h> +#include <asm/barrier.h> +#include <test_progs.h> +#include <sys/mman.h> +#include <sys/epoll.h> +#include <time.h> +#include <sched.h> +#include <signal.h> +#include <pthread.h> +#include <sys/sysinfo.h> +#include <linux/perf_event.h> +#include <linux/ring_buffer.h> +#include "test_ringbuf.skel.h" + +#define EDONE 7777 + +static int duration = 0; + +struct sample { + int pid; + int seq; + long value; + char comm[16]; +}; + +static int sample_cnt; + +static int process_sample(void *ctx, void *data, size_t len) +{ + struct sample *s = data; + + sample_cnt++; + + switch (s->seq) { + case 0: + CHECK(s->value != 333, "sample1_value", "exp %ld, got %ld\n", + 333L, s->value); + return 0; + case 1: + CHECK(s->value != 777, "sample2_value", "exp %ld, got %ld\n", + 777L, s->value); + return -EDONE; + default: + /* we don't care about the rest */ + return 0; + } +} + +static struct test_ringbuf *skel; +static struct ring_buffer *ringbuf; + +static void trigger_samples() +{ + skel->bss->dropped = 0; + skel->bss->total = 0; + skel->bss->discarded = 0; + + /* trigger exactly two samples */ + skel->bss->value = 333; + syscall(__NR_getpgid); + skel->bss->value = 777; + syscall(__NR_getpgid); +} + +static void *poll_thread(void *input) +{ + long timeout = (long)input; + + return (void *)(long)ring_buffer__poll(ringbuf, timeout); +} + +void test_ringbuf(void) +{ + const size_t rec_sz = BPF_RINGBUF_HDR_SZ + sizeof(struct sample); + pthread_t thread; + long bg_ret = -1; + int err; + + skel = test_ringbuf__open_and_load(); + if (CHECK(!skel, "skel_open_load", "skeleton open&load failed\n")) + return; + + /* only trigger BPF program for current process */ + skel->bss->pid = getpid(); + + ringbuf = ring_buffer__new(bpf_map__fd(skel->maps.ringbuf), + process_sample, NULL, NULL); + if (CHECK(!ringbuf, "ringbuf_create", "failed to create ringbuf\n")) + goto cleanup; + + err = test_ringbuf__attach(skel); + if (CHECK(err, "skel_attach", "skeleton attachment failed: %d\n", err)) + goto cleanup; + + trigger_samples(); + + /* 2 submitted + 1 discarded records */ + CHECK(skel->bss->avail_data != 3 * rec_sz, + "err_avail_size", "exp %ld, got %ld\n", + 3L * rec_sz, skel->bss->avail_data); + CHECK(skel->bss->ring_size != 4096, + "err_ring_size", "exp %ld, got %ld\n", + 4096L, skel->bss->ring_size); + CHECK(skel->bss->cons_pos != 0, + "err_cons_pos", "exp %ld, got %ld\n", + 0L, skel->bss->cons_pos); + CHECK(skel->bss->prod_pos != 3 * rec_sz, + "err_prod_pos", "exp %ld, got %ld\n", + 3L * rec_sz, skel->bss->prod_pos); + + /* poll for samples */ + err = ring_buffer__poll(ringbuf, -1); + + /* -EDONE is used as an indicator that we are done */ + if (CHECK(err != -EDONE, "err_done", "done err: %d\n", err)) + goto cleanup; + + /* we expect extra polling to return nothing */ + err = ring_buffer__poll(ringbuf, 0); + if (CHECK(err != 0, "extra_samples", "poll result: %d\n", err)) + goto cleanup; + + CHECK(skel->bss->dropped != 0, "err_dropped", "exp %ld, got %ld\n", + 0L, skel->bss->dropped); + CHECK(skel->bss->total != 2, "err_total", "exp %ld, got %ld\n", + 2L, skel->bss->total); + CHECK(skel->bss->discarded != 1, "err_discarded", "exp %ld, got %ld\n", + 1L, skel->bss->discarded); + + /* now validate consumer position is updated and returned */ + trigger_samples(); + CHECK(skel->bss->cons_pos != 3 * rec_sz, + "err_cons_pos", "exp %ld, got %ld\n", + 3L * rec_sz, skel->bss->cons_pos); + err = ring_buffer__poll(ringbuf, -1); + CHECK(err <= 0, "poll_err", "err %d\n", err); + + /* start poll in background w/ long timeout */ + err = pthread_create(&thread, NULL, poll_thread, (void *)(long)10000); + if (CHECK(err, "bg_poll", "pthread_create failed: %d\n", err)) + goto cleanup; + + /* turn off notifications now */ + skel->bss->flags = BPF_RB_NO_WAKEUP; + + /* give background thread a bit of a time */ + usleep(50000); + trigger_samples(); + /* sleeping arbitrarily is bad, but no better way to know that + * epoll_wait() **DID NOT** unblock in background thread + */ + usleep(50000); + /* background poll should still be blocked */ + err = pthread_tryjoin_np(thread, (void **)&bg_ret); + if (CHECK(err != EBUSY, "try_join", "err %d\n", err)) + goto cleanup; + + /* BPF side did everything right */ + CHECK(skel->bss->dropped != 0, "err_dropped", "exp %ld, got %ld\n", + 0L, skel->bss->dropped); + CHECK(skel->bss->total != 2, "err_total", "exp %ld, got %ld\n", + 2L, skel->bss->total); + CHECK(skel->bss->discarded != 1, "err_discarded", "exp %ld, got %ld\n", + 1L, skel->bss->discarded); + + /* clear flags to return to "adaptive" notification mode */ + skel->bss->flags = 0; + + /* produce new samples, no notification should be triggered, because + * consumer is now behind + */ + trigger_samples(); + + /* background poll should still be blocked */ + err = pthread_tryjoin_np(thread, (void **)&bg_ret); + if (CHECK(err != EBUSY, "try_join", "err %d\n", err)) + goto cleanup; + + /* now force notifications */ + skel->bss->flags = BPF_RB_FORCE_WAKEUP; + sample_cnt = 0; + trigger_samples(); + + /* now we should get a pending notification */ + usleep(50000); + err = pthread_tryjoin_np(thread, (void **)&bg_ret); + if (CHECK(err, "join_bg", "err %d\n", err)) + goto cleanup; + + if (CHECK(bg_ret != 1, "bg_ret", "epoll_wait result: %ld", bg_ret)) + goto cleanup; + + /* 3 rounds, 2 samples each */ + CHECK(sample_cnt != 6, "wrong_sample_cnt", + "expected to see %d samples, got %d\n", 6, sample_cnt); + + /* BPF side did everything right */ + CHECK(skel->bss->dropped != 0, "err_dropped", "exp %ld, got %ld\n", + 0L, skel->bss->dropped); + CHECK(skel->bss->total != 2, "err_total", "exp %ld, got %ld\n", + 2L, skel->bss->total); + CHECK(skel->bss->discarded != 1, "err_discarded", "exp %ld, got %ld\n", + 1L, skel->bss->discarded); + + test_ringbuf__detach(skel); +cleanup: + ring_buffer__free(ringbuf); + test_ringbuf__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c new file mode 100644 index 000000000000..78e450609803 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c @@ -0,0 +1,102 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include <test_progs.h> +#include <sys/epoll.h> +#include "test_ringbuf_multi.skel.h" + +static int duration = 0; + +struct sample { + int pid; + int seq; + long value; + char comm[16]; +}; + +static int process_sample(void *ctx, void *data, size_t len) +{ + int ring = (unsigned long)ctx; + struct sample *s = data; + + switch (s->seq) { + case 0: + CHECK(ring != 1, "sample1_ring", "exp %d, got %d\n", 1, ring); + CHECK(s->value != 333, "sample1_value", "exp %ld, got %ld\n", + 333L, s->value); + break; + case 1: + CHECK(ring != 2, "sample2_ring", "exp %d, got %d\n", 2, ring); + CHECK(s->value != 777, "sample2_value", "exp %ld, got %ld\n", + 777L, s->value); + break; + default: + CHECK(true, "extra_sample", "unexpected sample seq %d, val %ld\n", + s->seq, s->value); + return -1; + } + + return 0; +} + +void test_ringbuf_multi(void) +{ + struct test_ringbuf_multi *skel; + struct ring_buffer *ringbuf; + int err; + + skel = test_ringbuf_multi__open_and_load(); + if (CHECK(!skel, "skel_open_load", "skeleton open&load failed\n")) + return; + + /* only trigger BPF program for current process */ + skel->bss->pid = getpid(); + + ringbuf = ring_buffer__new(bpf_map__fd(skel->maps.ringbuf1), + process_sample, (void *)(long)1, NULL); + if (CHECK(!ringbuf, "ringbuf_create", "failed to create ringbuf\n")) + goto cleanup; + + err = ring_buffer__add(ringbuf, bpf_map__fd(skel->maps.ringbuf2), + process_sample, (void *)(long)2); + if (CHECK(err, "ringbuf_add", "failed to add another ring\n")) + goto cleanup; + + err = test_ringbuf_multi__attach(skel); + if (CHECK(err, "skel_attach", "skeleton attachment failed: %d\n", err)) + goto cleanup; + + /* trigger few samples, some will be skipped */ + skel->bss->target_ring = 0; + skel->bss->value = 333; + syscall(__NR_getpgid); + + /* skipped, no ringbuf in slot 1 */ + skel->bss->target_ring = 1; + skel->bss->value = 555; + syscall(__NR_getpgid); + + skel->bss->target_ring = 2; + skel->bss->value = 777; + syscall(__NR_getpgid); + + /* poll for samples, should get 2 ringbufs back */ + err = ring_buffer__poll(ringbuf, -1); + if (CHECK(err != 4, "poll_res", "expected 4 records, got %d\n", err)) + goto cleanup; + + /* expect extra polling to return nothing */ + err = ring_buffer__poll(ringbuf, 0); + if (CHECK(err < 0, "extra_samples", "poll result: %d\n", err)) + goto cleanup; + + CHECK(skel->bss->dropped != 0, "err_dropped", "exp %ld, got %ld\n", + 0L, skel->bss->dropped); + CHECK(skel->bss->skipped != 1, "err_skipped", "exp %ld, got %ld\n", + 1L, skel->bss->skipped); + CHECK(skel->bss->total != 2, "err_total", "exp %ld, got %ld\n", + 2L, skel->bss->total); + +cleanup: + ring_buffer__free(ringbuf); + test_ringbuf_multi__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/skb_helpers.c b/tools/testing/selftests/bpf/prog_tests/skb_helpers.c new file mode 100644 index 000000000000..f302ad84a298 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/skb_helpers.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include <network_helpers.h> + +void test_skb_helpers(void) +{ + struct __sk_buff skb = { + .wire_len = 100, + .gso_segs = 8, + .gso_size = 10, + }; + struct bpf_prog_test_run_attr tattr = { + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .ctx_in = &skb, + .ctx_size_in = sizeof(skb), + .ctx_out = &skb, + .ctx_size_out = sizeof(skb), + }; + struct bpf_object *obj; + int err; + + err = bpf_prog_load("./test_skb_helpers.o", BPF_PROG_TYPE_SCHED_CLS, &obj, + &tattr.prog_fd); + if (CHECK_ATTR(err, "load", "err %d errno %d\n", err, errno)) + return; + err = bpf_prog_test_run_xattr(&tattr); + CHECK_ATTR(err, "len", "err %d errno %d\n", err, errno); + bpf_object__close(obj); +} diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index aa43e0bd210c..96e7b7f84c65 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -1,7 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2020 Cloudflare +#include <error.h> #include "test_progs.h" +#include "test_skmsg_load_helpers.skel.h" #define TCP_REPAIR 19 /* TCP sock is under repair right now */ @@ -70,10 +72,43 @@ out: close(s); } +static void test_skmsg_helpers(enum bpf_map_type map_type) +{ + struct test_skmsg_load_helpers *skel; + int err, map, verdict; + + skel = test_skmsg_load_helpers__open_and_load(); + if (CHECK_FAIL(!skel)) { + perror("test_skmsg_load_helpers__open_and_load"); + return; + } + + verdict = bpf_program__fd(skel->progs.prog_msg_verdict); + map = bpf_map__fd(skel->maps.sock_map); + + err = bpf_prog_attach(verdict, map, BPF_SK_MSG_VERDICT, 0); + if (CHECK_FAIL(err)) { + perror("bpf_prog_attach"); + goto out; + } + + err = bpf_prog_detach2(verdict, map, BPF_SK_MSG_VERDICT); + if (CHECK_FAIL(err)) { + perror("bpf_prog_detach2"); + goto out; + } +out: + test_skmsg_load_helpers__destroy(skel); +} + void test_sockmap_basic(void) { if (test__start_subtest("sockmap create_update_free")) test_sockmap_create_update_free(BPF_MAP_TYPE_SOCKMAP); if (test__start_subtest("sockhash create_update_free")) test_sockmap_create_update_free(BPF_MAP_TYPE_SOCKHASH); + if (test__start_subtest("sockmap sk_msg load helpers")) + test_skmsg_helpers(BPF_MAP_TYPE_SOCKMAP); + if (test__start_subtest("sockhash sk_msg load helpers")) + test_skmsg_helpers(BPF_MAP_TYPE_SOCKHASH); } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c new file mode 100644 index 000000000000..d19dbd668f6a --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c @@ -0,0 +1,97 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <uapi/linux/bpf.h> +#include <linux/if_link.h> +#include <test_progs.h> + +#include "test_xdp_devmap_helpers.skel.h" +#include "test_xdp_with_devmap_helpers.skel.h" + +#define IFINDEX_LO 1 + +struct bpf_devmap_val { + u32 ifindex; /* device index */ + union { + int fd; /* prog fd on map write */ + u32 id; /* prog id on map read */ + } bpf_prog; +}; + +void test_xdp_with_devmap_helpers(void) +{ + struct test_xdp_with_devmap_helpers *skel; + struct bpf_prog_info info = {}; + struct bpf_devmap_val val = { + .ifindex = IFINDEX_LO, + }; + __u32 len = sizeof(info); + __u32 duration = 0, idx = 0; + int err, dm_fd, map_fd; + + + skel = test_xdp_with_devmap_helpers__open_and_load(); + if (CHECK_FAIL(!skel)) { + perror("test_xdp_with_devmap_helpers__open_and_load"); + return; + } + + /* can not attach program with DEVMAPs that allow programs + * as xdp generic + */ + dm_fd = bpf_program__fd(skel->progs.xdp_redir_prog); + err = bpf_set_link_xdp_fd(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE); + CHECK(err == 0, "Generic attach of program with 8-byte devmap", + "should have failed\n"); + + dm_fd = bpf_program__fd(skel->progs.xdp_dummy_dm); + map_fd = bpf_map__fd(skel->maps.dm_ports); + err = bpf_obj_get_info_by_fd(dm_fd, &info, &len); + if (CHECK_FAIL(err)) + goto out_close; + + val.bpf_prog.fd = dm_fd; + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + CHECK(err, "Add program to devmap entry", + "err %d errno %d\n", err, errno); + + err = bpf_map_lookup_elem(map_fd, &idx, &val); + CHECK(err, "Read devmap entry", "err %d errno %d\n", err, errno); + CHECK(info.id != val.bpf_prog.id, "Expected program id in devmap entry", + "expected %u read %u\n", info.id, val.bpf_prog.id); + + /* can not attach BPF_XDP_DEVMAP program to a device */ + err = bpf_set_link_xdp_fd(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE); + CHECK(err == 0, "Attach of BPF_XDP_DEVMAP program", + "should have failed\n"); + + val.ifindex = 1; + val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_prog); + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + CHECK(err == 0, "Add non-BPF_XDP_DEVMAP program to devmap entry", + "should have failed\n"); + +out_close: + test_xdp_with_devmap_helpers__destroy(skel); +} + +void test_neg_xdp_devmap_helpers(void) +{ + struct test_xdp_devmap_helpers *skel; + __u32 duration = 0; + + skel = test_xdp_devmap_helpers__open_and_load(); + if (CHECK(skel, + "Load of XDP program accessing egress ifindex without attach type", + "should have failed\n")) { + test_xdp_devmap_helpers__destroy(skel); + } +} + + +void test_xdp_devmap_attach(void) +{ + if (test__start_subtest("DEVMAP with programs in entries")) + test_xdp_with_devmap_helpers(); + + if (test__start_subtest("Verifier check of DEVMAP programs")) + test_neg_xdp_devmap_helpers(); +} diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c index 9941f0ba471e..de6de9221518 100644 --- a/tools/testing/selftests/bpf/progs/bpf_flow.c +++ b/tools/testing/selftests/bpf/progs/bpf_flow.c @@ -20,20 +20,20 @@ #include <bpf/bpf_endian.h> int _version SEC("version") = 1; -#define PROG(F) SEC(#F) int bpf_func_##F +#define PROG(F) PROG_(F, _##F) +#define PROG_(NUM, NAME) SEC("flow_dissector/"#NUM) int bpf_func##NAME /* These are the identifiers of the BPF programs that will be used in tail * calls. Name is limited to 16 characters, with the terminating character and * bpf_func_ above, we have only 6 to work with, anything after will be cropped. */ -enum { - IP, - IPV6, - IPV6OP, /* Destination/Hop-by-Hop Options IPv6 Extension header */ - IPV6FR, /* Fragmentation IPv6 Extension Header */ - MPLS, - VLAN, -}; +#define IP 0 +#define IPV6 1 +#define IPV6OP 2 /* Destination/Hop-by-Hop Options IPv6 Ext. Header */ +#define IPV6FR 3 /* Fragmentation IPv6 Extension Header */ +#define MPLS 4 +#define VLAN 5 +#define MAX_PROG 6 #define IP_MF 0x2000 #define IP_OFFSET 0x1FFF @@ -59,7 +59,7 @@ struct frag_hdr { struct { __uint(type, BPF_MAP_TYPE_PROG_ARRAY); - __uint(max_entries, 8); + __uint(max_entries, MAX_PROG); __uint(key_size, sizeof(__u32)); __uint(value_size, sizeof(__u32)); } jmp_table SEC(".maps"); diff --git a/tools/testing/selftests/bpf/progs/connect4_prog.c b/tools/testing/selftests/bpf/progs/connect4_prog.c index c2c85c31cffd..1ab2c5eba86c 100644 --- a/tools/testing/selftests/bpf/progs/connect4_prog.c +++ b/tools/testing/selftests/bpf/progs/connect4_prog.c @@ -9,6 +9,8 @@ #include <linux/in6.h> #include <sys/socket.h> #include <netinet/tcp.h> +#include <linux/if.h> +#include <errno.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> @@ -21,6 +23,10 @@ #define TCP_CA_NAME_MAX 16 #endif +#ifndef IFNAMSIZ +#define IFNAMSIZ 16 +#endif + int _version SEC("version") = 1; __attribute__ ((noinline)) @@ -75,6 +81,29 @@ static __inline int set_cc(struct bpf_sock_addr *ctx) return 0; } +static __inline int bind_to_device(struct bpf_sock_addr *ctx) +{ + char veth1[IFNAMSIZ] = "test_sock_addr1"; + char veth2[IFNAMSIZ] = "test_sock_addr2"; + char missing[IFNAMSIZ] = "nonexistent_dev"; + char del_bind[IFNAMSIZ] = ""; + + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE, + &veth1, sizeof(veth1))) + return 1; + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE, + &veth2, sizeof(veth2))) + return 1; + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE, + &missing, sizeof(missing)) != -ENODEV) + return 1; + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE, + &del_bind, sizeof(del_bind))) + return 1; + + return 0; +} + SEC("cgroup/connect4") int connect_v4_prog(struct bpf_sock_addr *ctx) { @@ -88,6 +117,10 @@ int connect_v4_prog(struct bpf_sock_addr *ctx) tuple.ipv4.daddr = bpf_htonl(DST_REWRITE_IP4); tuple.ipv4.dport = bpf_htons(DST_REWRITE_PORT4); + /* Bind to device and unbind it. */ + if (bind_to_device(ctx)) + return 0; + if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM) return 0; else if (ctx->type == SOCK_STREAM) diff --git a/tools/testing/selftests/bpf/progs/perfbuf_bench.c b/tools/testing/selftests/bpf/progs/perfbuf_bench.c new file mode 100644 index 000000000000..e5ab4836a641 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/perfbuf_bench.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __uint(value_size, sizeof(int)); + __uint(key_size, sizeof(int)); +} perfbuf SEC(".maps"); + +const volatile int batch_cnt = 0; + +long sample_val = 42; +long dropped __attribute__((aligned(128))) = 0; + +SEC("fentry/__x64_sys_getpgid") +int bench_perfbuf(void *ctx) +{ + __u64 *sample; + int i; + + for (i = 0; i < batch_cnt; i++) { + if (bpf_perf_event_output(ctx, &perfbuf, BPF_F_CURRENT_CPU, + &sample_val, sizeof(sample_val))) + __sync_add_and_fetch(&dropped, 1); + } + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/ringbuf_bench.c b/tools/testing/selftests/bpf/progs/ringbuf_bench.c new file mode 100644 index 000000000000..123607d314d6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/ringbuf_bench.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_RINGBUF); +} ringbuf SEC(".maps"); + +const volatile int batch_cnt = 0; +const volatile long use_output = 0; + +long sample_val = 42; +long dropped __attribute__((aligned(128))) = 0; + +const volatile long wakeup_data_size = 0; + +static __always_inline long get_flags() +{ + long sz; + + if (!wakeup_data_size) + return 0; + + sz = bpf_ringbuf_query(&ringbuf, BPF_RB_AVAIL_DATA); + return sz >= wakeup_data_size ? BPF_RB_FORCE_WAKEUP : BPF_RB_NO_WAKEUP; +} + +SEC("fentry/__x64_sys_getpgid") +int bench_ringbuf(void *ctx) +{ + long *sample, flags; + int i; + + if (!use_output) { + for (i = 0; i < batch_cnt; i++) { + sample = bpf_ringbuf_reserve(&ringbuf, + sizeof(sample_val), 0); + if (!sample) { + __sync_add_and_fetch(&dropped, 1); + } else { + *sample = sample_val; + flags = get_flags(); + bpf_ringbuf_submit(sample, flags); + } + } + } else { + for (i = 0; i < batch_cnt; i++) { + flags = get_flags(); + if (bpf_ringbuf_output(&ringbuf, &sample_val, + sizeof(sample_val), flags)) + __sync_add_and_fetch(&dropped, 1); + } + } + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_ringbuf.c b/tools/testing/selftests/bpf/progs/test_ringbuf.c new file mode 100644 index 000000000000..8ba9959b036b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_ringbuf.c @@ -0,0 +1,78 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +struct sample { + int pid; + int seq; + long value; + char comm[16]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_RINGBUF); + __uint(max_entries, 1 << 12); +} ringbuf SEC(".maps"); + +/* inputs */ +int pid = 0; +long value = 0; +long flags = 0; + +/* outputs */ +long total = 0; +long discarded = 0; +long dropped = 0; + +long avail_data = 0; +long ring_size = 0; +long cons_pos = 0; +long prod_pos = 0; + +/* inner state */ +long seq = 0; + +SEC("tp/syscalls/sys_enter_getpgid") +int test_ringbuf(void *ctx) +{ + int cur_pid = bpf_get_current_pid_tgid() >> 32; + struct sample *sample; + int zero = 0; + + if (cur_pid != pid) + return 0; + + sample = bpf_ringbuf_reserve(&ringbuf, sizeof(*sample), 0); + if (!sample) { + __sync_fetch_and_add(&dropped, 1); + return 1; + } + + sample->pid = pid; + bpf_get_current_comm(sample->comm, sizeof(sample->comm)); + sample->value = value; + + sample->seq = seq++; + __sync_fetch_and_add(&total, 1); + + if (sample->seq & 1) { + /* copy from reserved sample to a new one... */ + bpf_ringbuf_output(&ringbuf, sample, sizeof(*sample), flags); + /* ...and then discard reserved sample */ + bpf_ringbuf_discard(sample, flags); + __sync_fetch_and_add(&discarded, 1); + } else { + bpf_ringbuf_submit(sample, flags); + } + + avail_data = bpf_ringbuf_query(&ringbuf, BPF_RB_AVAIL_DATA); + ring_size = bpf_ringbuf_query(&ringbuf, BPF_RB_RING_SIZE); + cons_pos = bpf_ringbuf_query(&ringbuf, BPF_RB_CONS_POS); + prod_pos = bpf_ringbuf_query(&ringbuf, BPF_RB_PROD_POS); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_ringbuf_multi.c b/tools/testing/selftests/bpf/progs/test_ringbuf_multi.c new file mode 100644 index 000000000000..edf3b6953533 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_ringbuf_multi.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +struct sample { + int pid; + int seq; + long value; + char comm[16]; +}; + +struct ringbuf_map { + __uint(type, BPF_MAP_TYPE_RINGBUF); + __uint(max_entries, 1 << 12); +} ringbuf1 SEC(".maps"), + ringbuf2 SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, 4); + __type(key, int); + __array(values, struct ringbuf_map); +} ringbuf_arr SEC(".maps") = { + .values = { + [0] = &ringbuf1, + [2] = &ringbuf2, + }, +}; + +/* inputs */ +int pid = 0; +int target_ring = 0; +long value = 0; + +/* outputs */ +long total = 0; +long dropped = 0; +long skipped = 0; + +SEC("tp/syscalls/sys_enter_getpgid") +int test_ringbuf(void *ctx) +{ + int cur_pid = bpf_get_current_pid_tgid() >> 32; + struct sample *sample; + void *rb; + int zero = 0; + + if (cur_pid != pid) + return 0; + + rb = bpf_map_lookup_elem(&ringbuf_arr, &target_ring); + if (!rb) { + skipped += 1; + return 1; + } + + sample = bpf_ringbuf_reserve(rb, sizeof(*sample), 0); + if (!sample) { + dropped += 1; + return 1; + } + + sample->pid = pid; + bpf_get_current_comm(sample->comm, sizeof(sample->comm)); + sample->value = value; + + sample->seq = total; + total += 1; + + bpf_ringbuf_submit(sample, 0); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_skb_helpers.c b/tools/testing/selftests/bpf/progs/test_skb_helpers.c new file mode 100644 index 000000000000..bb3fbf1a29e3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_skb_helpers.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#define TEST_COMM_LEN 16 + +struct { + __uint(type, BPF_MAP_TYPE_CGROUP_ARRAY); + __uint(max_entries, 1); + __type(key, u32); + __type(value, u32); +} cgroup_map SEC(".maps"); + +char _license[] SEC("license") = "GPL"; + +SEC("classifier/test_skb_helpers") +int test_skb_helpers(struct __sk_buff *skb) +{ + struct task_struct *task; + char comm[TEST_COMM_LEN]; + __u32 tpid; + + task = (struct task_struct *)bpf_get_current_task(); + bpf_probe_read_kernel(&tpid , sizeof(tpid), &task->tgid); + bpf_probe_read_kernel_str(&comm, sizeof(comm), &task->comm); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_skmsg_load_helpers.c b/tools/testing/selftests/bpf/progs/test_skmsg_load_helpers.c new file mode 100644 index 000000000000..45e8fc75a739 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_skmsg_load_helpers.c @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Isovalent, Inc. +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 2); + __type(key, __u32); + __type(value, __u64); +} sock_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKHASH); + __uint(max_entries, 2); + __type(key, __u32); + __type(value, __u64); +} sock_hash SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, __u32); + __type(value, __u64); +} socket_storage SEC(".maps"); + +SEC("sk_msg") +int prog_msg_verdict(struct sk_msg_md *msg) +{ + struct task_struct *task = (struct task_struct *)bpf_get_current_task(); + int verdict = SK_PASS; + __u32 pid, tpid; + __u64 *sk_stg; + + pid = bpf_get_current_pid_tgid() >> 32; + sk_stg = bpf_sk_storage_get(&socket_storage, msg->sk, 0, BPF_SK_STORAGE_GET_F_CREATE); + if (!sk_stg) + return SK_DROP; + *sk_stg = pid; + bpf_probe_read_kernel(&tpid , sizeof(tpid), &task->tgid); + if (pid != tpid) + verdict = SK_DROP; + bpf_sk_storage_delete(&socket_storage, (void *)msg->sk); + return verdict; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h index a443d3637db3..057036ca1111 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h +++ b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h @@ -79,11 +79,18 @@ struct { struct { __uint(type, BPF_MAP_TYPE_ARRAY); - __uint(max_entries, 1); + __uint(max_entries, 2); __type(key, int); __type(value, int); } sock_skb_opts SEC(".maps"); +struct { + __uint(type, TEST_MAP_TYPE); + __uint(max_entries, 20); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(int)); +} tls_sock_map SEC(".maps"); + SEC("sk_skb1") int bpf_prog1(struct __sk_buff *skb) { @@ -118,6 +125,43 @@ int bpf_prog2(struct __sk_buff *skb) } +SEC("sk_skb3") +int bpf_prog3(struct __sk_buff *skb) +{ + const int one = 1; + int err, *f, ret = SK_PASS; + void *data_end; + char *c; + + err = bpf_skb_pull_data(skb, 19); + if (err) + goto tls_out; + + c = (char *)(long)skb->data; + data_end = (void *)(long)skb->data_end; + + if (c + 18 < data_end) + memcpy(&c[13], "PASS", 4); + f = bpf_map_lookup_elem(&sock_skb_opts, &one); + if (f && *f) { + __u64 flags = 0; + + ret = 0; + flags = *f; +#ifdef SOCKMAP + return bpf_sk_redirect_map(skb, &tls_sock_map, ret, flags); +#else + return bpf_sk_redirect_hash(skb, &tls_sock_map, &ret, flags); +#endif + } + + f = bpf_map_lookup_elem(&sock_skb_opts, &one); + if (f && *f) + ret = SK_DROP; +tls_out: + return ret; +} + SEC("sockops") int bpf_sockmap(struct bpf_sock_ops *skops) { diff --git a/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c new file mode 100644 index 000000000000..e5c0f131c8a7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0 +/* fails to load without expected_attach_type = BPF_XDP_DEVMAP + * because of access to egress_ifindex + */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +SEC("xdp_dm_log") +int xdpdm_devlog(struct xdp_md *ctx) +{ + char fmt[] = "devmap redirect: dev %u -> dev %u len %u\n"; + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + unsigned int len = data_end - data; + + bpf_trace_printk(fmt, sizeof(fmt), + ctx->ingress_ifindex, ctx->egress_ifindex, len); + + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c new file mode 100644 index 000000000000..deef0e050863 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_DEVMAP); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_devmap_val)); + __uint(max_entries, 4); +} dm_ports SEC(".maps"); + +SEC("xdp_redir") +int xdp_redir_prog(struct xdp_md *ctx) +{ + return bpf_redirect_map(&dm_ports, 1, 0); +} + +/* invalid program on DEVMAP entry; + * SEC name means expected attach type not set + */ +SEC("xdp_dummy") +int xdp_dummy_prog(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +/* valid program on DEVMAP entry via SEC name; + * has access to egress and ingress ifindex + */ +SEC("xdp_devmap") +int xdp_dummy_dm(struct xdp_md *ctx) +{ + char fmt[] = "devmap redirect: dev %u -> dev %u len %u\n"; + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + unsigned int len = data_end - data; + + bpf_trace_printk(fmt, sizeof(fmt), + ctx->ingress_ifindex, ctx->egress_ifindex, len); + + return XDP_PASS; +} +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index c6766b2cff85..6a12a0e01e07 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -1394,23 +1394,25 @@ static void test_map_rdonly(void) key = 1; value = 1234; - /* Insert key=1 element. */ + /* Try to insert key=1 element. */ assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == -1 && errno == EPERM); - /* Check that key=2 is not found. */ + /* Check that key=1 is not found. */ assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == ENOENT); assert(bpf_map_get_next_key(fd, &key, &value) == -1 && errno == ENOENT); + + close(fd); } -static void test_map_wronly(void) +static void test_map_wronly_hash(void) { int fd, key = 0, value = 0; fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), MAP_SIZE, map_flags | BPF_F_WRONLY); if (fd < 0) { - printf("Failed to create map for read only test '%s'!\n", + printf("Failed to create map for write only test '%s'!\n", strerror(errno)); exit(1); } @@ -1420,9 +1422,49 @@ static void test_map_wronly(void) /* Insert key=1 element. */ assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == 0); - /* Check that key=2 is not found. */ + /* Check that reading elements and keys from the map is not allowed. */ assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == EPERM); assert(bpf_map_get_next_key(fd, &key, &value) == -1 && errno == EPERM); + + close(fd); +} + +static void test_map_wronly_stack_or_queue(enum bpf_map_type map_type) +{ + int fd, value = 0; + + assert(map_type == BPF_MAP_TYPE_QUEUE || + map_type == BPF_MAP_TYPE_STACK); + fd = bpf_create_map(map_type, 0, sizeof(value), MAP_SIZE, + map_flags | BPF_F_WRONLY); + /* Stack/Queue maps do not support BPF_F_NO_PREALLOC */ + if (map_flags & BPF_F_NO_PREALLOC) { + assert(fd < 0 && errno == EINVAL); + return; + } + if (fd < 0) { + printf("Failed to create map '%s'!\n", strerror(errno)); + exit(1); + } + + value = 1234; + assert(bpf_map_update_elem(fd, NULL, &value, BPF_ANY) == 0); + + /* Peek element should fail */ + assert(bpf_map_lookup_elem(fd, NULL, &value) == -1 && errno == EPERM); + + /* Pop element should fail */ + assert(bpf_map_lookup_and_delete_elem(fd, NULL, &value) == -1 && + errno == EPERM); + + close(fd); +} + +static void test_map_wronly(void) +{ + test_map_wronly_hash(); + test_map_wronly_stack_or_queue(BPF_MAP_TYPE_STACK); + test_map_wronly_stack_or_queue(BPF_MAP_TYPE_QUEUE); } static void prepare_reuseport_grp(int type, int map_fd, size_t map_elem_size, diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index c80643828b82..37695fc8096a 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -63,8 +63,8 @@ int s1, s2, c1, c2, p1, p2; int test_cnt; int passed; int failed; -int map_fd[8]; -struct bpf_map *maps[8]; +int map_fd[9]; +struct bpf_map *maps[9]; int prog_fd[11]; int txmsg_pass; @@ -79,7 +79,10 @@ int txmsg_end_push; int txmsg_start_pop; int txmsg_pop; int txmsg_ingress; -int txmsg_skb; +int txmsg_redir_skb; +int txmsg_ktls_skb; +int txmsg_ktls_skb_drop; +int txmsg_ktls_skb_redir; int ktls; int peek_flag; @@ -104,7 +107,7 @@ static const struct option long_options[] = { {"txmsg_start_pop", required_argument, NULL, 'w'}, {"txmsg_pop", required_argument, NULL, 'x'}, {"txmsg_ingress", no_argument, &txmsg_ingress, 1 }, - {"txmsg_skb", no_argument, &txmsg_skb, 1 }, + {"txmsg_redir_skb", no_argument, &txmsg_redir_skb, 1 }, {"ktls", no_argument, &ktls, 1 }, {"peek", no_argument, &peek_flag, 1 }, {"whitelist", required_argument, NULL, 'n' }, @@ -169,7 +172,8 @@ static void test_reset(void) txmsg_start_push = txmsg_end_push = 0; txmsg_pass = txmsg_drop = txmsg_redir = 0; txmsg_apply = txmsg_cork = 0; - txmsg_ingress = txmsg_skb = 0; + txmsg_ingress = txmsg_redir_skb = 0; + txmsg_ktls_skb = txmsg_ktls_skb_drop = txmsg_ktls_skb_redir = 0; } static int test_start_subtest(const struct _test *t, struct sockmap_options *o) @@ -502,14 +506,41 @@ unwind_iov: static int msg_verify_data(struct msghdr *msg, int size, int chunk_sz) { - int i, j, bytes_cnt = 0; + int i, j = 0, bytes_cnt = 0; unsigned char k = 0; for (i = 0; i < msg->msg_iovlen; i++) { unsigned char *d = msg->msg_iov[i].iov_base; - for (j = 0; - j < msg->msg_iov[i].iov_len && size; j++) { + /* Special case test for skb ingress + ktls */ + if (i == 0 && txmsg_ktls_skb) { + if (msg->msg_iov[i].iov_len < 4) + return -EIO; + if (txmsg_ktls_skb_redir) { + if (memcmp(&d[13], "PASS", 4) != 0) { + fprintf(stderr, + "detected redirect ktls_skb data error with skb ingress update @iov[%i]:%i \"%02x %02x %02x %02x\" != \"PASS\"\n", i, 0, d[13], d[14], d[15], d[16]); + return -EIO; + } + d[13] = 0; + d[14] = 1; + d[15] = 2; + d[16] = 3; + j = 13; + } else if (txmsg_ktls_skb) { + if (memcmp(d, "PASS", 4) != 0) { + fprintf(stderr, + "detected ktls_skb data error with skb ingress update @iov[%i]:%i \"%02x %02x %02x %02x\" != \"PASS\"\n", i, 0, d[0], d[1], d[2], d[3]); + return -EIO; + } + d[0] = 0; + d[1] = 1; + d[2] = 2; + d[3] = 3; + } + } + + for (; j < msg->msg_iov[i].iov_len && size; j++) { if (d[j] != k++) { fprintf(stderr, "detected data corruption @iov[%i]:%i %02x != %02x, %02x ?= %02x\n", @@ -724,7 +755,7 @@ static int sendmsg_test(struct sockmap_options *opt) rxpid = fork(); if (rxpid == 0) { iov_buf -= (txmsg_pop - txmsg_start_pop + 1); - if (opt->drop_expected) + if (opt->drop_expected || txmsg_ktls_skb_drop) _exit(0); if (!iov_buf) /* zero bytes sent case */ @@ -911,8 +942,28 @@ static int run_options(struct sockmap_options *options, int cg_fd, int test) return err; } + /* Attach programs to TLS sockmap */ + if (txmsg_ktls_skb) { + err = bpf_prog_attach(prog_fd[0], map_fd[8], + BPF_SK_SKB_STREAM_PARSER, 0); + if (err) { + fprintf(stderr, + "ERROR: bpf_prog_attach (TLS sockmap %i->%i): %d (%s)\n", + prog_fd[0], map_fd[8], err, strerror(errno)); + return err; + } + + err = bpf_prog_attach(prog_fd[2], map_fd[8], + BPF_SK_SKB_STREAM_VERDICT, 0); + if (err) { + fprintf(stderr, "ERROR: bpf_prog_attach (TLS sockmap): %d (%s)\n", + err, strerror(errno)); + return err; + } + } + /* Attach to cgroups */ - err = bpf_prog_attach(prog_fd[2], cg_fd, BPF_CGROUP_SOCK_OPS, 0); + err = bpf_prog_attach(prog_fd[3], cg_fd, BPF_CGROUP_SOCK_OPS, 0); if (err) { fprintf(stderr, "ERROR: bpf_prog_attach (groups): %d (%s)\n", err, strerror(errno)); @@ -928,15 +979,15 @@ run: /* Attach txmsg program to sockmap */ if (txmsg_pass) - tx_prog_fd = prog_fd[3]; - else if (txmsg_redir) tx_prog_fd = prog_fd[4]; - else if (txmsg_apply) + else if (txmsg_redir) tx_prog_fd = prog_fd[5]; - else if (txmsg_cork) + else if (txmsg_apply) tx_prog_fd = prog_fd[6]; - else if (txmsg_drop) + else if (txmsg_cork) tx_prog_fd = prog_fd[7]; + else if (txmsg_drop) + tx_prog_fd = prog_fd[8]; else tx_prog_fd = 0; @@ -1108,7 +1159,35 @@ run: } } - if (txmsg_skb) { + if (txmsg_ktls_skb) { + int ingress = BPF_F_INGRESS; + + i = 0; + err = bpf_map_update_elem(map_fd[8], &i, &p2, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (c1 sockmap): %d (%s)\n", + err, strerror(errno)); + } + + if (txmsg_ktls_skb_redir) { + i = 1; + err = bpf_map_update_elem(map_fd[7], + &i, &ingress, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (txmsg_ingress): %d (%s)\n", + err, strerror(errno)); + } + } + + if (txmsg_ktls_skb_drop) { + i = 1; + err = bpf_map_update_elem(map_fd[7], &i, &i, BPF_ANY); + } + } + + if (txmsg_redir_skb) { int skb_fd = (test == SENDMSG || test == SENDPAGE) ? p2 : p1; int ingress = BPF_F_INGRESS; @@ -1123,8 +1202,7 @@ run: } i = 3; - err = bpf_map_update_elem(map_fd[0], - &i, &skb_fd, BPF_ANY); + err = bpf_map_update_elem(map_fd[0], &i, &skb_fd, BPF_ANY); if (err) { fprintf(stderr, "ERROR: bpf_map_update_elem (c1 sockmap): %d (%s)\n", @@ -1158,9 +1236,12 @@ run: fprintf(stderr, "unknown test\n"); out: /* Detatch and zero all the maps */ - bpf_prog_detach2(prog_fd[2], cg_fd, BPF_CGROUP_SOCK_OPS); + bpf_prog_detach2(prog_fd[3], cg_fd, BPF_CGROUP_SOCK_OPS); bpf_prog_detach2(prog_fd[0], map_fd[0], BPF_SK_SKB_STREAM_PARSER); bpf_prog_detach2(prog_fd[1], map_fd[0], BPF_SK_SKB_STREAM_VERDICT); + bpf_prog_detach2(prog_fd[0], map_fd[8], BPF_SK_SKB_STREAM_PARSER); + bpf_prog_detach2(prog_fd[2], map_fd[8], BPF_SK_SKB_STREAM_VERDICT); + if (tx_prog_fd >= 0) bpf_prog_detach2(tx_prog_fd, map_fd[1], BPF_SK_MSG_VERDICT); @@ -1229,8 +1310,10 @@ static void test_options(char *options) } if (txmsg_ingress) strncat(options, "ingress,", OPTSTRING); - if (txmsg_skb) - strncat(options, "skb,", OPTSTRING); + if (txmsg_redir_skb) + strncat(options, "redir_skb,", OPTSTRING); + if (txmsg_ktls_skb) + strncat(options, "ktls_skb,", OPTSTRING); if (ktls) strncat(options, "ktls,", OPTSTRING); if (peek_flag) @@ -1362,6 +1445,40 @@ static void test_txmsg_ingress_redir(int cgrp, struct sockmap_options *opt) test_send(opt, cgrp); } +static void test_txmsg_skb(int cgrp, struct sockmap_options *opt) +{ + bool data = opt->data_test; + int k = ktls; + + opt->data_test = true; + ktls = 1; + + txmsg_pass = txmsg_drop = 0; + txmsg_ingress = txmsg_redir = 0; + txmsg_ktls_skb = 1; + txmsg_pass = 1; + + /* Using data verification so ensure iov layout is + * expected from test receiver side. e.g. has enough + * bytes to write test code. + */ + opt->iov_length = 100; + opt->iov_count = 1; + opt->rate = 1; + test_exec(cgrp, opt); + + txmsg_ktls_skb_drop = 1; + test_exec(cgrp, opt); + + txmsg_ktls_skb_drop = 0; + txmsg_ktls_skb_redir = 1; + test_exec(cgrp, opt); + + opt->data_test = data; + ktls = k; +} + + /* Test cork with hung data. This tests poor usage patterns where * cork can leave data on the ring if user program is buggy and * doesn't flush them somehow. They do take some time however @@ -1542,11 +1659,13 @@ char *map_names[] = { "sock_bytes", "sock_redir_flags", "sock_skb_opts", + "tls_sock_map", }; int prog_attach_type[] = { BPF_SK_SKB_STREAM_PARSER, BPF_SK_SKB_STREAM_VERDICT, + BPF_SK_SKB_STREAM_VERDICT, BPF_CGROUP_SOCK_OPS, BPF_SK_MSG_VERDICT, BPF_SK_MSG_VERDICT, @@ -1560,6 +1679,7 @@ int prog_attach_type[] = { int prog_type[] = { BPF_PROG_TYPE_SK_SKB, BPF_PROG_TYPE_SK_SKB, + BPF_PROG_TYPE_SK_SKB, BPF_PROG_TYPE_SOCK_OPS, BPF_PROG_TYPE_SK_MSG, BPF_PROG_TYPE_SK_MSG, @@ -1620,6 +1740,7 @@ struct _test test[] = { {"txmsg test redirect", test_txmsg_redir}, {"txmsg test drop", test_txmsg_drop}, {"txmsg test ingress redirect", test_txmsg_ingress_redir}, + {"txmsg test skb", test_txmsg_skb}, {"txmsg test apply", test_txmsg_apply}, {"txmsg test cork", test_txmsg_cork}, {"txmsg test hanging corks", test_txmsg_cork_hangs}, diff --git a/tools/testing/selftests/bpf/verifier/and.c b/tools/testing/selftests/bpf/verifier/and.c index e0fad1548737..d781bc86e100 100644 --- a/tools/testing/selftests/bpf/verifier/and.c +++ b/tools/testing/selftests/bpf/verifier/and.c @@ -15,7 +15,7 @@ BPF_EXIT_INSN(), }, .fixup_map_hash_48b = { 3 }, - .errstr = "R0 max value is outside of the array range", + .errstr = "R0 max value is outside of the allowed memory range", .result = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, @@ -44,7 +44,7 @@ BPF_EXIT_INSN(), }, .fixup_map_hash_48b = { 3 }, - .errstr = "R0 max value is outside of the array range", + .errstr = "R0 max value is outside of the allowed memory range", .result = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, diff --git a/tools/testing/selftests/bpf/verifier/array_access.c b/tools/testing/selftests/bpf/verifier/array_access.c index f3c33e128709..1c4b1939f5a8 100644 --- a/tools/testing/selftests/bpf/verifier/array_access.c +++ b/tools/testing/selftests/bpf/verifier/array_access.c @@ -117,7 +117,7 @@ BPF_EXIT_INSN(), }, .fixup_map_hash_48b = { 3 }, - .errstr = "R0 min value is outside of the array range", + .errstr = "R0 min value is outside of the allowed memory range", .result = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, @@ -137,7 +137,7 @@ BPF_EXIT_INSN(), }, .fixup_map_hash_48b = { 3 }, - .errstr = "R0 unbounded memory access, make sure to bounds check any array access into a map", + .errstr = "R0 unbounded memory access, make sure to bounds check any such access", .result = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, diff --git a/tools/testing/selftests/bpf/verifier/bounds.c b/tools/testing/selftests/bpf/verifier/bounds.c index 58f4aa593b1b..4d6645f2874c 100644 --- a/tools/testing/selftests/bpf/verifier/bounds.c +++ b/tools/testing/selftests/bpf/verifier/bounds.c @@ -20,7 +20,7 @@ BPF_EXIT_INSN(), }, .fixup_map_hash_8b = { 3 }, - .errstr = "R0 max value is outside of the array range", + .errstr = "R0 max value is outside of the allowed memory range", .result = REJECT, }, { @@ -146,7 +146,7 @@ BPF_EXIT_INSN(), }, .fixup_map_hash_8b = { 3 }, - .errstr = "R0 min value is outside of the array range", + .errstr = "R0 min value is outside of the allowed memory range", .result = REJECT }, { @@ -354,7 +354,7 @@ BPF_EXIT_INSN(), }, .fixup_map_hash_8b = { 3 }, - .errstr = "R0 max value is outside of the array range", + .errstr = "R0 max value is outside of the allowed memory range", .result = REJECT }, { diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index 7629a0cebb9b..94258c6b5235 100644 --- a/tools/testing/selftests/bpf/verifier/calls.c +++ b/tools/testing/selftests/bpf/verifier/calls.c @@ -105,7 +105,7 @@ .prog_type = BPF_PROG_TYPE_SCHED_CLS, .fixup_map_hash_8b = { 16 }, .result = REJECT, - .errstr = "R0 min value is outside of the array range", + .errstr = "R0 min value is outside of the allowed memory range", }, { "calls: overlapping caller/callee", diff --git a/tools/testing/selftests/bpf/verifier/direct_value_access.c b/tools/testing/selftests/bpf/verifier/direct_value_access.c index b9fb28e8e224..988f46a1a4c7 100644 --- a/tools/testing/selftests/bpf/verifier/direct_value_access.c +++ b/tools/testing/selftests/bpf/verifier/direct_value_access.c @@ -68,7 +68,7 @@ }, .fixup_map_array_48b = { 1 }, .result = REJECT, - .errstr = "R1 min value is outside of the array range", + .errstr = "R1 min value is outside of the allowed memory range", }, { "direct map access, write test 7", @@ -220,7 +220,7 @@ }, .fixup_map_array_small = { 1 }, .result = REJECT, - .errstr = "R1 min value is outside of the array range", + .errstr = "R1 min value is outside of the allowed memory range", }, { "direct map access, write test 19", diff --git a/tools/testing/selftests/bpf/verifier/helper_access_var_len.c b/tools/testing/selftests/bpf/verifier/helper_access_var_len.c index 67ab12410050..5a605ae131a9 100644 --- a/tools/testing/selftests/bpf/verifier/helper_access_var_len.c +++ b/tools/testing/selftests/bpf/verifier/helper_access_var_len.c @@ -318,7 +318,7 @@ BPF_EXIT_INSN(), }, .fixup_map_hash_48b = { 4 }, - .errstr = "R1 min value is outside of the array range", + .errstr = "R1 min value is outside of the allowed memory range", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, diff --git a/tools/testing/selftests/bpf/verifier/helper_value_access.c b/tools/testing/selftests/bpf/verifier/helper_value_access.c index 7572e403ddb9..961f28139b96 100644 --- a/tools/testing/selftests/bpf/verifier/helper_value_access.c +++ b/tools/testing/selftests/bpf/verifier/helper_value_access.c @@ -280,7 +280,7 @@ BPF_EXIT_INSN(), }, .fixup_map_hash_48b = { 3 }, - .errstr = "R1 min value is outside of the array range", + .errstr = "R1 min value is outside of the allowed memory range", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, @@ -415,7 +415,7 @@ BPF_EXIT_INSN(), }, .fixup_map_hash_48b = { 3 }, - .errstr = "R1 min value is outside of the array range", + .errstr = "R1 min value is outside of the allowed memory range", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, @@ -926,7 +926,7 @@ }, .fixup_map_hash_16b = { 3, 10 }, .result = REJECT, - .errstr = "R2 unbounded memory access, make sure to bounds check any array access into a map", + .errstr = "R2 unbounded memory access, make sure to bounds check any such access", .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, { diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c index a53d99cebd9f..97ee658e1242 100644 --- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c +++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c @@ -50,7 +50,7 @@ .fixup_map_array_48b = { 8 }, .result = ACCEPT, .result_unpriv = REJECT, - .errstr_unpriv = "R0 min value is outside of the array range", + .errstr_unpriv = "R0 min value is outside of the allowed memory range", .retval = 1, }, { @@ -325,7 +325,7 @@ }, .fixup_map_array_48b = { 3 }, .result = REJECT, - .errstr = "R0 min value is outside of the array range", + .errstr = "R0 min value is outside of the allowed memory range", .result_unpriv = REJECT, .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", }, @@ -601,7 +601,7 @@ }, .fixup_map_array_48b = { 3 }, .result = REJECT, - .errstr = "R1 max value is outside of the array range", + .errstr = "R1 max value is outside of the allowed memory range", .errstr_unpriv = "R1 pointer arithmetic of map value goes out of range", .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, @@ -726,7 +726,7 @@ }, .fixup_map_array_48b = { 3 }, .result = REJECT, - .errstr = "R0 min value is outside of the array range", + .errstr = "R0 min value is outside of the allowed memory range", }, { "map access: value_ptr -= known scalar, 2", |