diff options
Diffstat (limited to 'tools')
78 files changed, 4011 insertions, 600 deletions
diff --git a/tools/bpf/bpftool/Documentation/bpftool-gen.rst b/tools/bpf/bpftool/Documentation/bpftool-gen.rst index 18d646b571ec..68454ef28f58 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-gen.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-gen.rst @@ -25,6 +25,7 @@ GEN COMMANDS | **bpftool** **gen object** *OUTPUT_FILE* *INPUT_FILE* [*INPUT_FILE*...] | **bpftool** **gen skeleton** *FILE* [**name** *OBJECT_NAME*] +| **bpftool** **gen subskeleton** *FILE* [**name** *OBJECT_NAME*] | **bpftool** **gen min_core_btf** *INPUT* *OUTPUT* *OBJECT* [*OBJECT*...] | **bpftool** **gen help** @@ -150,6 +151,30 @@ DESCRIPTION (non-read-only) data from userspace, with same simplicity as for BPF side. + **bpftool gen subskeleton** *FILE* + Generate BPF subskeleton C header file for a given *FILE*. + + Subskeletons are similar to skeletons, except they do not own + the corresponding maps, programs, or global variables. They + require that the object file used to generate them is already + loaded into a *bpf_object* by some other means. + + This functionality is useful when a library is included into a + larger BPF program. A subskeleton for the library would have + access to all objects and globals defined in it, without + having to know about the larger program. + + Consequently, there are only two functions defined + for subskeletons: + + - **example__open(bpf_object\*)** + Instantiates a subskeleton from an already opened (but not + necessarily loaded) **bpf_object**. + + - **example__destroy()** + Frees the storage for the subskeleton but *does not* unload + any BPF programs or maps. + **bpftool** **gen min_core_btf** *INPUT* *OUTPUT* *OBJECT* [*OBJECT*...] Generate a minimum BTF file as *OUTPUT*, derived from a given *INPUT* BTF file, containing all needed BTF types so one, or diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst index 7084dd9fa2f8..6965c94dfdaf 100644 --- a/tools/bpf/bpftool/Documentation/bpftool.rst +++ b/tools/bpf/bpftool/Documentation/bpftool.rst @@ -20,7 +20,8 @@ SYNOPSIS **bpftool** **version** - *OBJECT* := { **map** | **program** | **cgroup** | **perf** | **net** | **feature** } + *OBJECT* := { **map** | **program** | **link** | **cgroup** | **perf** | **net** | **feature** | + **btf** | **gen** | **struct_ops** | **iter** } *OPTIONS* := { { **-V** | **--version** } | |COMMON_OPTIONS| } @@ -31,6 +32,8 @@ SYNOPSIS *PROG-COMMANDS* := { **show** | **list** | **dump jited** | **dump xlated** | **pin** | **load** | **attach** | **detach** | **help** } + *LINK-COMMANDS* := { **show** | **list** | **pin** | **detach** | **help** } + *CGROUP-COMMANDS* := { **show** | **list** | **attach** | **detach** | **help** } *PERF-COMMANDS* := { **show** | **list** | **help** } @@ -39,6 +42,14 @@ SYNOPSIS *FEATURE-COMMANDS* := { **probe** | **help** } + *BTF-COMMANDS* := { **show** | **list** | **dump** | **help** } + + *GEN-COMMANDS* := { **object** | **skeleton** | **min_core_btf** | **help** } + + *STRUCT-OPS-COMMANDS* := { **show** | **list** | **dump** | **register** | **unregister** | **help** } + + *ITER-COMMANDS* := { **pin** | **help** } + DESCRIPTION =========== *bpftool* allows for inspection and simple modification of BPF objects diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index 958e1fd71b5c..5df8d72c5179 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -1003,13 +1003,25 @@ _bpftool() ;; esac ;; + subskeleton) + case $prev in + $command) + _filedir + return 0 + ;; + *) + _bpftool_once_attr 'name' + return 0 + ;; + esac + ;; min_core_btf) _filedir return 0 ;; *) [[ $prev == $object ]] && \ - COMPREPLY=( $( compgen -W 'object skeleton help min_core_btf' -- "$cur" ) ) + COMPREPLY=( $( compgen -W 'object skeleton subskeleton help min_core_btf' -- "$cur" ) ) ;; esac ;; diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 606743c6db41..0c1e06cf50b9 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -56,7 +56,6 @@ const char * const attach_type_name[__MAX_BPF_ATTACH_TYPE] = { [BPF_CGROUP_UDP6_RECVMSG] = "recvmsg6", [BPF_CGROUP_GETSOCKOPT] = "getsockopt", [BPF_CGROUP_SETSOCKOPT] = "setsockopt", - [BPF_SK_SKB_STREAM_PARSER] = "sk_skb_stream_parser", [BPF_SK_SKB_STREAM_VERDICT] = "sk_skb_stream_verdict", [BPF_SK_SKB_VERDICT] = "sk_skb_verdict", @@ -76,6 +75,7 @@ const char * const attach_type_name[__MAX_BPF_ATTACH_TYPE] = { [BPF_SK_REUSEPORT_SELECT] = "sk_skb_reuseport_select", [BPF_SK_REUSEPORT_SELECT_OR_MIGRATE] = "sk_skb_reuseport_select_or_migrate", [BPF_PERF_EVENT] = "perf_event", + [BPF_TRACE_KPROBE_MULTI] = "trace_kprobe_multi", }; void p_err(const char *fmt, ...) diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index 9c894b1447de..c2f43a5d38e0 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -3,6 +3,7 @@ #include <ctype.h> #include <errno.h> +#include <fcntl.h> #include <string.h> #include <unistd.h> #include <net/if.h> @@ -45,6 +46,11 @@ static bool run_as_unprivileged; /* Miscellaneous utility functions */ +static bool grep(const char *buffer, const char *pattern) +{ + return !!strstr(buffer, pattern); +} + static bool check_procfs(void) { struct statfs st_fs; @@ -135,6 +141,32 @@ static void print_end_section(void) /* Probing functions */ +static int get_vendor_id(int ifindex) +{ + char ifname[IF_NAMESIZE], path[64], buf[8]; + ssize_t len; + int fd; + + if (!if_indextoname(ifindex, ifname)) + return -1; + + snprintf(path, sizeof(path), "/sys/class/net/%s/device/vendor", ifname); + + fd = open(path, O_RDONLY | O_CLOEXEC); + if (fd < 0) + return -1; + + len = read(fd, buf, sizeof(buf)); + close(fd); + if (len < 0) + return -1; + if (len >= (ssize_t)sizeof(buf)) + return -1; + buf[len] = '\0'; + + return strtol(buf, NULL, 0); +} + static int read_procfs(const char *path) { char *endptr, *line = NULL; @@ -478,6 +510,40 @@ static bool probe_bpf_syscall(const char *define_prefix) return res; } +static bool +probe_prog_load_ifindex(enum bpf_prog_type prog_type, + const struct bpf_insn *insns, size_t insns_cnt, + char *log_buf, size_t log_buf_sz, + __u32 ifindex) +{ + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .log_buf = log_buf, + .log_size = log_buf_sz, + .log_level = log_buf ? 1 : 0, + .prog_ifindex = ifindex, + ); + int fd; + + errno = 0; + fd = bpf_prog_load(prog_type, NULL, "GPL", insns, insns_cnt, &opts); + if (fd >= 0) + close(fd); + + return fd >= 0 && errno != EINVAL && errno != EOPNOTSUPP; +} + +static bool probe_prog_type_ifindex(enum bpf_prog_type prog_type, __u32 ifindex) +{ + /* nfp returns -EINVAL on exit(0) with TC offload */ + struct bpf_insn insns[2] = { + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_EXIT_INSN() + }; + + return probe_prog_load_ifindex(prog_type, insns, ARRAY_SIZE(insns), + NULL, 0, ifindex); +} + static void probe_prog_type(enum bpf_prog_type prog_type, bool *supported_types, const char *define_prefix, __u32 ifindex) @@ -488,11 +554,19 @@ probe_prog_type(enum bpf_prog_type prog_type, bool *supported_types, bool res; if (ifindex) { - p_info("BPF offload feature probing is not supported"); - return; + switch (prog_type) { + case BPF_PROG_TYPE_SCHED_CLS: + case BPF_PROG_TYPE_XDP: + break; + default: + return; + } + + res = probe_prog_type_ifindex(prog_type, ifindex); + } else { + res = libbpf_probe_bpf_prog_type(prog_type, NULL); } - res = libbpf_probe_bpf_prog_type(prog_type, NULL); #ifdef USE_LIBCAP /* Probe may succeed even if program load fails, for unprivileged users * check that we did not fail because of insufficient permissions @@ -521,6 +595,26 @@ probe_prog_type(enum bpf_prog_type prog_type, bool *supported_types, define_prefix); } +static bool probe_map_type_ifindex(enum bpf_map_type map_type, __u32 ifindex) +{ + LIBBPF_OPTS(bpf_map_create_opts, opts); + int key_size, value_size, max_entries; + int fd; + + opts.map_ifindex = ifindex; + + key_size = sizeof(__u32); + value_size = sizeof(__u32); + max_entries = 1; + + fd = bpf_map_create(map_type, NULL, key_size, value_size, max_entries, + &opts); + if (fd >= 0) + close(fd); + + return fd >= 0; +} + static void probe_map_type(enum bpf_map_type map_type, const char *define_prefix, __u32 ifindex) @@ -531,11 +625,18 @@ probe_map_type(enum bpf_map_type map_type, const char *define_prefix, bool res; if (ifindex) { - p_info("BPF offload feature probing is not supported"); - return; - } + switch (map_type) { + case BPF_MAP_TYPE_HASH: + case BPF_MAP_TYPE_ARRAY: + break; + default: + return; + } - res = libbpf_probe_bpf_map_type(map_type, NULL); + res = probe_map_type_ifindex(map_type, ifindex); + } else { + res = libbpf_probe_bpf_map_type(map_type, NULL); + } /* Probe result depends on the success of map creation, no additional * check required for unprivileged users @@ -559,6 +660,33 @@ probe_map_type(enum bpf_map_type map_type, const char *define_prefix, define_prefix); } +static bool +probe_helper_ifindex(enum bpf_func_id id, enum bpf_prog_type prog_type, + __u32 ifindex) +{ + struct bpf_insn insns[2] = { + BPF_EMIT_CALL(id), + BPF_EXIT_INSN() + }; + char buf[4096] = {}; + bool res; + + probe_prog_load_ifindex(prog_type, insns, ARRAY_SIZE(insns), buf, + sizeof(buf), ifindex); + res = !grep(buf, "invalid func ") && !grep(buf, "unknown func "); + + switch (get_vendor_id(ifindex)) { + case 0x19ee: /* Netronome specific */ + res = res && !grep(buf, "not supported by FW") && + !grep(buf, "unsupported function id"); + break; + default: + break; + } + + return res; +} + static void probe_helper_for_progtype(enum bpf_prog_type prog_type, bool supported_type, const char *define_prefix, unsigned int id, @@ -567,12 +695,10 @@ probe_helper_for_progtype(enum bpf_prog_type prog_type, bool supported_type, bool res = false; if (supported_type) { - if (ifindex) { - p_info("BPF offload feature probing is not supported"); - return; - } - - res = libbpf_probe_bpf_helper(prog_type, id, NULL); + if (ifindex) + res = probe_helper_ifindex(id, prog_type, ifindex); + else + res = libbpf_probe_bpf_helper(prog_type, id, NULL); #ifdef USE_LIBCAP /* Probe may succeed even if program load fails, for * unprivileged users check that we did not fail because of diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c index 145734b4fe41..7ba7ff55d2ea 100644 --- a/tools/bpf/bpftool/gen.c +++ b/tools/bpf/bpftool/gen.c @@ -64,11 +64,11 @@ static void get_obj_name(char *name, const char *file) sanitize_identifier(name); } -static void get_header_guard(char *guard, const char *obj_name) +static void get_header_guard(char *guard, const char *obj_name, const char *suffix) { int i; - sprintf(guard, "__%s_SKEL_H__", obj_name); + sprintf(guard, "__%s_%s__", obj_name, suffix); for (i = 0; guard[i]; i++) guard[i] = toupper(guard[i]); } @@ -231,6 +231,17 @@ static const struct btf_type *find_type_for_map(struct btf *btf, const char *map return NULL; } +static bool is_internal_mmapable_map(const struct bpf_map *map, char *buf, size_t sz) +{ + if (!bpf_map__is_internal(map) || !(bpf_map__map_flags(map) & BPF_F_MMAPABLE)) + return false; + + if (!get_map_ident(map, buf, sz)) + return false; + + return true; +} + static int codegen_datasecs(struct bpf_object *obj, const char *obj_name) { struct btf *btf = bpf_object__btf(obj); @@ -247,12 +258,7 @@ static int codegen_datasecs(struct bpf_object *obj, const char *obj_name) bpf_object__for_each_map(map, obj) { /* only generate definitions for memory-mapped internal maps */ - if (!bpf_map__is_internal(map)) - continue; - if (!(bpf_map__map_flags(map) & BPF_F_MMAPABLE)) - continue; - - if (!get_map_ident(map, map_ident, sizeof(map_ident))) + if (!is_internal_mmapable_map(map, map_ident, sizeof(map_ident))) continue; sec = find_type_for_map(btf, map_ident); @@ -280,6 +286,96 @@ out: return err; } +static bool btf_is_ptr_to_func_proto(const struct btf *btf, + const struct btf_type *v) +{ + return btf_is_ptr(v) && btf_is_func_proto(btf__type_by_id(btf, v->type)); +} + +static int codegen_subskel_datasecs(struct bpf_object *obj, const char *obj_name) +{ + struct btf *btf = bpf_object__btf(obj); + struct btf_dump *d; + struct bpf_map *map; + const struct btf_type *sec, *var; + const struct btf_var_secinfo *sec_var; + int i, err = 0, vlen; + char map_ident[256], sec_ident[256]; + bool strip_mods = false, needs_typeof = false; + const char *sec_name, *var_name; + __u32 var_type_id; + + d = btf_dump__new(btf, codegen_btf_dump_printf, NULL, NULL); + if (!d) + return -errno; + + bpf_object__for_each_map(map, obj) { + /* only generate definitions for memory-mapped internal maps */ + if (!is_internal_mmapable_map(map, map_ident, sizeof(map_ident))) + continue; + + sec = find_type_for_map(btf, map_ident); + if (!sec) + continue; + + sec_name = btf__name_by_offset(btf, sec->name_off); + if (!get_datasec_ident(sec_name, sec_ident, sizeof(sec_ident))) + continue; + + strip_mods = strcmp(sec_name, ".kconfig") != 0; + printf(" struct %s__%s {\n", obj_name, sec_ident); + + sec_var = btf_var_secinfos(sec); + vlen = btf_vlen(sec); + for (i = 0; i < vlen; i++, sec_var++) { + DECLARE_LIBBPF_OPTS(btf_dump_emit_type_decl_opts, opts, + .indent_level = 2, + .strip_mods = strip_mods, + /* we'll print the name separately */ + .field_name = "", + ); + + var = btf__type_by_id(btf, sec_var->type); + var_name = btf__name_by_offset(btf, var->name_off); + var_type_id = var->type; + + /* static variables are not exposed through BPF skeleton */ + if (btf_var(var)->linkage == BTF_VAR_STATIC) + continue; + + /* The datasec member has KIND_VAR but we want the + * underlying type of the variable (e.g. KIND_INT). + */ + var = skip_mods_and_typedefs(btf, var->type, NULL); + + printf("\t\t"); + /* Func and array members require special handling. + * Instead of producing `typename *var`, they produce + * `typeof(typename) *var`. This allows us to keep a + * similar syntax where the identifier is just prefixed + * by *, allowing us to ignore C declaration minutiae. + */ + needs_typeof = btf_is_array(var) || btf_is_ptr_to_func_proto(btf, var); + if (needs_typeof) + printf("typeof("); + + err = btf_dump__emit_type_decl(d, var_type_id, &opts); + if (err) + goto out; + + if (needs_typeof) + printf(")"); + + printf(" *%s;\n", var_name); + } + printf(" } %s;\n", sec_ident); + } + +out: + btf_dump__free(d); + return err; +} + static void codegen(const char *template, ...) { const char *src, *end; @@ -389,11 +485,7 @@ static void codegen_asserts(struct bpf_object *obj, const char *obj_name) ", obj_name); bpf_object__for_each_map(map, obj) { - if (!bpf_map__is_internal(map)) - continue; - if (!(bpf_map__map_flags(map) & BPF_F_MMAPABLE)) - continue; - if (!get_map_ident(map, map_ident, sizeof(map_ident))) + if (!is_internal_mmapable_map(map, map_ident, sizeof(map_ident))) continue; sec = find_type_for_map(btf, map_ident); @@ -608,11 +700,7 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h const void *mmap_data = NULL; size_t mmap_size = 0; - if (!get_map_ident(map, ident, sizeof(ident))) - continue; - - if (!bpf_map__is_internal(map) || - !(bpf_map__map_flags(map) & BPF_F_MMAPABLE)) + if (!is_internal_mmapable_map(map, ident, sizeof(ident))) continue; codegen("\ @@ -671,11 +759,7 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h bpf_object__for_each_map(map, obj) { const char *mmap_flags; - if (!get_map_ident(map, ident, sizeof(ident))) - continue; - - if (!bpf_map__is_internal(map) || - !(bpf_map__map_flags(map) & BPF_F_MMAPABLE)) + if (!is_internal_mmapable_map(map, ident, sizeof(ident))) continue; if (bpf_map__map_flags(map) & BPF_F_RDONLY_PROG) @@ -727,10 +811,95 @@ out: return err; } +static void +codegen_maps_skeleton(struct bpf_object *obj, size_t map_cnt, bool mmaped) +{ + struct bpf_map *map; + char ident[256]; + size_t i; + + if (!map_cnt) + return; + + codegen("\ + \n\ + \n\ + /* maps */ \n\ + s->map_cnt = %zu; \n\ + s->map_skel_sz = sizeof(*s->maps); \n\ + s->maps = (struct bpf_map_skeleton *)calloc(s->map_cnt, s->map_skel_sz);\n\ + if (!s->maps) \n\ + goto err; \n\ + ", + map_cnt + ); + i = 0; + bpf_object__for_each_map(map, obj) { + if (!get_map_ident(map, ident, sizeof(ident))) + continue; + + codegen("\ + \n\ + \n\ + s->maps[%zu].name = \"%s\"; \n\ + s->maps[%zu].map = &obj->maps.%s; \n\ + ", + i, bpf_map__name(map), i, ident); + /* memory-mapped internal maps */ + if (mmaped && is_internal_mmapable_map(map, ident, sizeof(ident))) { + printf("\ts->maps[%zu].mmaped = (void **)&obj->%s;\n", + i, ident); + } + i++; + } +} + +static void +codegen_progs_skeleton(struct bpf_object *obj, size_t prog_cnt, bool populate_links) +{ + struct bpf_program *prog; + int i; + + if (!prog_cnt) + return; + + codegen("\ + \n\ + \n\ + /* programs */ \n\ + s->prog_cnt = %zu; \n\ + s->prog_skel_sz = sizeof(*s->progs); \n\ + s->progs = (struct bpf_prog_skeleton *)calloc(s->prog_cnt, s->prog_skel_sz);\n\ + if (!s->progs) \n\ + goto err; \n\ + ", + prog_cnt + ); + i = 0; + bpf_object__for_each_program(prog, obj) { + codegen("\ + \n\ + \n\ + s->progs[%1$zu].name = \"%2$s\"; \n\ + s->progs[%1$zu].prog = &obj->progs.%2$s;\n\ + ", + i, bpf_program__name(prog)); + + if (populate_links) { + codegen("\ + \n\ + s->progs[%1$zu].link = &obj->links.%2$s;\n\ + ", + i, bpf_program__name(prog)); + } + i++; + } +} + static int do_skeleton(int argc, char **argv) { char header_guard[MAX_OBJ_NAME_LEN + sizeof("__SKEL_H__")]; - size_t i, map_cnt = 0, prog_cnt = 0, file_sz, mmap_sz; + size_t map_cnt = 0, prog_cnt = 0, file_sz, mmap_sz; DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts); char obj_name[MAX_OBJ_NAME_LEN] = "", *obj_data; struct bpf_object *obj = NULL; @@ -821,7 +990,7 @@ static int do_skeleton(int argc, char **argv) prog_cnt++; } - get_header_guard(header_guard, obj_name); + get_header_guard(header_guard, obj_name, "SKEL_H"); if (use_loader) { codegen("\ \n\ @@ -1024,66 +1193,10 @@ static int do_skeleton(int argc, char **argv) ", obj_name ); - if (map_cnt) { - codegen("\ - \n\ - \n\ - /* maps */ \n\ - s->map_cnt = %zu; \n\ - s->map_skel_sz = sizeof(*s->maps); \n\ - s->maps = (struct bpf_map_skeleton *)calloc(s->map_cnt, s->map_skel_sz);\n\ - if (!s->maps) \n\ - goto err; \n\ - ", - map_cnt - ); - i = 0; - bpf_object__for_each_map(map, obj) { - if (!get_map_ident(map, ident, sizeof(ident))) - continue; - codegen("\ - \n\ - \n\ - s->maps[%zu].name = \"%s\"; \n\ - s->maps[%zu].map = &obj->maps.%s; \n\ - ", - i, bpf_map__name(map), i, ident); - /* memory-mapped internal maps */ - if (bpf_map__is_internal(map) && - (bpf_map__map_flags(map) & BPF_F_MMAPABLE)) { - printf("\ts->maps[%zu].mmaped = (void **)&obj->%s;\n", - i, ident); - } - i++; - } - } - if (prog_cnt) { - codegen("\ - \n\ - \n\ - /* programs */ \n\ - s->prog_cnt = %zu; \n\ - s->prog_skel_sz = sizeof(*s->progs); \n\ - s->progs = (struct bpf_prog_skeleton *)calloc(s->prog_cnt, s->prog_skel_sz);\n\ - if (!s->progs) \n\ - goto err; \n\ - ", - prog_cnt - ); - i = 0; - bpf_object__for_each_program(prog, obj) { - codegen("\ - \n\ - \n\ - s->progs[%1$zu].name = \"%2$s\"; \n\ - s->progs[%1$zu].prog = &obj->progs.%2$s;\n\ - s->progs[%1$zu].link = &obj->links.%2$s;\n\ - ", - i, bpf_program__name(prog)); - i++; - } - } + codegen_maps_skeleton(obj, map_cnt, true /*mmaped*/); + codegen_progs_skeleton(obj, prog_cnt, true /*populate_links*/); + codegen("\ \n\ \n\ @@ -1141,6 +1254,310 @@ out: return err; } +/* Subskeletons are like skeletons, except they don't own the bpf_object, + * associated maps, links, etc. Instead, they know about the existence of + * variables, maps, programs and are able to find their locations + * _at runtime_ from an already loaded bpf_object. + * + * This allows for library-like BPF objects to have userspace counterparts + * with access to their own items without having to know anything about the + * final BPF object that the library was linked into. + */ +static int do_subskeleton(int argc, char **argv) +{ + char header_guard[MAX_OBJ_NAME_LEN + sizeof("__SUBSKEL_H__")]; + size_t i, len, file_sz, map_cnt = 0, prog_cnt = 0, mmap_sz, var_cnt = 0, var_idx = 0; + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts); + char obj_name[MAX_OBJ_NAME_LEN] = "", *obj_data; + struct bpf_object *obj = NULL; + const char *file, *var_name; + char ident[256]; + int fd, err = -1, map_type_id; + const struct bpf_map *map; + struct bpf_program *prog; + struct btf *btf; + const struct btf_type *map_type, *var_type; + const struct btf_var_secinfo *var; + struct stat st; + + if (!REQ_ARGS(1)) { + usage(); + return -1; + } + file = GET_ARG(); + + while (argc) { + if (!REQ_ARGS(2)) + return -1; + + if (is_prefix(*argv, "name")) { + NEXT_ARG(); + + if (obj_name[0] != '\0') { + p_err("object name already specified"); + return -1; + } + + strncpy(obj_name, *argv, MAX_OBJ_NAME_LEN - 1); + obj_name[MAX_OBJ_NAME_LEN - 1] = '\0'; + } else { + p_err("unknown arg %s", *argv); + return -1; + } + + NEXT_ARG(); + } + + if (argc) { + p_err("extra unknown arguments"); + return -1; + } + + if (use_loader) { + p_err("cannot use loader for subskeletons"); + return -1; + } + + if (stat(file, &st)) { + p_err("failed to stat() %s: %s", file, strerror(errno)); + return -1; + } + file_sz = st.st_size; + mmap_sz = roundup(file_sz, sysconf(_SC_PAGE_SIZE)); + fd = open(file, O_RDONLY); + if (fd < 0) { + p_err("failed to open() %s: %s", file, strerror(errno)); + return -1; + } + obj_data = mmap(NULL, mmap_sz, PROT_READ, MAP_PRIVATE, fd, 0); + if (obj_data == MAP_FAILED) { + obj_data = NULL; + p_err("failed to mmap() %s: %s", file, strerror(errno)); + goto out; + } + if (obj_name[0] == '\0') + get_obj_name(obj_name, file); + + /* The empty object name allows us to use bpf_map__name and produce + * ELF section names out of it. (".data" instead of "obj.data") + */ + opts.object_name = ""; + obj = bpf_object__open_mem(obj_data, file_sz, &opts); + if (!obj) { + char err_buf[256]; + + libbpf_strerror(errno, err_buf, sizeof(err_buf)); + p_err("failed to open BPF object file: %s", err_buf); + obj = NULL; + goto out; + } + + btf = bpf_object__btf(obj); + if (!btf) { + err = -1; + p_err("need btf type information for %s", obj_name); + goto out; + } + + bpf_object__for_each_program(prog, obj) { + prog_cnt++; + } + + /* First, count how many variables we have to find. + * We need this in advance so the subskel can allocate the right + * amount of storage. + */ + bpf_object__for_each_map(map, obj) { + if (!get_map_ident(map, ident, sizeof(ident))) + continue; + + /* Also count all maps that have a name */ + map_cnt++; + + if (!is_internal_mmapable_map(map, ident, sizeof(ident))) + continue; + + map_type_id = bpf_map__btf_value_type_id(map); + if (map_type_id <= 0) { + err = map_type_id; + goto out; + } + map_type = btf__type_by_id(btf, map_type_id); + + var = btf_var_secinfos(map_type); + len = btf_vlen(map_type); + for (i = 0; i < len; i++, var++) { + var_type = btf__type_by_id(btf, var->type); + + if (btf_var(var_type)->linkage == BTF_VAR_STATIC) + continue; + + var_cnt++; + } + } + + get_header_guard(header_guard, obj_name, "SUBSKEL_H"); + codegen("\ + \n\ + /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ \n\ + \n\ + /* THIS FILE IS AUTOGENERATED! */ \n\ + #ifndef %2$s \n\ + #define %2$s \n\ + \n\ + #include <errno.h> \n\ + #include <stdlib.h> \n\ + #include <bpf/libbpf.h> \n\ + \n\ + struct %1$s { \n\ + struct bpf_object *obj; \n\ + struct bpf_object_subskeleton *subskel; \n\ + ", obj_name, header_guard); + + if (map_cnt) { + printf("\tstruct {\n"); + bpf_object__for_each_map(map, obj) { + if (!get_map_ident(map, ident, sizeof(ident))) + continue; + printf("\t\tstruct bpf_map *%s;\n", ident); + } + printf("\t} maps;\n"); + } + + if (prog_cnt) { + printf("\tstruct {\n"); + bpf_object__for_each_program(prog, obj) { + printf("\t\tstruct bpf_program *%s;\n", + bpf_program__name(prog)); + } + printf("\t} progs;\n"); + } + + err = codegen_subskel_datasecs(obj, obj_name); + if (err) + goto out; + + /* emit code that will allocate enough storage for all symbols */ + codegen("\ + \n\ + \n\ + #ifdef __cplusplus \n\ + static inline struct %1$s *open(const struct bpf_object *src);\n\ + static inline void destroy(struct %1$s *skel); \n\ + #endif /* __cplusplus */ \n\ + }; \n\ + \n\ + static inline void \n\ + %1$s__destroy(struct %1$s *skel) \n\ + { \n\ + if (!skel) \n\ + return; \n\ + if (skel->subskel) \n\ + bpf_object__destroy_subskeleton(skel->subskel);\n\ + free(skel); \n\ + } \n\ + \n\ + static inline struct %1$s * \n\ + %1$s__open(const struct bpf_object *src) \n\ + { \n\ + struct %1$s *obj; \n\ + struct bpf_object_subskeleton *s; \n\ + int err; \n\ + \n\ + obj = (struct %1$s *)calloc(1, sizeof(*obj)); \n\ + if (!obj) { \n\ + errno = ENOMEM; \n\ + goto err; \n\ + } \n\ + s = (struct bpf_object_subskeleton *)calloc(1, sizeof(*s));\n\ + if (!s) { \n\ + errno = ENOMEM; \n\ + goto err; \n\ + } \n\ + s->sz = sizeof(*s); \n\ + s->obj = src; \n\ + s->var_skel_sz = sizeof(*s->vars); \n\ + obj->subskel = s; \n\ + \n\ + /* vars */ \n\ + s->var_cnt = %2$d; \n\ + s->vars = (struct bpf_var_skeleton *)calloc(%2$d, sizeof(*s->vars));\n\ + if (!s->vars) { \n\ + errno = ENOMEM; \n\ + goto err; \n\ + } \n\ + ", + obj_name, var_cnt + ); + + /* walk through each symbol and emit the runtime representation */ + bpf_object__for_each_map(map, obj) { + if (!is_internal_mmapable_map(map, ident, sizeof(ident))) + continue; + + map_type_id = bpf_map__btf_value_type_id(map); + if (map_type_id <= 0) + /* skip over internal maps with no type*/ + continue; + + map_type = btf__type_by_id(btf, map_type_id); + var = btf_var_secinfos(map_type); + len = btf_vlen(map_type); + for (i = 0; i < len; i++, var++) { + var_type = btf__type_by_id(btf, var->type); + var_name = btf__name_by_offset(btf, var_type->name_off); + + if (btf_var(var_type)->linkage == BTF_VAR_STATIC) + continue; + + /* Note that we use the dot prefix in .data as the + * field access operator i.e. maps%s becomes maps.data + */ + codegen("\ + \n\ + \n\ + s->vars[%3$d].name = \"%1$s\"; \n\ + s->vars[%3$d].map = &obj->maps.%2$s; \n\ + s->vars[%3$d].addr = (void **) &obj->%2$s.%1$s;\n\ + ", var_name, ident, var_idx); + + var_idx++; + } + } + + codegen_maps_skeleton(obj, map_cnt, false /*mmaped*/); + codegen_progs_skeleton(obj, prog_cnt, false /*links*/); + + codegen("\ + \n\ + \n\ + err = bpf_object__open_subskeleton(s); \n\ + if (err) \n\ + goto err; \n\ + \n\ + return obj; \n\ + err: \n\ + %1$s__destroy(obj); \n\ + return NULL; \n\ + } \n\ + \n\ + #ifdef __cplusplus \n\ + struct %1$s *%1$s::open(const struct bpf_object *src) { return %1$s__open(src); }\n\ + void %1$s::destroy(struct %1$s *skel) { %1$s__destroy(skel); }\n\ + #endif /* __cplusplus */ \n\ + \n\ + #endif /* %2$s */ \n\ + ", + obj_name, header_guard); + err = 0; +out: + bpf_object__close(obj); + if (obj_data) + munmap(obj_data, mmap_sz); + close(fd); + return err; +} + static int do_object(int argc, char **argv) { struct bpf_linker *linker; @@ -1192,6 +1609,7 @@ static int do_help(int argc, char **argv) fprintf(stderr, "Usage: %1$s %2$s object OUTPUT_FILE INPUT_FILE [INPUT_FILE...]\n" " %1$s %2$s skeleton FILE [name OBJECT_NAME]\n" + " %1$s %2$s subskeleton FILE [name OBJECT_NAME]\n" " %1$s %2$s min_core_btf INPUT OUTPUT OBJECT [OBJECT...]\n" " %1$s %2$s help\n" "\n" @@ -1788,6 +2206,7 @@ static int do_min_core_btf(int argc, char **argv) static const struct cmd cmds[] = { { "object", do_object }, { "skeleton", do_skeleton }, + { "subskeleton", do_subskeleton }, { "min_core_btf", do_min_core_btf}, { "help", do_help }, { 0 } diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 0468e5b24bd4..6e9277ffc68c 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -113,7 +113,9 @@ struct obj_ref { struct obj_refs { int ref_cnt; + bool has_bpf_cookie; struct obj_ref *refs; + __u64 bpf_cookie; }; struct btf; diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index e746642de292..c26378f20831 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -504,7 +504,7 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) jsonw_uint_field(json_wtr, "max_entries", info->max_entries); if (memlock) - jsonw_int_field(json_wtr, "bytes_memlock", atoi(memlock)); + jsonw_int_field(json_wtr, "bytes_memlock", atoll(memlock)); free(memlock); if (info->type == BPF_MAP_TYPE_PROG_ARRAY) { @@ -620,17 +620,14 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) u32_as_hash_field(info->id)) printf("\n\tpinned %s", (char *)entry->value); } - printf("\n"); if (frozen_str) { frozen = atoi(frozen_str); free(frozen_str); } - if (!info->btf_id && !frozen) - return 0; - - printf("\t"); + if (info->btf_id || frozen) + printf("\n\t"); if (info->btf_id) printf("btf_id %d", info->btf_id); diff --git a/tools/bpf/bpftool/pids.c b/tools/bpf/bpftool/pids.c index 7c384d10e95f..bb6c969a114a 100644 --- a/tools/bpf/bpftool/pids.c +++ b/tools/bpf/bpftool/pids.c @@ -78,6 +78,8 @@ static void add_ref(struct hashmap *map, struct pid_iter_entry *e) ref->pid = e->pid; memcpy(ref->comm, e->comm, sizeof(ref->comm)); refs->ref_cnt = 1; + refs->has_bpf_cookie = e->has_bpf_cookie; + refs->bpf_cookie = e->bpf_cookie; err = hashmap__append(map, u32_as_hash_field(e->id), refs); if (err) @@ -205,6 +207,9 @@ void emit_obj_refs_json(struct hashmap *map, __u32 id, if (refs->ref_cnt == 0) break; + if (refs->has_bpf_cookie) + jsonw_lluint_field(json_writer, "bpf_cookie", refs->bpf_cookie); + jsonw_name(json_writer, "pids"); jsonw_start_array(json_writer); for (i = 0; i < refs->ref_cnt; i++) { @@ -234,6 +239,9 @@ void emit_obj_refs_plain(struct hashmap *map, __u32 id, const char *prefix) if (refs->ref_cnt == 0) break; + if (refs->has_bpf_cookie) + printf("\n\tbpf_cookie %llu", (unsigned long long) refs->bpf_cookie); + printf("%s", prefix); for (i = 0; i < refs->ref_cnt; i++) { struct obj_ref *ref = &refs->refs[i]; diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 8a52eed19fa2..bc4e05542c2b 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -485,7 +485,7 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) memlock = get_fdinfo(fd, "memlock"); if (memlock) - jsonw_int_field(json_wtr, "bytes_memlock", atoi(memlock)); + jsonw_int_field(json_wtr, "bytes_memlock", atoll(memlock)); free(memlock); if (info->nr_map_ids) diff --git a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c index f70702fcb224..eb05ea53afb1 100644 --- a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c +++ b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c @@ -38,6 +38,17 @@ static __always_inline __u32 get_obj_id(void *ent, enum bpf_obj_type type) } } +/* could be used only with BPF_LINK_TYPE_PERF_EVENT links */ +static __u64 get_bpf_cookie(struct bpf_link *link) +{ + struct bpf_perf_link *perf_link; + struct perf_event *event; + + perf_link = container_of(link, struct bpf_perf_link, link); + event = BPF_CORE_READ(perf_link, perf_file, private_data); + return BPF_CORE_READ(event, bpf_cookie); +} + SEC("iter/task_file") int iter(struct bpf_iter__task_file *ctx) { @@ -69,8 +80,19 @@ int iter(struct bpf_iter__task_file *ctx) if (file->f_op != fops) return 0; + __builtin_memset(&e, 0, sizeof(e)); e.pid = task->tgid; e.id = get_obj_id(file->private_data, obj_type); + + if (obj_type == BPF_OBJ_LINK) { + struct bpf_link *link = (struct bpf_link *) file->private_data; + + if (BPF_CORE_READ(link, type) == BPF_LINK_TYPE_PERF_EVENT) { + e.has_bpf_cookie = true; + e.bpf_cookie = get_bpf_cookie(link); + } + } + bpf_probe_read_kernel_str(&e.comm, sizeof(e.comm), task->group_leader->comm); bpf_seq_write(ctx->meta->seq, &e, sizeof(e)); diff --git a/tools/bpf/bpftool/skeleton/pid_iter.h b/tools/bpf/bpftool/skeleton/pid_iter.h index 5692cf257adb..bbb570d4cca6 100644 --- a/tools/bpf/bpftool/skeleton/pid_iter.h +++ b/tools/bpf/bpftool/skeleton/pid_iter.h @@ -6,6 +6,8 @@ struct pid_iter_entry { __u32 id; int pid; + __u64 bpf_cookie; + bool has_bpf_cookie; char comm[16]; }; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 4eebea830613..7604e7d5438f 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -997,6 +997,7 @@ enum bpf_attach_type { BPF_SK_REUSEPORT_SELECT, BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, BPF_PERF_EVENT, + BPF_TRACE_KPROBE_MULTI, __MAX_BPF_ATTACH_TYPE }; @@ -1011,6 +1012,7 @@ enum bpf_link_type { BPF_LINK_TYPE_NETNS = 5, BPF_LINK_TYPE_XDP = 6, BPF_LINK_TYPE_PERF_EVENT = 7, + BPF_LINK_TYPE_KPROBE_MULTI = 8, MAX_BPF_LINK_TYPE, }; @@ -1118,6 +1120,11 @@ enum bpf_link_type { */ #define BPF_F_XDP_HAS_FRAGS (1U << 5) +/* link_create.kprobe_multi.flags used in LINK_CREATE command for + * BPF_TRACE_KPROBE_MULTI attach type to create return probe. + */ +#define BPF_F_KPROBE_MULTI_RETURN (1U << 0) + /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * the following extensions: * @@ -1232,6 +1239,8 @@ enum { /* If set, run the test on the cpu specified by bpf_attr.test.cpu */ #define BPF_F_TEST_RUN_ON_CPU (1U << 0) +/* If set, XDP frames will be transmitted after processing */ +#define BPF_F_TEST_XDP_LIVE_FRAMES (1U << 1) /* type for BPF_ENABLE_STATS */ enum bpf_stats_type { @@ -1393,6 +1402,7 @@ union bpf_attr { __aligned_u64 ctx_out; __u32 flags; __u32 cpu; + __u32 batch_size; } test; struct { /* anonymous struct used by BPF_*_GET_*_ID */ @@ -1472,6 +1482,13 @@ union bpf_attr { */ __u64 bpf_cookie; } perf_event; + struct { + __u32 flags; + __u32 cnt; + __aligned_u64 syms; + __aligned_u64 addrs; + __aligned_u64 cookies; + } kprobe_multi; }; } link_create; @@ -2299,8 +2316,8 @@ union bpf_attr { * Return * The return value depends on the result of the test, and can be: * - * * 0, if current task belongs to the cgroup2. - * * 1, if current task does not belong to the cgroup2. + * * 1, if current task belongs to the cgroup2. + * * 0, if current task does not belong to the cgroup2. * * A negative error code, if an error occurred. * * long bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags) @@ -5087,23 +5104,22 @@ union bpf_attr { * 0 on success, or a negative error in case of failure. On error * *dst* buffer is zeroed out. * - * long bpf_skb_set_delivery_time(struct sk_buff *skb, u64 dtime, u32 dtime_type) + * long bpf_skb_set_tstamp(struct sk_buff *skb, u64 tstamp, u32 tstamp_type) * Description - * Set a *dtime* (delivery time) to the __sk_buff->tstamp and also - * change the __sk_buff->delivery_time_type to *dtime_type*. - * - * When setting a delivery time (non zero *dtime*) to - * __sk_buff->tstamp, only BPF_SKB_DELIVERY_TIME_MONO *dtime_type* - * is supported. It is the only delivery_time_type that will be - * kept after bpf_redirect_*(). + * Change the __sk_buff->tstamp_type to *tstamp_type* + * and set *tstamp* to the __sk_buff->tstamp together. * - * If there is no need to change the __sk_buff->delivery_time_type, - * the delivery time can be directly written to __sk_buff->tstamp + * If there is no need to change the __sk_buff->tstamp_type, + * the tstamp value can be directly written to __sk_buff->tstamp * instead. * - * *dtime* 0 and *dtime_type* BPF_SKB_DELIVERY_TIME_NONE - * can be used to clear any delivery time stored in - * __sk_buff->tstamp. + * BPF_SKB_TSTAMP_DELIVERY_MONO is the only tstamp that + * will be kept during bpf_redirect_*(). A non zero + * *tstamp* must be used with the BPF_SKB_TSTAMP_DELIVERY_MONO + * *tstamp_type*. + * + * A BPF_SKB_TSTAMP_UNSPEC *tstamp_type* can only be used + * with a zero *tstamp*. * * Only IPv4 and IPv6 skb->protocol are supported. * @@ -5116,7 +5132,17 @@ union bpf_attr { * Return * 0 on success. * **-EINVAL** for invalid input - * **-EOPNOTSUPP** for unsupported delivery_time_type and protocol + * **-EOPNOTSUPP** for unsupported protocol + * + * long bpf_ima_file_hash(struct file *file, void *dst, u32 size) + * Description + * Returns a calculated IMA hash of the *file*. + * If the hash is larger than *size*, then only *size* + * bytes will be copied to *dst* + * Return + * The **hash_algo** is returned on success, + * **-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if + * invalid arguments are passed. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5311,7 +5337,8 @@ union bpf_attr { FN(xdp_load_bytes), \ FN(xdp_store_bytes), \ FN(copy_from_user_task), \ - FN(skb_set_delivery_time), \ + FN(skb_set_tstamp), \ + FN(ima_file_hash), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -5502,9 +5529,12 @@ union { \ } __attribute__((aligned(8))) enum { - BPF_SKB_DELIVERY_TIME_NONE, - BPF_SKB_DELIVERY_TIME_UNSPEC, - BPF_SKB_DELIVERY_TIME_MONO, + BPF_SKB_TSTAMP_UNSPEC, + BPF_SKB_TSTAMP_DELIVERY_MONO, /* tstamp has mono delivery time */ + /* For any BPF_SKB_TSTAMP_* that the bpf prog cannot handle, + * the bpf prog should handle it like BPF_SKB_TSTAMP_UNSPEC + * and try to deduce it by ingress, egress or skb->sk->sk_clockid. + */ }; /* user accessible mirror of in-kernel sk_buff. @@ -5547,7 +5577,7 @@ struct __sk_buff { __u32 gso_segs; __bpf_md_ptr(struct bpf_sock *, sk); __u32 gso_size; - __u8 delivery_time_type; + __u8 tstamp_type; __u32 :24; /* Padding, future use. */ __u64 hwtstamp; }; diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 418b259166f8..cf27251adb92 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -29,6 +29,7 @@ #include <errno.h> #include <linux/bpf.h> #include <linux/filter.h> +#include <linux/kernel.h> #include <limits.h> #include <sys/resource.h> #include "bpf.h" @@ -111,7 +112,7 @@ int probe_memcg_account(void) BPF_EMIT_CALL(BPF_FUNC_ktime_get_coarse_ns), BPF_EXIT_INSN(), }; - size_t insn_cnt = sizeof(insns) / sizeof(insns[0]); + size_t insn_cnt = ARRAY_SIZE(insns); union bpf_attr attr; int prog_fd; @@ -853,6 +854,15 @@ int bpf_link_create(int prog_fd, int target_fd, if (!OPTS_ZEROED(opts, perf_event)) return libbpf_err(-EINVAL); break; + case BPF_TRACE_KPROBE_MULTI: + attr.link_create.kprobe_multi.flags = OPTS_GET(opts, kprobe_multi.flags, 0); + attr.link_create.kprobe_multi.cnt = OPTS_GET(opts, kprobe_multi.cnt, 0); + attr.link_create.kprobe_multi.syms = ptr_to_u64(OPTS_GET(opts, kprobe_multi.syms, 0)); + attr.link_create.kprobe_multi.addrs = ptr_to_u64(OPTS_GET(opts, kprobe_multi.addrs, 0)); + attr.link_create.kprobe_multi.cookies = ptr_to_u64(OPTS_GET(opts, kprobe_multi.cookies, 0)); + if (!OPTS_ZEROED(opts, kprobe_multi)) + return libbpf_err(-EINVAL); + break; default: if (!OPTS_ZEROED(opts, flags)) return libbpf_err(-EINVAL); @@ -994,6 +1004,7 @@ int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts) memset(&attr, 0, sizeof(attr)); attr.test.prog_fd = prog_fd; + attr.test.batch_size = OPTS_GET(opts, batch_size, 0); attr.test.cpu = OPTS_GET(opts, cpu, 0); attr.test.flags = OPTS_GET(opts, flags, 0); attr.test.repeat = OPTS_GET(opts, repeat, 0); diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 16b21757b8bf..f4b4afb6d4ba 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -413,10 +413,17 @@ struct bpf_link_create_opts { struct { __u64 bpf_cookie; } perf_event; + struct { + __u32 flags; + __u32 cnt; + const char **syms; + const unsigned long *addrs; + const __u64 *cookies; + } kprobe_multi; }; size_t :0; }; -#define bpf_link_create_opts__last_field perf_event +#define bpf_link_create_opts__last_field kprobe_multi.cookies LIBBPF_API int bpf_link_create(int prog_fd, int target_fd, enum bpf_attach_type attach_type, @@ -512,8 +519,9 @@ struct bpf_test_run_opts { __u32 duration; /* out: average per repetition in ns */ __u32 flags; __u32 cpu; + __u32 batch_size; }; -#define bpf_test_run_opts__last_field cpu +#define bpf_test_run_opts__last_field batch_size LIBBPF_API int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts); diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 81bf01d67671..809fe209cdcc 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -201,12 +201,6 @@ struct reloc_desc { }; }; -struct bpf_sec_def; - -typedef int (*init_fn_t)(struct bpf_program *prog, long cookie); -typedef int (*preload_fn_t)(struct bpf_program *prog, struct bpf_prog_load_opts *opts, long cookie); -typedef struct bpf_link *(*attach_fn_t)(const struct bpf_program *prog, long cookie); - /* stored as sec_def->cookie for all libbpf-supported SEC()s */ enum sec_def_flags { SEC_NONE = 0, @@ -234,14 +228,15 @@ enum sec_def_flags { }; struct bpf_sec_def { - const char *sec; + char *sec; enum bpf_prog_type prog_type; enum bpf_attach_type expected_attach_type; long cookie; + int handler_id; - init_fn_t init_fn; - preload_fn_t preload_fn; - attach_fn_t attach_fn; + libbpf_prog_setup_fn_t prog_setup_fn; + libbpf_prog_prepare_load_fn_t prog_prepare_load_fn; + libbpf_prog_attach_fn_t prog_attach_fn; }; /* @@ -1523,6 +1518,9 @@ static char *internal_map_name(struct bpf_object *obj, const char *real_name) } static int +bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map); + +static int bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, const char *real_name, int sec_idx, void *data, size_t data_sz) { @@ -1569,6 +1567,9 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, return err; } + /* failures are fine because of maps like .rodata.str1.1 */ + (void) bpf_map_find_btf_info(obj, map); + if (data) memcpy(map->mmaped, data, data_sz); @@ -2051,6 +2052,9 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) } memcpy(&map->def, def, sizeof(struct bpf_map_def)); } + + /* btf info may not exist but fill it in if it does exist */ + (void) bpf_map_find_btf_info(obj, map); } return 0; } @@ -2539,6 +2543,10 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, fill_map_from_def(map->inner_map, &inner_def); } + err = bpf_map_find_btf_info(obj, map); + if (err) + return err; + return 0; } @@ -3837,7 +3845,14 @@ static bool prog_is_subprog(const struct bpf_object *obj, * .text programs are subprograms (even if they are not called from * other programs), because libbpf never explicitly supported mixing * SEC()-designated BPF programs and .text entry-point BPF programs. + * + * In libbpf 1.0 strict mode, we always consider .text + * programs to be subprograms. */ + + if (libbpf_mode & LIBBPF_STRICT_SEC_NAME) + return prog->sec_idx == obj->efile.text_shndx; + return prog->sec_idx == obj->efile.text_shndx && obj->nr_programs > 1; } @@ -4182,6 +4197,9 @@ static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map) __u32 key_type_id = 0, value_type_id = 0; int ret; + if (!obj->btf) + return -ENOENT; + /* if it's BTF-defined map, we don't need to search for type IDs. * For struct_ops map, it does not need btf_key_type_id and * btf_value_type_id. @@ -4805,8 +4823,8 @@ bpf_object__reuse_map(struct bpf_map *map) } err = bpf_map__reuse_fd(map, pin_fd); + close(pin_fd); if (err) { - close(pin_fd); return err; } map->pinned = true; @@ -4871,7 +4889,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b if (bpf_map__is_struct_ops(map)) create_attr.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id; - if (obj->btf && btf__fd(obj->btf) >= 0 && !bpf_map_find_btf_info(obj, map)) { + if (obj->btf && btf__fd(obj->btf) >= 0) { create_attr.btf_fd = btf__fd(obj->btf); create_attr.btf_key_type_id = map->btf_key_type_id; create_attr.btf_value_type_id = map->btf_value_type_id; @@ -6572,9 +6590,9 @@ static int bpf_object__sanitize_prog(struct bpf_object *obj, struct bpf_program static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attach_name, int *btf_obj_fd, int *btf_type_id); -/* this is called as prog->sec_def->preload_fn for libbpf-supported sec_defs */ -static int libbpf_preload_prog(struct bpf_program *prog, - struct bpf_prog_load_opts *opts, long cookie) +/* this is called as prog->sec_def->prog_prepare_load_fn for libbpf-supported sec_defs */ +static int libbpf_prepare_prog_load(struct bpf_program *prog, + struct bpf_prog_load_opts *opts, long cookie) { enum sec_def_flags def = cookie; @@ -6670,8 +6688,8 @@ static int bpf_object_load_prog_instance(struct bpf_object *obj, struct bpf_prog load_attr.fd_array = obj->fd_array; /* adjust load_attr if sec_def provides custom preload callback */ - if (prog->sec_def && prog->sec_def->preload_fn) { - err = prog->sec_def->preload_fn(prog, &load_attr, prog->sec_def->cookie); + if (prog->sec_def && prog->sec_def->prog_prepare_load_fn) { + err = prog->sec_def->prog_prepare_load_fn(prog, &load_attr, prog->sec_def->cookie); if (err < 0) { pr_warn("prog '%s': failed to prepare load attributes: %d\n", prog->name, err); @@ -6971,8 +6989,8 @@ static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object /* sec_def can have custom callback which should be called * after bpf_program is initialized to adjust its properties */ - if (prog->sec_def->init_fn) { - err = prog->sec_def->init_fn(prog, prog->sec_def->cookie); + if (prog->sec_def->prog_setup_fn) { + err = prog->sec_def->prog_setup_fn(prog, prog->sec_def->cookie); if (err < 0) { pr_warn("prog '%s': failed to initialize: %d\n", prog->name, err); @@ -7176,12 +7194,10 @@ static int bpf_object__sanitize_maps(struct bpf_object *obj) return 0; } -static int bpf_object__read_kallsyms_file(struct bpf_object *obj) +int libbpf_kallsyms_parse(kallsyms_cb_t cb, void *ctx) { char sym_type, sym_name[500]; unsigned long long sym_addr; - const struct btf_type *t; - struct extern_desc *ext; int ret, err = 0; FILE *f; @@ -7200,35 +7216,51 @@ static int bpf_object__read_kallsyms_file(struct bpf_object *obj) if (ret != 3) { pr_warn("failed to read kallsyms entry: %d\n", ret); err = -EINVAL; - goto out; + break; } - ext = find_extern_by_name(obj, sym_name); - if (!ext || ext->type != EXT_KSYM) - continue; - - t = btf__type_by_id(obj->btf, ext->btf_id); - if (!btf_is_var(t)) - continue; - - if (ext->is_set && ext->ksym.addr != sym_addr) { - pr_warn("extern (ksym) '%s' resolution is ambiguous: 0x%llx or 0x%llx\n", - sym_name, ext->ksym.addr, sym_addr); - err = -EINVAL; - goto out; - } - if (!ext->is_set) { - ext->is_set = true; - ext->ksym.addr = sym_addr; - pr_debug("extern (ksym) %s=0x%llx\n", sym_name, sym_addr); - } + err = cb(sym_addr, sym_type, sym_name, ctx); + if (err) + break; } -out: fclose(f); return err; } +static int kallsyms_cb(unsigned long long sym_addr, char sym_type, + const char *sym_name, void *ctx) +{ + struct bpf_object *obj = ctx; + const struct btf_type *t; + struct extern_desc *ext; + + ext = find_extern_by_name(obj, sym_name); + if (!ext || ext->type != EXT_KSYM) + return 0; + + t = btf__type_by_id(obj->btf, ext->btf_id); + if (!btf_is_var(t)) + return 0; + + if (ext->is_set && ext->ksym.addr != sym_addr) { + pr_warn("extern (ksym) '%s' resolution is ambiguous: 0x%llx or 0x%llx\n", + sym_name, ext->ksym.addr, sym_addr); + return -EINVAL; + } + if (!ext->is_set) { + ext->is_set = true; + ext->ksym.addr = sym_addr; + pr_debug("extern (ksym) %s=0x%llx\n", sym_name, sym_addr); + } + return 0; +} + +static int bpf_object__read_kallsyms_file(struct bpf_object *obj) +{ + return libbpf_kallsyms_parse(kallsyms_cb, obj); +} + static int find_ksym_btf_id(struct bpf_object *obj, const char *ksym_name, __u16 kind, struct btf **res_btf, struct module_btf **res_mod_btf) @@ -8589,20 +8621,21 @@ int bpf_program__set_log_buf(struct bpf_program *prog, char *log_buf, size_t log } #define SEC_DEF(sec_pfx, ptype, atype, flags, ...) { \ - .sec = sec_pfx, \ + .sec = (char *)sec_pfx, \ .prog_type = BPF_PROG_TYPE_##ptype, \ .expected_attach_type = atype, \ .cookie = (long)(flags), \ - .preload_fn = libbpf_preload_prog, \ + .prog_prepare_load_fn = libbpf_prepare_prog_load, \ __VA_ARGS__ \ } -static struct bpf_link *attach_kprobe(const struct bpf_program *prog, long cookie); -static struct bpf_link *attach_tp(const struct bpf_program *prog, long cookie); -static struct bpf_link *attach_raw_tp(const struct bpf_program *prog, long cookie); -static struct bpf_link *attach_trace(const struct bpf_program *prog, long cookie); -static struct bpf_link *attach_lsm(const struct bpf_program *prog, long cookie); -static struct bpf_link *attach_iter(const struct bpf_program *prog, long cookie); +static int attach_kprobe(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_tp(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_raw_tp(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_trace(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_kprobe_multi(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_lsm(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_iter(const struct bpf_program *prog, long cookie, struct bpf_link **link); static const struct bpf_sec_def section_defs[] = { SEC_DEF("socket", SOCKET_FILTER, 0, SEC_NONE | SEC_SLOPPY_PFX), @@ -8612,6 +8645,8 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("uprobe/", KPROBE, 0, SEC_NONE), SEC_DEF("kretprobe/", KPROBE, 0, SEC_NONE, attach_kprobe), SEC_DEF("uretprobe/", KPROBE, 0, SEC_NONE), + SEC_DEF("kprobe.multi/", KPROBE, BPF_TRACE_KPROBE_MULTI, SEC_NONE, attach_kprobe_multi), + SEC_DEF("kretprobe.multi/", KPROBE, BPF_TRACE_KPROBE_MULTI, SEC_NONE, attach_kprobe_multi), SEC_DEF("tc", SCHED_CLS, 0, SEC_NONE), SEC_DEF("classifier", SCHED_CLS, 0, SEC_NONE | SEC_SLOPPY_PFX | SEC_DEPRECATED), SEC_DEF("action", SCHED_ACT, 0, SEC_NONE | SEC_SLOPPY_PFX), @@ -8682,61 +8717,167 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("sk_lookup", SK_LOOKUP, BPF_SK_LOOKUP, SEC_ATTACHABLE | SEC_SLOPPY_PFX), }; -#define MAX_TYPE_NAME_SIZE 32 +static size_t custom_sec_def_cnt; +static struct bpf_sec_def *custom_sec_defs; +static struct bpf_sec_def custom_fallback_def; +static bool has_custom_fallback_def; -static const struct bpf_sec_def *find_sec_def(const char *sec_name) +static int last_custom_sec_def_handler_id; + +int libbpf_register_prog_handler(const char *sec, + enum bpf_prog_type prog_type, + enum bpf_attach_type exp_attach_type, + const struct libbpf_prog_handler_opts *opts) { - const struct bpf_sec_def *sec_def; - enum sec_def_flags sec_flags; - int i, n = ARRAY_SIZE(section_defs), len; - bool strict = libbpf_mode & LIBBPF_STRICT_SEC_NAME; + struct bpf_sec_def *sec_def; - for (i = 0; i < n; i++) { - sec_def = §ion_defs[i]; - sec_flags = sec_def->cookie; - len = strlen(sec_def->sec); + if (!OPTS_VALID(opts, libbpf_prog_handler_opts)) + return libbpf_err(-EINVAL); - /* "type/" always has to have proper SEC("type/extras") form */ - if (sec_def->sec[len - 1] == '/') { - if (str_has_pfx(sec_name, sec_def->sec)) - return sec_def; - continue; - } + if (last_custom_sec_def_handler_id == INT_MAX) /* prevent overflow */ + return libbpf_err(-E2BIG); - /* "type+" means it can be either exact SEC("type") or - * well-formed SEC("type/extras") with proper '/' separator - */ - if (sec_def->sec[len - 1] == '+') { - len--; - /* not even a prefix */ - if (strncmp(sec_name, sec_def->sec, len) != 0) - continue; - /* exact match or has '/' separator */ - if (sec_name[len] == '\0' || sec_name[len] == '/') - return sec_def; - continue; - } + if (sec) { + sec_def = libbpf_reallocarray(custom_sec_defs, custom_sec_def_cnt + 1, + sizeof(*sec_def)); + if (!sec_def) + return libbpf_err(-ENOMEM); - /* SEC_SLOPPY_PFX definitions are allowed to be just prefix - * matches, unless strict section name mode - * (LIBBPF_STRICT_SEC_NAME) is enabled, in which case the - * match has to be exact. - */ - if ((sec_flags & SEC_SLOPPY_PFX) && !strict) { - if (str_has_pfx(sec_name, sec_def->sec)) - return sec_def; - continue; - } + custom_sec_defs = sec_def; + sec_def = &custom_sec_defs[custom_sec_def_cnt]; + } else { + if (has_custom_fallback_def) + return libbpf_err(-EBUSY); - /* Definitions not marked SEC_SLOPPY_PFX (e.g., - * SEC("syscall")) are exact matches in both modes. - */ - if (strcmp(sec_name, sec_def->sec) == 0) + sec_def = &custom_fallback_def; + } + + sec_def->sec = sec ? strdup(sec) : NULL; + if (sec && !sec_def->sec) + return libbpf_err(-ENOMEM); + + sec_def->prog_type = prog_type; + sec_def->expected_attach_type = exp_attach_type; + sec_def->cookie = OPTS_GET(opts, cookie, 0); + + sec_def->prog_setup_fn = OPTS_GET(opts, prog_setup_fn, NULL); + sec_def->prog_prepare_load_fn = OPTS_GET(opts, prog_prepare_load_fn, NULL); + sec_def->prog_attach_fn = OPTS_GET(opts, prog_attach_fn, NULL); + + sec_def->handler_id = ++last_custom_sec_def_handler_id; + + if (sec) + custom_sec_def_cnt++; + else + has_custom_fallback_def = true; + + return sec_def->handler_id; +} + +int libbpf_unregister_prog_handler(int handler_id) +{ + struct bpf_sec_def *sec_defs; + int i; + + if (handler_id <= 0) + return libbpf_err(-EINVAL); + + if (has_custom_fallback_def && custom_fallback_def.handler_id == handler_id) { + memset(&custom_fallback_def, 0, sizeof(custom_fallback_def)); + has_custom_fallback_def = false; + return 0; + } + + for (i = 0; i < custom_sec_def_cnt; i++) { + if (custom_sec_defs[i].handler_id == handler_id) + break; + } + + if (i == custom_sec_def_cnt) + return libbpf_err(-ENOENT); + + free(custom_sec_defs[i].sec); + for (i = i + 1; i < custom_sec_def_cnt; i++) + custom_sec_defs[i - 1] = custom_sec_defs[i]; + custom_sec_def_cnt--; + + /* try to shrink the array, but it's ok if we couldn't */ + sec_defs = libbpf_reallocarray(custom_sec_defs, custom_sec_def_cnt, sizeof(*sec_defs)); + if (sec_defs) + custom_sec_defs = sec_defs; + + return 0; +} + +static bool sec_def_matches(const struct bpf_sec_def *sec_def, const char *sec_name, + bool allow_sloppy) +{ + size_t len = strlen(sec_def->sec); + + /* "type/" always has to have proper SEC("type/extras") form */ + if (sec_def->sec[len - 1] == '/') { + if (str_has_pfx(sec_name, sec_def->sec)) + return true; + return false; + } + + /* "type+" means it can be either exact SEC("type") or + * well-formed SEC("type/extras") with proper '/' separator + */ + if (sec_def->sec[len - 1] == '+') { + len--; + /* not even a prefix */ + if (strncmp(sec_name, sec_def->sec, len) != 0) + return false; + /* exact match or has '/' separator */ + if (sec_name[len] == '\0' || sec_name[len] == '/') + return true; + return false; + } + + /* SEC_SLOPPY_PFX definitions are allowed to be just prefix + * matches, unless strict section name mode + * (LIBBPF_STRICT_SEC_NAME) is enabled, in which case the + * match has to be exact. + */ + if (allow_sloppy && str_has_pfx(sec_name, sec_def->sec)) + return true; + + /* Definitions not marked SEC_SLOPPY_PFX (e.g., + * SEC("syscall")) are exact matches in both modes. + */ + return strcmp(sec_name, sec_def->sec) == 0; +} + +static const struct bpf_sec_def *find_sec_def(const char *sec_name) +{ + const struct bpf_sec_def *sec_def; + int i, n; + bool strict = libbpf_mode & LIBBPF_STRICT_SEC_NAME, allow_sloppy; + + n = custom_sec_def_cnt; + for (i = 0; i < n; i++) { + sec_def = &custom_sec_defs[i]; + if (sec_def_matches(sec_def, sec_name, false)) + return sec_def; + } + + n = ARRAY_SIZE(section_defs); + for (i = 0; i < n; i++) { + sec_def = §ion_defs[i]; + allow_sloppy = (sec_def->cookie & SEC_SLOPPY_PFX) && !strict; + if (sec_def_matches(sec_def, sec_name, allow_sloppy)) return sec_def; } + + if (has_custom_fallback_def) + return &custom_fallback_def; + return NULL; } +#define MAX_TYPE_NAME_SIZE 32 + static char *libbpf_get_type_names(bool attach_type) { int i, len = ARRAY_SIZE(section_defs) * MAX_TYPE_NAME_SIZE; @@ -8752,7 +8893,7 @@ static char *libbpf_get_type_names(bool attach_type) const struct bpf_sec_def *sec_def = §ion_defs[i]; if (attach_type) { - if (sec_def->preload_fn != libbpf_preload_prog) + if (sec_def->prog_prepare_load_fn != libbpf_prepare_prog_load) continue; if (!(sec_def->cookie & SEC_ATTACHABLE)) @@ -9135,7 +9276,7 @@ int libbpf_attach_type_by_name(const char *name, return libbpf_err(-EINVAL); } - if (sec_def->preload_fn != libbpf_preload_prog) + if (sec_def->prog_prepare_load_fn != libbpf_prepare_prog_load) return libbpf_err(-EINVAL); if (!(sec_def->cookie & SEC_ATTACHABLE)) return libbpf_err(-EINVAL); @@ -10109,14 +10250,146 @@ struct bpf_link *bpf_program__attach_kprobe(const struct bpf_program *prog, return bpf_program__attach_kprobe_opts(prog, func_name, &opts); } -static struct bpf_link *attach_kprobe(const struct bpf_program *prog, long cookie) +/* Adapted from perf/util/string.c */ +static bool glob_match(const char *str, const char *pat) +{ + while (*str && *pat && *pat != '*') { + if (*pat == '?') { /* Matches any single character */ + str++; + pat++; + continue; + } + if (*str != *pat) + return false; + str++; + pat++; + } + /* Check wild card */ + if (*pat == '*') { + while (*pat == '*') + pat++; + if (!*pat) /* Tail wild card matches all */ + return true; + while (*str) + if (glob_match(str++, pat)) + return true; + } + return !*str && !*pat; +} + +struct kprobe_multi_resolve { + const char *pattern; + unsigned long *addrs; + size_t cap; + size_t cnt; +}; + +static int +resolve_kprobe_multi_cb(unsigned long long sym_addr, char sym_type, + const char *sym_name, void *ctx) +{ + struct kprobe_multi_resolve *res = ctx; + int err; + + if (!glob_match(sym_name, res->pattern)) + return 0; + + err = libbpf_ensure_mem((void **) &res->addrs, &res->cap, sizeof(unsigned long), + res->cnt + 1); + if (err) + return err; + + res->addrs[res->cnt++] = (unsigned long) sym_addr; + return 0; +} + +struct bpf_link * +bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, + const char *pattern, + const struct bpf_kprobe_multi_opts *opts) +{ + LIBBPF_OPTS(bpf_link_create_opts, lopts); + struct kprobe_multi_resolve res = { + .pattern = pattern, + }; + struct bpf_link *link = NULL; + char errmsg[STRERR_BUFSIZE]; + const unsigned long *addrs; + int err, link_fd, prog_fd; + const __u64 *cookies; + const char **syms; + bool retprobe; + size_t cnt; + + if (!OPTS_VALID(opts, bpf_kprobe_multi_opts)) + return libbpf_err_ptr(-EINVAL); + + syms = OPTS_GET(opts, syms, false); + addrs = OPTS_GET(opts, addrs, false); + cnt = OPTS_GET(opts, cnt, false); + cookies = OPTS_GET(opts, cookies, false); + + if (!pattern && !addrs && !syms) + return libbpf_err_ptr(-EINVAL); + if (pattern && (addrs || syms || cookies || cnt)) + return libbpf_err_ptr(-EINVAL); + if (!pattern && !cnt) + return libbpf_err_ptr(-EINVAL); + if (addrs && syms) + return libbpf_err_ptr(-EINVAL); + + if (pattern) { + err = libbpf_kallsyms_parse(resolve_kprobe_multi_cb, &res); + if (err) + goto error; + if (!res.cnt) { + err = -ENOENT; + goto error; + } + addrs = res.addrs; + cnt = res.cnt; + } + + retprobe = OPTS_GET(opts, retprobe, false); + + lopts.kprobe_multi.syms = syms; + lopts.kprobe_multi.addrs = addrs; + lopts.kprobe_multi.cookies = cookies; + lopts.kprobe_multi.cnt = cnt; + lopts.kprobe_multi.flags = retprobe ? BPF_F_KPROBE_MULTI_RETURN : 0; + + link = calloc(1, sizeof(*link)); + if (!link) { + err = -ENOMEM; + goto error; + } + link->detach = &bpf_link__detach_fd; + + prog_fd = bpf_program__fd(prog); + link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_KPROBE_MULTI, &lopts); + if (link_fd < 0) { + err = -errno; + pr_warn("prog '%s': failed to attach: %s\n", + prog->name, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + goto error; + } + link->fd = link_fd; + free(res.addrs); + return link; + +error: + free(link); + free(res.addrs); + return libbpf_err_ptr(err); +} + +static int attach_kprobe(const struct bpf_program *prog, long cookie, struct bpf_link **link) { DECLARE_LIBBPF_OPTS(bpf_kprobe_opts, opts); unsigned long offset = 0; - struct bpf_link *link; const char *func_name; char *func; - int n, err; + int n; opts.retprobe = str_has_pfx(prog->sec_name, "kretprobe/"); if (opts.retprobe) @@ -10126,21 +10399,43 @@ static struct bpf_link *attach_kprobe(const struct bpf_program *prog, long cooki n = sscanf(func_name, "%m[a-zA-Z0-9_.]+%li", &func, &offset); if (n < 1) { - err = -EINVAL; pr_warn("kprobe name is invalid: %s\n", func_name); - return libbpf_err_ptr(err); + return -EINVAL; } if (opts.retprobe && offset != 0) { free(func); - err = -EINVAL; pr_warn("kretprobes do not support offset specification\n"); - return libbpf_err_ptr(err); + return -EINVAL; } opts.offset = offset; - link = bpf_program__attach_kprobe_opts(prog, func, &opts); + *link = bpf_program__attach_kprobe_opts(prog, func, &opts); free(func); - return link; + return libbpf_get_error(*link); +} + +static int attach_kprobe_multi(const struct bpf_program *prog, long cookie, struct bpf_link **link) +{ + LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); + const char *spec; + char *pattern; + int n; + + opts.retprobe = str_has_pfx(prog->sec_name, "kretprobe.multi/"); + if (opts.retprobe) + spec = prog->sec_name + sizeof("kretprobe.multi/") - 1; + else + spec = prog->sec_name + sizeof("kprobe.multi/") - 1; + + n = sscanf(spec, "%m[a-zA-Z0-9_.*?]", &pattern); + if (n < 1) { + pr_warn("kprobe multi pattern is invalid: %s\n", pattern); + return -EINVAL; + } + + *link = bpf_program__attach_kprobe_multi_opts(prog, pattern, &opts); + free(pattern); + return libbpf_get_error(*link); } static void gen_uprobe_legacy_event_name(char *buf, size_t buf_sz, @@ -10395,14 +10690,13 @@ struct bpf_link *bpf_program__attach_tracepoint(const struct bpf_program *prog, return bpf_program__attach_tracepoint_opts(prog, tp_category, tp_name, NULL); } -static struct bpf_link *attach_tp(const struct bpf_program *prog, long cookie) +static int attach_tp(const struct bpf_program *prog, long cookie, struct bpf_link **link) { char *sec_name, *tp_cat, *tp_name; - struct bpf_link *link; sec_name = strdup(prog->sec_name); if (!sec_name) - return libbpf_err_ptr(-ENOMEM); + return -ENOMEM; /* extract "tp/<category>/<name>" or "tracepoint/<category>/<name>" */ if (str_has_pfx(prog->sec_name, "tp/")) @@ -10412,14 +10706,14 @@ static struct bpf_link *attach_tp(const struct bpf_program *prog, long cookie) tp_name = strchr(tp_cat, '/'); if (!tp_name) { free(sec_name); - return libbpf_err_ptr(-EINVAL); + return -EINVAL; } *tp_name = '\0'; tp_name++; - link = bpf_program__attach_tracepoint(prog, tp_cat, tp_name); + *link = bpf_program__attach_tracepoint(prog, tp_cat, tp_name); free(sec_name); - return link; + return libbpf_get_error(*link); } struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *prog, @@ -10452,7 +10746,7 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *pr return link; } -static struct bpf_link *attach_raw_tp(const struct bpf_program *prog, long cookie) +static int attach_raw_tp(const struct bpf_program *prog, long cookie, struct bpf_link **link) { static const char *const prefixes[] = { "raw_tp/", @@ -10472,10 +10766,11 @@ static struct bpf_link *attach_raw_tp(const struct bpf_program *prog, long cooki if (!tp_name) { pr_warn("prog '%s': invalid section name '%s'\n", prog->name, prog->sec_name); - return libbpf_err_ptr(-EINVAL); + return -EINVAL; } - return bpf_program__attach_raw_tracepoint(prog, tp_name); + *link = bpf_program__attach_raw_tracepoint(prog, tp_name); + return libbpf_get_error(link); } /* Common logic for all BPF program types that attach to a btf_id */ @@ -10518,14 +10813,16 @@ struct bpf_link *bpf_program__attach_lsm(const struct bpf_program *prog) return bpf_program__attach_btf_id(prog); } -static struct bpf_link *attach_trace(const struct bpf_program *prog, long cookie) +static int attach_trace(const struct bpf_program *prog, long cookie, struct bpf_link **link) { - return bpf_program__attach_trace(prog); + *link = bpf_program__attach_trace(prog); + return libbpf_get_error(*link); } -static struct bpf_link *attach_lsm(const struct bpf_program *prog, long cookie) +static int attach_lsm(const struct bpf_program *prog, long cookie, struct bpf_link **link) { - return bpf_program__attach_lsm(prog); + *link = bpf_program__attach_lsm(prog); + return libbpf_get_error(*link); } static struct bpf_link * @@ -10654,17 +10951,33 @@ bpf_program__attach_iter(const struct bpf_program *prog, return link; } -static struct bpf_link *attach_iter(const struct bpf_program *prog, long cookie) +static int attach_iter(const struct bpf_program *prog, long cookie, struct bpf_link **link) { - return bpf_program__attach_iter(prog, NULL); + *link = bpf_program__attach_iter(prog, NULL); + return libbpf_get_error(*link); } struct bpf_link *bpf_program__attach(const struct bpf_program *prog) { - if (!prog->sec_def || !prog->sec_def->attach_fn) - return libbpf_err_ptr(-ESRCH); + struct bpf_link *link = NULL; + int err; + + if (!prog->sec_def || !prog->sec_def->prog_attach_fn) + return libbpf_err_ptr(-EOPNOTSUPP); + + err = prog->sec_def->prog_attach_fn(prog, prog->sec_def->cookie, &link); + if (err) + return libbpf_err_ptr(err); - return prog->sec_def->attach_fn(prog, prog->sec_def->cookie); + /* When calling bpf_program__attach() explicitly, auto-attach support + * is expected to work, so NULL returned link is considered an error. + * This is different for skeleton's attach, see comment in + * bpf_object__attach_skeleton(). + */ + if (!link) + return libbpf_err_ptr(-EOPNOTSUPP); + + return link; } static int bpf_link__detach_struct_ops(struct bpf_link *link) @@ -11679,6 +11992,49 @@ int libbpf_num_possible_cpus(void) return tmp_cpus; } +static int populate_skeleton_maps(const struct bpf_object *obj, + struct bpf_map_skeleton *maps, + size_t map_cnt) +{ + int i; + + for (i = 0; i < map_cnt; i++) { + struct bpf_map **map = maps[i].map; + const char *name = maps[i].name; + void **mmaped = maps[i].mmaped; + + *map = bpf_object__find_map_by_name(obj, name); + if (!*map) { + pr_warn("failed to find skeleton map '%s'\n", name); + return -ESRCH; + } + + /* externs shouldn't be pre-setup from user code */ + if (mmaped && (*map)->libbpf_type != LIBBPF_MAP_KCONFIG) + *mmaped = (*map)->mmaped; + } + return 0; +} + +static int populate_skeleton_progs(const struct bpf_object *obj, + struct bpf_prog_skeleton *progs, + size_t prog_cnt) +{ + int i; + + for (i = 0; i < prog_cnt; i++) { + struct bpf_program **prog = progs[i].prog; + const char *name = progs[i].name; + + *prog = bpf_object__find_program_by_name(obj, name); + if (!*prog) { + pr_warn("failed to find skeleton program '%s'\n", name); + return -ESRCH; + } + } + return 0; +} + int bpf_object__open_skeleton(struct bpf_object_skeleton *s, const struct bpf_object_open_opts *opts) { @@ -11686,7 +12042,7 @@ int bpf_object__open_skeleton(struct bpf_object_skeleton *s, .object_name = s->name, ); struct bpf_object *obj; - int i, err; + int err; /* Attempt to preserve opts->object_name, unless overriden by user * explicitly. Overwriting object name for skeletons is discouraged, @@ -11709,37 +12065,91 @@ int bpf_object__open_skeleton(struct bpf_object_skeleton *s, } *s->obj = obj; + err = populate_skeleton_maps(obj, s->maps, s->map_cnt); + if (err) { + pr_warn("failed to populate skeleton maps for '%s': %d\n", s->name, err); + return libbpf_err(err); + } - for (i = 0; i < s->map_cnt; i++) { - struct bpf_map **map = s->maps[i].map; - const char *name = s->maps[i].name; - void **mmaped = s->maps[i].mmaped; + err = populate_skeleton_progs(obj, s->progs, s->prog_cnt); + if (err) { + pr_warn("failed to populate skeleton progs for '%s': %d\n", s->name, err); + return libbpf_err(err); + } - *map = bpf_object__find_map_by_name(obj, name); - if (!*map) { - pr_warn("failed to find skeleton map '%s'\n", name); - return libbpf_err(-ESRCH); - } + return 0; +} - /* externs shouldn't be pre-setup from user code */ - if (mmaped && (*map)->libbpf_type != LIBBPF_MAP_KCONFIG) - *mmaped = (*map)->mmaped; +int bpf_object__open_subskeleton(struct bpf_object_subskeleton *s) +{ + int err, len, var_idx, i; + const char *var_name; + const struct bpf_map *map; + struct btf *btf; + __u32 map_type_id; + const struct btf_type *map_type, *var_type; + const struct bpf_var_skeleton *var_skel; + struct btf_var_secinfo *var; + + if (!s->obj) + return libbpf_err(-EINVAL); + + btf = bpf_object__btf(s->obj); + if (!btf) { + pr_warn("subskeletons require BTF at runtime (object %s)\n", + bpf_object__name(s->obj)); + return libbpf_err(-errno); } - for (i = 0; i < s->prog_cnt; i++) { - struct bpf_program **prog = s->progs[i].prog; - const char *name = s->progs[i].name; + err = populate_skeleton_maps(s->obj, s->maps, s->map_cnt); + if (err) { + pr_warn("failed to populate subskeleton maps: %d\n", err); + return libbpf_err(err); + } - *prog = bpf_object__find_program_by_name(obj, name); - if (!*prog) { - pr_warn("failed to find skeleton program '%s'\n", name); - return libbpf_err(-ESRCH); - } + err = populate_skeleton_progs(s->obj, s->progs, s->prog_cnt); + if (err) { + pr_warn("failed to populate subskeleton maps: %d\n", err); + return libbpf_err(err); } + for (var_idx = 0; var_idx < s->var_cnt; var_idx++) { + var_skel = &s->vars[var_idx]; + map = *var_skel->map; + map_type_id = bpf_map__btf_value_type_id(map); + map_type = btf__type_by_id(btf, map_type_id); + + if (!btf_is_datasec(map_type)) { + pr_warn("type for map '%1$s' is not a datasec: %2$s", + bpf_map__name(map), + __btf_kind_str(btf_kind(map_type))); + return libbpf_err(-EINVAL); + } + + len = btf_vlen(map_type); + var = btf_var_secinfos(map_type); + for (i = 0; i < len; i++, var++) { + var_type = btf__type_by_id(btf, var->type); + var_name = btf__name_by_offset(btf, var_type->name_off); + if (strcmp(var_name, var_skel->name) == 0) { + *var_skel->addr = map->mmaped + var->offset; + break; + } + } + } return 0; } +void bpf_object__destroy_subskeleton(struct bpf_object_subskeleton *s) +{ + if (!s) + return; + free(s->maps); + free(s->progs); + free(s->vars); + free(s); +} + int bpf_object__load_skeleton(struct bpf_object_skeleton *s) { int i, err; @@ -11805,16 +12215,30 @@ int bpf_object__attach_skeleton(struct bpf_object_skeleton *s) continue; /* auto-attaching not supported for this program */ - if (!prog->sec_def || !prog->sec_def->attach_fn) + if (!prog->sec_def || !prog->sec_def->prog_attach_fn) continue; - *link = bpf_program__attach(prog); - err = libbpf_get_error(*link); + /* if user already set the link manually, don't attempt auto-attach */ + if (*link) + continue; + + err = prog->sec_def->prog_attach_fn(prog, prog->sec_def->cookie, link); if (err) { - pr_warn("failed to auto-attach program '%s': %d\n", + pr_warn("prog '%s': failed to auto-attach: %d\n", bpf_program__name(prog), err); return libbpf_err(err); } + + /* It's possible that for some SEC() definitions auto-attach + * is supported in some cases (e.g., if definition completely + * specifies target information), but is not in other cases. + * SEC("uprobe") is one such case. If user specified target + * binary and function name, such BPF program can be + * auto-attached. But if not, it shouldn't trigger skeleton's + * attach to fail. It should just be skipped. + * attach_fn signals such case with returning 0 (no error) and + * setting link to NULL. + */ } return 0; diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index c8d8daad212e..05dde85e19a6 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -425,6 +425,29 @@ bpf_program__attach_kprobe_opts(const struct bpf_program *prog, const char *func_name, const struct bpf_kprobe_opts *opts); +struct bpf_kprobe_multi_opts { + /* size of this struct, for forward/backward compatibility */ + size_t sz; + /* array of function symbols to attach */ + const char **syms; + /* array of function addresses to attach */ + const unsigned long *addrs; + /* array of user-provided values fetchable through bpf_get_attach_cookie */ + const __u64 *cookies; + /* number of elements in syms/addrs/cookies arrays */ + size_t cnt; + /* create return kprobes */ + bool retprobe; + size_t :0; +}; + +#define bpf_kprobe_multi_opts__last_field retprobe + +LIBBPF_API struct bpf_link * +bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, + const char *pattern, + const struct bpf_kprobe_multi_opts *opts); + struct bpf_uprobe_opts { /* size of this struct, for forward/backward compatiblity */ size_t sz; @@ -1289,6 +1312,35 @@ LIBBPF_API int bpf_object__attach_skeleton(struct bpf_object_skeleton *s); LIBBPF_API void bpf_object__detach_skeleton(struct bpf_object_skeleton *s); LIBBPF_API void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s); +struct bpf_var_skeleton { + const char *name; + struct bpf_map **map; + void **addr; +}; + +struct bpf_object_subskeleton { + size_t sz; /* size of this struct, for forward/backward compatibility */ + + const struct bpf_object *obj; + + int map_cnt; + int map_skel_sz; /* sizeof(struct bpf_map_skeleton) */ + struct bpf_map_skeleton *maps; + + int prog_cnt; + int prog_skel_sz; /* sizeof(struct bpf_prog_skeleton) */ + struct bpf_prog_skeleton *progs; + + int var_cnt; + int var_skel_sz; /* sizeof(struct bpf_var_skeleton) */ + struct bpf_var_skeleton *vars; +}; + +LIBBPF_API int +bpf_object__open_subskeleton(struct bpf_object_subskeleton *s); +LIBBPF_API void +bpf_object__destroy_subskeleton(struct bpf_object_subskeleton *s); + struct gen_loader_opts { size_t sz; /* size of this struct, for forward/backward compatiblity */ const char *data; @@ -1328,6 +1380,115 @@ LIBBPF_API int bpf_linker__add_file(struct bpf_linker *linker, LIBBPF_API int bpf_linker__finalize(struct bpf_linker *linker); LIBBPF_API void bpf_linker__free(struct bpf_linker *linker); +/* + * Custom handling of BPF program's SEC() definitions + */ + +struct bpf_prog_load_opts; /* defined in bpf.h */ + +/* Called during bpf_object__open() for each recognized BPF program. Callback + * can use various bpf_program__set_*() setters to adjust whatever properties + * are necessary. + */ +typedef int (*libbpf_prog_setup_fn_t)(struct bpf_program *prog, long cookie); + +/* Called right before libbpf performs bpf_prog_load() to load BPF program + * into the kernel. Callback can adjust opts as necessary. + */ +typedef int (*libbpf_prog_prepare_load_fn_t)(struct bpf_program *prog, + struct bpf_prog_load_opts *opts, long cookie); + +/* Called during skeleton attach or through bpf_program__attach(). If + * auto-attach is not supported, callback should return 0 and set link to + * NULL (it's not considered an error during skeleton attach, but it will be + * an error for bpf_program__attach() calls). On error, error should be + * returned directly and link set to NULL. On success, return 0 and set link + * to a valid struct bpf_link. + */ +typedef int (*libbpf_prog_attach_fn_t)(const struct bpf_program *prog, long cookie, + struct bpf_link **link); + +struct libbpf_prog_handler_opts { + /* size of this struct, for forward/backward compatiblity */ + size_t sz; + /* User-provided value that is passed to prog_setup_fn, + * prog_prepare_load_fn, and prog_attach_fn callbacks. Allows user to + * register one set of callbacks for multiple SEC() definitions and + * still be able to distinguish them, if necessary. For example, + * libbpf itself is using this to pass necessary flags (e.g., + * sleepable flag) to a common internal SEC() handler. + */ + long cookie; + /* BPF program initialization callback (see libbpf_prog_setup_fn_t). + * Callback is optional, pass NULL if it's not necessary. + */ + libbpf_prog_setup_fn_t prog_setup_fn; + /* BPF program loading callback (see libbpf_prog_prepare_load_fn_t). + * Callback is optional, pass NULL if it's not necessary. + */ + libbpf_prog_prepare_load_fn_t prog_prepare_load_fn; + /* BPF program attach callback (see libbpf_prog_attach_fn_t). + * Callback is optional, pass NULL if it's not necessary. + */ + libbpf_prog_attach_fn_t prog_attach_fn; +}; +#define libbpf_prog_handler_opts__last_field prog_attach_fn + +/** + * @brief **libbpf_register_prog_handler()** registers a custom BPF program + * SEC() handler. + * @param sec section prefix for which custom handler is registered + * @param prog_type BPF program type associated with specified section + * @param exp_attach_type Expected BPF attach type associated with specified section + * @param opts optional cookie, callbacks, and other extra options + * @return Non-negative handler ID is returned on success. This handler ID has + * to be passed to *libbpf_unregister_prog_handler()* to unregister such + * custom handler. Negative error code is returned on error. + * + * *sec* defines which SEC() definitions are handled by this custom handler + * registration. *sec* can have few different forms: + * - if *sec* is just a plain string (e.g., "abc"), it will match only + * SEC("abc"). If BPF program specifies SEC("abc/whatever") it will result + * in an error; + * - if *sec* is of the form "abc/", proper SEC() form is + * SEC("abc/something"), where acceptable "something" should be checked by + * *prog_init_fn* callback, if there are additional restrictions; + * - if *sec* is of the form "abc+", it will successfully match both + * SEC("abc") and SEC("abc/whatever") forms; + * - if *sec* is NULL, custom handler is registered for any BPF program that + * doesn't match any of the registered (custom or libbpf's own) SEC() + * handlers. There could be only one such generic custom handler registered + * at any given time. + * + * All custom handlers (except the one with *sec* == NULL) are processed + * before libbpf's own SEC() handlers. It is allowed to "override" libbpf's + * SEC() handlers by registering custom ones for the same section prefix + * (i.e., it's possible to have custom SEC("perf_event/LLC-load-misses") + * handler). + * + * Note, like much of global libbpf APIs (e.g., libbpf_set_print(), + * libbpf_set_strict_mode(), etc)) these APIs are not thread-safe. User needs + * to ensure synchronization if there is a risk of running this API from + * multiple threads simultaneously. + */ +LIBBPF_API int libbpf_register_prog_handler(const char *sec, + enum bpf_prog_type prog_type, + enum bpf_attach_type exp_attach_type, + const struct libbpf_prog_handler_opts *opts); +/** + * @brief *libbpf_unregister_prog_handler()* unregisters previously registered + * custom BPF program SEC() handler. + * @param handler_id handler ID returned by *libbpf_register_prog_handler()* + * after successful registration + * @return 0 on success, negative error code if handler isn't found + * + * Note, like much of global libbpf APIs (e.g., libbpf_set_print(), + * libbpf_set_strict_mode(), etc)) these APIs are not thread-safe. User needs + * to ensure synchronization if there is a risk of running this API from + * multiple threads simultaneously. + */ +LIBBPF_API int libbpf_unregister_prog_handler(int handler_id); + #ifdef __cplusplus } /* extern "C" */ #endif diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 47e70c9058d9..dd35ee58bfaa 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -439,3 +439,12 @@ LIBBPF_0.7.0 { libbpf_probe_bpf_prog_type; libbpf_set_memlock_rlim_max; } LIBBPF_0.6.0; + +LIBBPF_0.8.0 { + global: + bpf_object__destroy_subskeleton; + bpf_object__open_subskeleton; + libbpf_register_prog_handler; + libbpf_unregister_prog_handler; + bpf_program__attach_kprobe_multi_opts; +} LIBBPF_0.7.0; diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 4fda8bdf0a0d..b6247dc7f8eb 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -449,6 +449,11 @@ __s32 btf__find_by_name_kind_own(const struct btf *btf, const char *type_name, extern enum libbpf_strict_mode libbpf_mode; +typedef int (*kallsyms_cb_t)(unsigned long long sym_addr, char sym_type, + const char *sym_name, void *ctx); + +int libbpf_kallsyms_parse(kallsyms_cb_t cb, void *arg); + /* handle direct returned errors */ static inline int libbpf_err(int ret) { diff --git a/tools/lib/bpf/libbpf_legacy.h b/tools/lib/bpf/libbpf_legacy.h index a283cf031665..d7bcbd01f66f 100644 --- a/tools/lib/bpf/libbpf_legacy.h +++ b/tools/lib/bpf/libbpf_legacy.h @@ -54,6 +54,10 @@ enum libbpf_strict_mode { * * Note, in this mode the program pin path will be based on the * function name instead of section name. + * + * Additionally, routines in the .text section are always considered + * sub-programs. Legacy behavior allows for a single routine in .text + * to be a program. */ LIBBPF_STRICT_SEC_NAME = 0x04, /* diff --git a/tools/lib/bpf/libbpf_version.h b/tools/lib/bpf/libbpf_version.h index 0fefefc3500b..61f2039404b6 100644 --- a/tools/lib/bpf/libbpf_version.h +++ b/tools/lib/bpf/libbpf_version.h @@ -4,6 +4,6 @@ #define __LIBBPF_VERSION_H #define LIBBPF_MAJOR_VERSION 0 -#define LIBBPF_MINOR_VERSION 7 +#define LIBBPF_MINOR_VERSION 8 #endif /* __LIBBPF_VERSION_H */ diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index edafe56664f3..af136f73b09d 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -481,8 +481,8 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk) BPF_EMIT_CALL(BPF_FUNC_redirect_map), BPF_EXIT_INSN(), }; - size_t insns_cnt[] = {sizeof(prog) / sizeof(struct bpf_insn), - sizeof(prog_redirect_flags) / sizeof(struct bpf_insn), + size_t insns_cnt[] = {ARRAY_SIZE(prog), + ARRAY_SIZE(prog_redirect_flags), }; struct bpf_insn *progs[] = {prog, prog_redirect_flags}; enum xsk_prog option = get_xsk_prog(); @@ -1193,12 +1193,23 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, int xsk_umem__delete(struct xsk_umem *umem) { + struct xdp_mmap_offsets off; + int err; + if (!umem) return 0; if (umem->refcount) return -EBUSY; + err = xsk_get_mmap_offsets(umem->fd, &off); + if (!err && umem->fill_save && umem->comp_save) { + munmap(umem->fill_save->ring - off.fr.desc, + off.fr.desc + umem->config.fill_size * sizeof(__u64)); + munmap(umem->comp_save->ring - off.cr.desc, + off.cr.desc + umem->config.comp_size * sizeof(__u64)); + } + close(umem->fd); free(umem); diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include index 79d102304470..a2335e402145 100644 --- a/tools/scripts/Makefile.include +++ b/tools/scripts/Makefile.include @@ -89,6 +89,9 @@ ifeq ($(CC_NO_CLANG), 1) EXTRA_WARNINGS += -Wstrict-aliasing=3 else ifneq ($(CROSS_COMPILE),) +# Allow userspace to override CLANG_CROSS_FLAGS to specify their own +# sysroots and flags or to avoid the GCC call in pure Clang builds. +ifeq ($(CLANG_CROSS_FLAGS),) CLANG_CROSS_FLAGS := --target=$(notdir $(CROSS_COMPILE:%-=%)) GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)gcc 2>/dev/null)) ifneq ($(GCC_TOOLCHAIN_DIR),) @@ -96,6 +99,7 @@ CLANG_CROSS_FLAGS += --prefix=$(GCC_TOOLCHAIN_DIR)$(notdir $(CROSS_COMPILE)) CLANG_CROSS_FLAGS += --sysroot=$(shell $(CROSS_COMPILE)gcc -print-sysroot) CLANG_CROSS_FLAGS += --gcc-toolchain=$(realpath $(GCC_TOOLCHAIN_DIR)/..) endif # GCC_TOOLCHAIN_DIR +endif # CLANG_CROSS_FLAGS CFLAGS += $(CLANG_CROSS_FLAGS) AFLAGS += $(CLANG_CROSS_FLAGS) endif # CROSS_COMPILE diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index a7eead8820a0..595565eb68c0 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -31,6 +31,7 @@ test_tcp_check_syncookie_user test_sysctl xdping test_cpp +*.subskel.h *.skel.h *.lskel.h /no_alu32 diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index fe12b4f5fe20..3820608faf57 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -25,7 +25,7 @@ CFLAGS += -g -O0 -rdynamic -Wall -Werror $(GENFLAGS) $(SAN_CFLAGS) \ -I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) \ -I$(TOOLSINCDIR) -I$(APIDIR) -I$(OUTPUT) LDFLAGS += $(SAN_CFLAGS) -LDLIBS += -lcap -lelf -lz -lrt -lpthread +LDLIBS += -lelf -lz -lrt -lpthread # Silence some warnings when compiled with clang ifneq ($(LLVM),) @@ -195,6 +195,7 @@ $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): $(BPFOBJ) CGROUP_HELPERS := $(OUTPUT)/cgroup_helpers.o TESTING_HELPERS := $(OUTPUT)/testing_helpers.o TRACE_HELPERS := $(OUTPUT)/trace_helpers.o +CAP_HELPERS := $(OUTPUT)/cap_helpers.o $(OUTPUT)/test_dev_cgroup: $(CGROUP_HELPERS) $(TESTING_HELPERS) $(OUTPUT)/test_skb_cgroup_id_user: $(CGROUP_HELPERS) $(TESTING_HELPERS) @@ -211,7 +212,7 @@ $(OUTPUT)/test_lirc_mode2_user: $(TESTING_HELPERS) $(OUTPUT)/xdping: $(TESTING_HELPERS) $(OUTPUT)/flow_dissector_load: $(TESTING_HELPERS) $(OUTPUT)/test_maps: $(TESTING_HELPERS) -$(OUTPUT)/test_verifier: $(TESTING_HELPERS) +$(OUTPUT)/test_verifier: $(TESTING_HELPERS) $(CAP_HELPERS) BPFTOOL ?= $(DEFAULT_BPFTOOL) $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) \ @@ -326,7 +327,13 @@ endef SKEL_BLACKLIST := btf__% test_pinning_invalid.c test_sk_assign.c LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h \ - linked_vars.skel.h linked_maps.skel.h + linked_vars.skel.h linked_maps.skel.h \ + test_subskeleton.skel.h test_subskeleton_lib.skel.h + +# In the subskeleton case, we want the test_subskeleton_lib.subskel.h file +# but that's created as a side-effect of the skel.h generation. +test_subskeleton.skel.h-deps := test_subskeleton_lib2.o test_subskeleton_lib.o test_subskeleton.o +test_subskeleton_lib.skel.h-deps := test_subskeleton_lib2.o test_subskeleton_lib.o LSKELS := kfunc_call_test.c fentry_test.c fexit_test.c fexit_sleep.c \ test_ringbuf.c atomics.c trace_printk.c trace_vprintk.c \ @@ -404,6 +411,7 @@ $(TRUNNER_BPF_SKELS): %.skel.h: %.o $(BPFTOOL) | $(TRUNNER_OUTPUT) $(Q)$$(BPFTOOL) gen object $$(<:.o=.linked3.o) $$(<:.o=.linked2.o) $(Q)diff $$(<:.o=.linked2.o) $$(<:.o=.linked3.o) $(Q)$$(BPFTOOL) gen skeleton $$(<:.o=.linked3.o) name $$(notdir $$(<:.o=)) > $$@ + $(Q)$$(BPFTOOL) gen subskeleton $$(<:.o=.linked3.o) name $$(notdir $$(<:.o=)) > $$(@:.skel.h=.subskel.h) $(TRUNNER_BPF_LSKELS): %.lskel.h: %.o $(BPFTOOL) | $(TRUNNER_OUTPUT) $$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@) @@ -421,6 +429,7 @@ $(TRUNNER_BPF_SKELS_LINKED): $(TRUNNER_BPF_OBJS) $(BPFTOOL) | $(TRUNNER_OUTPUT) $(Q)diff $$(@:.skel.h=.linked2.o) $$(@:.skel.h=.linked3.o) $$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@) $(Q)$$(BPFTOOL) gen skeleton $$(@:.skel.h=.linked3.o) name $$(notdir $$(@:.skel.h=)) > $$@ + $(Q)$$(BPFTOOL) gen subskeleton $$(@:.skel.h=.linked3.o) name $$(notdir $$(@:.skel.h=)) > $$(@:.skel.h=.subskel.h) endif # ensure we set up tests.h header generation rule just once @@ -479,7 +488,8 @@ TRUNNER_TESTS_DIR := prog_tests TRUNNER_BPF_PROGS_DIR := progs TRUNNER_EXTRA_SOURCES := test_progs.c cgroup_helpers.c trace_helpers.c \ network_helpers.c testing_helpers.c \ - btf_helpers.c flow_dissector_load.h + btf_helpers.c flow_dissector_load.h \ + cap_helpers.c TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read $(OUTPUT)/bpf_testmod.ko \ ima_setup.sh \ $(wildcard progs/btf_dump_test_case_*.c) @@ -557,6 +567,6 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o \ EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) $(HOST_SCRATCH_DIR) \ prog_tests/tests.h map_tests/tests.h verifier/tests.h \ feature bpftool \ - $(addprefix $(OUTPUT)/,*.o *.skel.h *.lskel.h no_alu32 bpf_gcc bpf_testmod.ko) + $(addprefix $(OUTPUT)/,*.o *.skel.h *.lskel.h *.subskel.h no_alu32 bpf_gcc bpf_testmod.ko) .PHONY: docs docs-clean diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst index d099d91adc3b..eb1b7541f39d 100644 --- a/tools/testing/selftests/bpf/README.rst +++ b/tools/testing/selftests/bpf/README.rst @@ -32,11 +32,19 @@ For more information on about using the script, run: $ tools/testing/selftests/bpf/vmtest.sh -h +In case of linker errors when running selftests, try using static linking: + +.. code-block:: console + + $ LDLIBS=-static vmtest.sh + +.. note:: Some distros may not support static linking. + .. note:: The script uses pahole and clang based on host environment setting. If you want to change pahole and llvm, you can change `PATH` environment variable in the beginning of script. -.. note:: The script currently only supports x86_64. +.. note:: The script currently only supports x86_64 and s390x architectures. Additional information about selftest failures are documented here. diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index 27d63be47b95..e585e1cefc77 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -33,6 +33,10 @@ struct bpf_testmod_btf_type_tag_2 { struct bpf_testmod_btf_type_tag_1 __user *p; }; +struct bpf_testmod_btf_type_tag_3 { + struct bpf_testmod_btf_type_tag_1 __percpu *p; +}; + noinline int bpf_testmod_test_btf_type_tag_user_1(struct bpf_testmod_btf_type_tag_1 __user *arg) { BTF_TYPE_EMIT(func_proto_typedef); @@ -46,6 +50,16 @@ bpf_testmod_test_btf_type_tag_user_2(struct bpf_testmod_btf_type_tag_2 *arg) { return arg->p->a; } +noinline int +bpf_testmod_test_btf_type_tag_percpu_1(struct bpf_testmod_btf_type_tag_1 __percpu *arg) { + return arg->a; +} + +noinline int +bpf_testmod_test_btf_type_tag_percpu_2(struct bpf_testmod_btf_type_tag_3 *arg) { + return arg->p->a; +} + noinline int bpf_testmod_loop_test(int n) { int i, sum = 0; diff --git a/tools/testing/selftests/bpf/cap_helpers.c b/tools/testing/selftests/bpf/cap_helpers.c new file mode 100644 index 000000000000..d5ac507401d7 --- /dev/null +++ b/tools/testing/selftests/bpf/cap_helpers.c @@ -0,0 +1,67 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "cap_helpers.h" + +/* Avoid including <sys/capability.h> from the libcap-devel package, + * so directly declare them here and use them from glibc. + */ +int capget(cap_user_header_t header, cap_user_data_t data); +int capset(cap_user_header_t header, const cap_user_data_t data); + +int cap_enable_effective(__u64 caps, __u64 *old_caps) +{ + struct __user_cap_data_struct data[_LINUX_CAPABILITY_U32S_3]; + struct __user_cap_header_struct hdr = { + .version = _LINUX_CAPABILITY_VERSION_3, + }; + __u32 cap0 = caps; + __u32 cap1 = caps >> 32; + int err; + + err = capget(&hdr, data); + if (err) + return err; + + if (old_caps) + *old_caps = (__u64)(data[1].effective) << 32 | data[0].effective; + + if ((data[0].effective & cap0) == cap0 && + (data[1].effective & cap1) == cap1) + return 0; + + data[0].effective |= cap0; + data[1].effective |= cap1; + err = capset(&hdr, data); + if (err) + return err; + + return 0; +} + +int cap_disable_effective(__u64 caps, __u64 *old_caps) +{ + struct __user_cap_data_struct data[_LINUX_CAPABILITY_U32S_3]; + struct __user_cap_header_struct hdr = { + .version = _LINUX_CAPABILITY_VERSION_3, + }; + __u32 cap0 = caps; + __u32 cap1 = caps >> 32; + int err; + + err = capget(&hdr, data); + if (err) + return err; + + if (old_caps) + *old_caps = (__u64)(data[1].effective) << 32 | data[0].effective; + + if (!(data[0].effective & cap0) && !(data[1].effective & cap1)) + return 0; + + data[0].effective &= ~cap0; + data[1].effective &= ~cap1; + err = capset(&hdr, data); + if (err) + return err; + + return 0; +} diff --git a/tools/testing/selftests/bpf/cap_helpers.h b/tools/testing/selftests/bpf/cap_helpers.h new file mode 100644 index 000000000000..6d163530cb0f --- /dev/null +++ b/tools/testing/selftests/bpf/cap_helpers.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __CAP_HELPERS_H +#define __CAP_HELPERS_H + +#include <linux/types.h> +#include <linux/capability.h> + +#ifndef CAP_PERFMON +#define CAP_PERFMON 38 +#endif + +#ifndef CAP_BPF +#define CAP_BPF 39 +#endif + +int cap_enable_effective(__u64 caps, __u64 *old_caps); +int cap_disable_effective(__u64 caps, __u64 *old_caps); + +#endif diff --git a/tools/testing/selftests/bpf/ima_setup.sh b/tools/testing/selftests/bpf/ima_setup.sh index 8e62581113a3..8ecead4ccad0 100755 --- a/tools/testing/selftests/bpf/ima_setup.sh +++ b/tools/testing/selftests/bpf/ima_setup.sh @@ -12,7 +12,7 @@ LOG_FILE="$(mktemp /tmp/ima_setup.XXXX.log)" usage() { - echo "Usage: $0 <setup|cleanup|run> <existing_tmp_dir>" + echo "Usage: $0 <setup|cleanup|run|modify-bin|restore-bin|load-policy> <existing_tmp_dir>" exit 1 } @@ -51,6 +51,7 @@ setup() ensure_mount_securityfs echo "measure func=BPRM_CHECK fsuuid=${mount_uuid}" > ${IMA_POLICY_FILE} + echo "measure func=BPRM_CHECK fsuuid=${mount_uuid}" > ${mount_dir}/policy_test } cleanup() { @@ -77,6 +78,32 @@ run() exec "${copied_bin_path}" } +modify_bin() +{ + local tmp_dir="$1" + local mount_dir="${tmp_dir}/mnt" + local copied_bin_path="${mount_dir}/$(basename ${TEST_BINARY})" + + echo "mod" >> "${copied_bin_path}" +} + +restore_bin() +{ + local tmp_dir="$1" + local mount_dir="${tmp_dir}/mnt" + local copied_bin_path="${mount_dir}/$(basename ${TEST_BINARY})" + + truncate -s -4 "${copied_bin_path}" +} + +load_policy() +{ + local tmp_dir="$1" + local mount_dir="${tmp_dir}/mnt" + + echo ${mount_dir}/policy_test > ${IMA_POLICY_FILE} 2> /dev/null +} + catch() { local exit_code="$1" @@ -105,6 +132,12 @@ main() cleanup "${tmp_dir}" elif [[ "${action}" == "run" ]]; then run "${tmp_dir}" + elif [[ "${action}" == "modify-bin" ]]; then + modify_bin "${tmp_dir}" + elif [[ "${action}" == "restore-bin" ]]; then + restore_bin "${tmp_dir}" + elif [[ "${action}" == "load-policy" ]]; then + load_policy "${tmp_dir}" else echo "Unknown action: ${action}" exit 1 diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index 6db1af8fdee7..2bb1f9b3841d 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -1,18 +1,25 @@ // SPDX-License-Identifier: GPL-2.0-only +#define _GNU_SOURCE + #include <errno.h> #include <stdbool.h> #include <stdio.h> #include <string.h> #include <unistd.h> +#include <sched.h> #include <arpa/inet.h> +#include <sys/mount.h> +#include <sys/stat.h> #include <linux/err.h> #include <linux/in.h> #include <linux/in6.h> +#include <linux/limits.h> #include "bpf_util.h" #include "network_helpers.h" +#include "test_progs.h" #define clean_errno() (errno == 0 ? "None" : strerror(errno)) #define log_err(MSG, ...) ({ \ @@ -356,3 +363,82 @@ char *ping_command(int family) } return "ping"; } + +struct nstoken { + int orig_netns_fd; +}; + +static int setns_by_fd(int nsfd) +{ + int err; + + err = setns(nsfd, CLONE_NEWNET); + close(nsfd); + + if (!ASSERT_OK(err, "setns")) + return err; + + /* Switch /sys to the new namespace so that e.g. /sys/class/net + * reflects the devices in the new namespace. + */ + err = unshare(CLONE_NEWNS); + if (!ASSERT_OK(err, "unshare")) + return err; + + /* Make our /sys mount private, so the following umount won't + * trigger the global umount in case it's shared. + */ + err = mount("none", "/sys", NULL, MS_PRIVATE, NULL); + if (!ASSERT_OK(err, "remount private /sys")) + return err; + + err = umount2("/sys", MNT_DETACH); + if (!ASSERT_OK(err, "umount2 /sys")) + return err; + + err = mount("sysfs", "/sys", "sysfs", 0, NULL); + if (!ASSERT_OK(err, "mount /sys")) + return err; + + err = mount("bpffs", "/sys/fs/bpf", "bpf", 0, NULL); + if (!ASSERT_OK(err, "mount /sys/fs/bpf")) + return err; + + return 0; +} + +struct nstoken *open_netns(const char *name) +{ + int nsfd; + char nspath[PATH_MAX]; + int err; + struct nstoken *token; + + token = malloc(sizeof(struct nstoken)); + if (!ASSERT_OK_PTR(token, "malloc token")) + return NULL; + + token->orig_netns_fd = open("/proc/self/ns/net", O_RDONLY); + if (!ASSERT_GE(token->orig_netns_fd, 0, "open /proc/self/ns/net")) + goto fail; + + snprintf(nspath, sizeof(nspath), "%s/%s", "/var/run/netns", name); + nsfd = open(nspath, O_RDONLY | O_CLOEXEC); + if (!ASSERT_GE(nsfd, 0, "open netns fd")) + goto fail; + + err = setns_by_fd(nsfd); + if (!ASSERT_OK(err, "setns_by_fd")) + goto fail; + + return token; +fail: + free(token); + return NULL; +} + +void close_netns(struct nstoken *token) +{ + ASSERT_OK(setns_by_fd(token->orig_netns_fd), "setns_by_fd"); + free(token); +} diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h index d198181a5648..a4b3b2f9877b 100644 --- a/tools/testing/selftests/bpf/network_helpers.h +++ b/tools/testing/selftests/bpf/network_helpers.h @@ -55,4 +55,13 @@ int make_sockaddr(int family, const char *addr_str, __u16 port, struct sockaddr_storage *addr, socklen_t *len); char *ping_command(int family); +struct nstoken; +/** + * open_netns() - Switch to specified network namespace by name. + * + * Returns token with which to restore the original namespace + * using close_netns(). + */ +struct nstoken *open_netns(const char *name); +void close_netns(struct nstoken *token); #endif diff --git a/tools/testing/selftests/bpf/prog_tests/bind_perm.c b/tools/testing/selftests/bpf/prog_tests/bind_perm.c index eac71fbb24ce..a1766a298bb7 100644 --- a/tools/testing/selftests/bpf/prog_tests/bind_perm.c +++ b/tools/testing/selftests/bpf/prog_tests/bind_perm.c @@ -4,9 +4,9 @@ #include <stdlib.h> #include <sys/types.h> #include <sys/socket.h> -#include <sys/capability.h> #include "test_progs.h" +#include "cap_helpers.h" #include "bind_perm.skel.h" static int duration; @@ -49,41 +49,11 @@ close_socket: close(fd); } -bool cap_net_bind_service(cap_flag_value_t flag) -{ - const cap_value_t cap_net_bind_service = CAP_NET_BIND_SERVICE; - cap_flag_value_t original_value; - bool was_effective = false; - cap_t caps; - - caps = cap_get_proc(); - if (CHECK(!caps, "cap_get_proc", "errno %d", errno)) - goto free_caps; - - if (CHECK(cap_get_flag(caps, CAP_NET_BIND_SERVICE, CAP_EFFECTIVE, - &original_value), - "cap_get_flag", "errno %d", errno)) - goto free_caps; - - was_effective = (original_value == CAP_SET); - - if (CHECK(cap_set_flag(caps, CAP_EFFECTIVE, 1, &cap_net_bind_service, - flag), - "cap_set_flag", "errno %d", errno)) - goto free_caps; - - if (CHECK(cap_set_proc(caps), "cap_set_proc", "errno %d", errno)) - goto free_caps; - -free_caps: - CHECK(cap_free(caps), "cap_free", "errno %d", errno); - return was_effective; -} - void test_bind_perm(void) { - bool cap_was_effective; + const __u64 net_bind_svc_cap = 1ULL << CAP_NET_BIND_SERVICE; struct bind_perm *skel; + __u64 old_caps = 0; int cgroup_fd; if (create_netns()) @@ -105,7 +75,8 @@ void test_bind_perm(void) if (!ASSERT_OK_PTR(skel, "bind_v6_prog")) goto close_skeleton; - cap_was_effective = cap_net_bind_service(CAP_CLEAR); + ASSERT_OK(cap_disable_effective(net_bind_svc_cap, &old_caps), + "cap_disable_effective"); try_bind(AF_INET, 110, EACCES); try_bind(AF_INET6, 110, EACCES); @@ -113,8 +84,9 @@ void test_bind_perm(void) try_bind(AF_INET, 111, 0); try_bind(AF_INET6, 111, 0); - if (cap_was_effective) - cap_net_bind_service(CAP_SET); + if (old_caps & net_bind_svc_cap) + ASSERT_OK(cap_enable_effective(net_bind_svc_cap, NULL), + "cap_enable_effective"); close_skeleton: bind_perm__destroy(skel); diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c index cd10df6cd0fc..923a6139b2d8 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c @@ -7,6 +7,7 @@ #include <unistd.h> #include <test_progs.h> #include "test_bpf_cookie.skel.h" +#include "kprobe_multi.skel.h" /* uprobe attach point */ static void trigger_func(void) @@ -63,6 +64,178 @@ cleanup: bpf_link__destroy(retlink2); } +static void kprobe_multi_test_run(struct kprobe_multi *skel) +{ + LIBBPF_OPTS(bpf_test_run_opts, topts); + int err, prog_fd; + + prog_fd = bpf_program__fd(skel->progs.trigger); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, 0, "test_run"); + + ASSERT_EQ(skel->bss->kprobe_test1_result, 1, "kprobe_test1_result"); + ASSERT_EQ(skel->bss->kprobe_test2_result, 1, "kprobe_test2_result"); + ASSERT_EQ(skel->bss->kprobe_test3_result, 1, "kprobe_test3_result"); + ASSERT_EQ(skel->bss->kprobe_test4_result, 1, "kprobe_test4_result"); + ASSERT_EQ(skel->bss->kprobe_test5_result, 1, "kprobe_test5_result"); + ASSERT_EQ(skel->bss->kprobe_test6_result, 1, "kprobe_test6_result"); + ASSERT_EQ(skel->bss->kprobe_test7_result, 1, "kprobe_test7_result"); + ASSERT_EQ(skel->bss->kprobe_test8_result, 1, "kprobe_test8_result"); + + ASSERT_EQ(skel->bss->kretprobe_test1_result, 1, "kretprobe_test1_result"); + ASSERT_EQ(skel->bss->kretprobe_test2_result, 1, "kretprobe_test2_result"); + ASSERT_EQ(skel->bss->kretprobe_test3_result, 1, "kretprobe_test3_result"); + ASSERT_EQ(skel->bss->kretprobe_test4_result, 1, "kretprobe_test4_result"); + ASSERT_EQ(skel->bss->kretprobe_test5_result, 1, "kretprobe_test5_result"); + ASSERT_EQ(skel->bss->kretprobe_test6_result, 1, "kretprobe_test6_result"); + ASSERT_EQ(skel->bss->kretprobe_test7_result, 1, "kretprobe_test7_result"); + ASSERT_EQ(skel->bss->kretprobe_test8_result, 1, "kretprobe_test8_result"); +} + +static void kprobe_multi_link_api_subtest(void) +{ + int prog_fd, link1_fd = -1, link2_fd = -1; + struct kprobe_multi *skel = NULL; + LIBBPF_OPTS(bpf_link_create_opts, opts); + unsigned long long addrs[8]; + __u64 cookies[8]; + + if (!ASSERT_OK(load_kallsyms(), "load_kallsyms")) + goto cleanup; + + skel = kprobe_multi__open_and_load(); + if (!ASSERT_OK_PTR(skel, "fentry_raw_skel_load")) + goto cleanup; + + skel->bss->pid = getpid(); + skel->bss->test_cookie = true; + +#define GET_ADDR(__sym, __addr) ({ \ + __addr = ksym_get_addr(__sym); \ + if (!ASSERT_NEQ(__addr, 0, "ksym_get_addr " #__sym)) \ + goto cleanup; \ +}) + + GET_ADDR("bpf_fentry_test1", addrs[0]); + GET_ADDR("bpf_fentry_test2", addrs[1]); + GET_ADDR("bpf_fentry_test3", addrs[2]); + GET_ADDR("bpf_fentry_test4", addrs[3]); + GET_ADDR("bpf_fentry_test5", addrs[4]); + GET_ADDR("bpf_fentry_test6", addrs[5]); + GET_ADDR("bpf_fentry_test7", addrs[6]); + GET_ADDR("bpf_fentry_test8", addrs[7]); + +#undef GET_ADDR + + cookies[0] = 1; + cookies[1] = 2; + cookies[2] = 3; + cookies[3] = 4; + cookies[4] = 5; + cookies[5] = 6; + cookies[6] = 7; + cookies[7] = 8; + + opts.kprobe_multi.addrs = (const unsigned long *) &addrs; + opts.kprobe_multi.cnt = ARRAY_SIZE(addrs); + opts.kprobe_multi.cookies = (const __u64 *) &cookies; + prog_fd = bpf_program__fd(skel->progs.test_kprobe); + + link1_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_KPROBE_MULTI, &opts); + if (!ASSERT_GE(link1_fd, 0, "link1_fd")) + goto cleanup; + + cookies[0] = 8; + cookies[1] = 7; + cookies[2] = 6; + cookies[3] = 5; + cookies[4] = 4; + cookies[5] = 3; + cookies[6] = 2; + cookies[7] = 1; + + opts.kprobe_multi.flags = BPF_F_KPROBE_MULTI_RETURN; + prog_fd = bpf_program__fd(skel->progs.test_kretprobe); + + link2_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_KPROBE_MULTI, &opts); + if (!ASSERT_GE(link2_fd, 0, "link2_fd")) + goto cleanup; + + kprobe_multi_test_run(skel); + +cleanup: + close(link1_fd); + close(link2_fd); + kprobe_multi__destroy(skel); +} + +static void kprobe_multi_attach_api_subtest(void) +{ + struct bpf_link *link1 = NULL, *link2 = NULL; + LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); + LIBBPF_OPTS(bpf_test_run_opts, topts); + struct kprobe_multi *skel = NULL; + const char *syms[8] = { + "bpf_fentry_test1", + "bpf_fentry_test2", + "bpf_fentry_test3", + "bpf_fentry_test4", + "bpf_fentry_test5", + "bpf_fentry_test6", + "bpf_fentry_test7", + "bpf_fentry_test8", + }; + __u64 cookies[8]; + + skel = kprobe_multi__open_and_load(); + if (!ASSERT_OK_PTR(skel, "fentry_raw_skel_load")) + goto cleanup; + + skel->bss->pid = getpid(); + skel->bss->test_cookie = true; + + cookies[0] = 1; + cookies[1] = 2; + cookies[2] = 3; + cookies[3] = 4; + cookies[4] = 5; + cookies[5] = 6; + cookies[6] = 7; + cookies[7] = 8; + + opts.syms = syms; + opts.cnt = ARRAY_SIZE(syms); + opts.cookies = cookies; + + link1 = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe, + NULL, &opts); + if (!ASSERT_OK_PTR(link1, "bpf_program__attach_kprobe_multi_opts")) + goto cleanup; + + cookies[0] = 8; + cookies[1] = 7; + cookies[2] = 6; + cookies[3] = 5; + cookies[4] = 4; + cookies[5] = 3; + cookies[6] = 2; + cookies[7] = 1; + + opts.retprobe = true; + + link2 = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kretprobe, + NULL, &opts); + if (!ASSERT_OK_PTR(link2, "bpf_program__attach_kprobe_multi_opts")) + goto cleanup; + + kprobe_multi_test_run(skel); + +cleanup: + bpf_link__destroy(link2); + bpf_link__destroy(link1); + kprobe_multi__destroy(skel); +} static void uprobe_subtest(struct test_bpf_cookie *skel) { DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, opts); @@ -199,7 +372,7 @@ static void pe_subtest(struct test_bpf_cookie *skel) attr.type = PERF_TYPE_SOFTWARE; attr.config = PERF_COUNT_SW_CPU_CLOCK; attr.freq = 1; - attr.sample_freq = 4000; + attr.sample_freq = 1000; pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC); if (!ASSERT_GE(pfd, 0, "perf_fd")) goto cleanup; @@ -249,6 +422,10 @@ void test_bpf_cookie(void) if (test__start_subtest("kprobe")) kprobe_subtest(skel); + if (test__start_subtest("multi_kprobe_link_api")) + kprobe_multi_link_api_subtest(); + if (test__start_subtest("multi_kprobe_attach_api")) + kprobe_multi_attach_api_subtest(); if (test__start_subtest("uprobe")) uprobe_subtest(skel); if (test__start_subtest("tracepoint")) diff --git a/tools/testing/selftests/bpf/prog_tests/btf_tag.c b/tools/testing/selftests/bpf/prog_tests/btf_tag.c index f7560b54a6bb..071430cd54de 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_tag.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_tag.c @@ -10,6 +10,7 @@ struct btf_type_tag_test { }; #include "btf_type_tag.skel.h" #include "btf_type_tag_user.skel.h" +#include "btf_type_tag_percpu.skel.h" static void test_btf_decl_tag(void) { @@ -43,38 +44,81 @@ static void test_btf_type_tag(void) btf_type_tag__destroy(skel); } -static void test_btf_type_tag_mod_user(bool load_test_user1) +/* loads vmlinux_btf as well as module_btf. If the caller passes NULL as + * module_btf, it will not load module btf. + * + * Returns 0 on success. + * Return -1 On error. In case of error, the loaded btf will be freed and the + * input parameters will be set to pointing to NULL. + */ +static int load_btfs(struct btf **vmlinux_btf, struct btf **module_btf, + bool needs_vmlinux_tag) { const char *module_name = "bpf_testmod"; - struct btf *vmlinux_btf, *module_btf; - struct btf_type_tag_user *skel; __s32 type_id; - int err; if (!env.has_testmod) { test__skip(); - return; + return -1; } - /* skip the test if the module does not have __user tags */ - vmlinux_btf = btf__load_vmlinux_btf(); - if (!ASSERT_OK_PTR(vmlinux_btf, "could not load vmlinux BTF")) - return; + *vmlinux_btf = btf__load_vmlinux_btf(); + if (!ASSERT_OK_PTR(*vmlinux_btf, "could not load vmlinux BTF")) + return -1; + + if (!needs_vmlinux_tag) + goto load_module_btf; - module_btf = btf__load_module_btf(module_name, vmlinux_btf); - if (!ASSERT_OK_PTR(module_btf, "could not load module BTF")) + /* skip the test if the vmlinux does not have __user tags */ + type_id = btf__find_by_name_kind(*vmlinux_btf, "user", BTF_KIND_TYPE_TAG); + if (type_id <= 0) { + printf("%s:SKIP: btf_type_tag attribute not in vmlinux btf", __func__); + test__skip(); goto free_vmlinux_btf; + } - type_id = btf__find_by_name_kind(module_btf, "user", BTF_KIND_TYPE_TAG); +load_module_btf: + /* skip loading module_btf, if not requested by caller */ + if (!module_btf) + return 0; + + *module_btf = btf__load_module_btf(module_name, *vmlinux_btf); + if (!ASSERT_OK_PTR(*module_btf, "could not load module BTF")) + goto free_vmlinux_btf; + + /* skip the test if the module does not have __user tags */ + type_id = btf__find_by_name_kind(*module_btf, "user", BTF_KIND_TYPE_TAG); if (type_id <= 0) { printf("%s:SKIP: btf_type_tag attribute not in %s", __func__, module_name); test__skip(); goto free_module_btf; } + return 0; + +free_module_btf: + btf__free(*module_btf); +free_vmlinux_btf: + btf__free(*vmlinux_btf); + + *vmlinux_btf = NULL; + if (module_btf) + *module_btf = NULL; + return -1; +} + +static void test_btf_type_tag_mod_user(bool load_test_user1) +{ + struct btf *vmlinux_btf = NULL, *module_btf = NULL; + struct btf_type_tag_user *skel; + int err; + + if (load_btfs(&vmlinux_btf, &module_btf, /*needs_vmlinux_tag=*/false)) + return; + skel = btf_type_tag_user__open(); if (!ASSERT_OK_PTR(skel, "btf_type_tag_user")) - goto free_module_btf; + goto cleanup; bpf_program__set_autoload(skel->progs.test_sys_getsockname, false); if (load_test_user1) @@ -87,34 +131,23 @@ static void test_btf_type_tag_mod_user(bool load_test_user1) btf_type_tag_user__destroy(skel); -free_module_btf: +cleanup: btf__free(module_btf); -free_vmlinux_btf: btf__free(vmlinux_btf); } static void test_btf_type_tag_vmlinux_user(void) { struct btf_type_tag_user *skel; - struct btf *vmlinux_btf; - __s32 type_id; + struct btf *vmlinux_btf = NULL; int err; - /* skip the test if the vmlinux does not have __user tags */ - vmlinux_btf = btf__load_vmlinux_btf(); - if (!ASSERT_OK_PTR(vmlinux_btf, "could not load vmlinux BTF")) + if (load_btfs(&vmlinux_btf, NULL, /*needs_vmlinux_tag=*/true)) return; - type_id = btf__find_by_name_kind(vmlinux_btf, "user", BTF_KIND_TYPE_TAG); - if (type_id <= 0) { - printf("%s:SKIP: btf_type_tag attribute not in vmlinux btf", __func__); - test__skip(); - goto free_vmlinux_btf; - } - skel = btf_type_tag_user__open(); if (!ASSERT_OK_PTR(skel, "btf_type_tag_user")) - goto free_vmlinux_btf; + goto cleanup; bpf_program__set_autoload(skel->progs.test_user2, false); bpf_program__set_autoload(skel->progs.test_user1, false); @@ -124,7 +157,70 @@ static void test_btf_type_tag_vmlinux_user(void) btf_type_tag_user__destroy(skel); -free_vmlinux_btf: +cleanup: + btf__free(vmlinux_btf); +} + +static void test_btf_type_tag_mod_percpu(bool load_test_percpu1) +{ + struct btf *vmlinux_btf, *module_btf; + struct btf_type_tag_percpu *skel; + int err; + + if (load_btfs(&vmlinux_btf, &module_btf, /*needs_vmlinux_tag=*/false)) + return; + + skel = btf_type_tag_percpu__open(); + if (!ASSERT_OK_PTR(skel, "btf_type_tag_percpu")) + goto cleanup; + + bpf_program__set_autoload(skel->progs.test_percpu_load, false); + bpf_program__set_autoload(skel->progs.test_percpu_helper, false); + if (load_test_percpu1) + bpf_program__set_autoload(skel->progs.test_percpu2, false); + else + bpf_program__set_autoload(skel->progs.test_percpu1, false); + + err = btf_type_tag_percpu__load(skel); + ASSERT_ERR(err, "btf_type_tag_percpu"); + + btf_type_tag_percpu__destroy(skel); + +cleanup: + btf__free(module_btf); + btf__free(vmlinux_btf); +} + +static void test_btf_type_tag_vmlinux_percpu(bool load_test) +{ + struct btf_type_tag_percpu *skel; + struct btf *vmlinux_btf = NULL; + int err; + + if (load_btfs(&vmlinux_btf, NULL, /*needs_vmlinux_tag=*/true)) + return; + + skel = btf_type_tag_percpu__open(); + if (!ASSERT_OK_PTR(skel, "btf_type_tag_percpu")) + goto cleanup; + + bpf_program__set_autoload(skel->progs.test_percpu2, false); + bpf_program__set_autoload(skel->progs.test_percpu1, false); + if (load_test) { + bpf_program__set_autoload(skel->progs.test_percpu_helper, false); + + err = btf_type_tag_percpu__load(skel); + ASSERT_ERR(err, "btf_type_tag_percpu_load"); + } else { + bpf_program__set_autoload(skel->progs.test_percpu_load, false); + + err = btf_type_tag_percpu__load(skel); + ASSERT_OK(err, "btf_type_tag_percpu_helper"); + } + + btf_type_tag_percpu__destroy(skel); + +cleanup: btf__free(vmlinux_btf); } @@ -134,10 +230,20 @@ void test_btf_tag(void) test_btf_decl_tag(); if (test__start_subtest("btf_type_tag")) test_btf_type_tag(); + if (test__start_subtest("btf_type_tag_user_mod1")) test_btf_type_tag_mod_user(true); if (test__start_subtest("btf_type_tag_user_mod2")) test_btf_type_tag_mod_user(false); if (test__start_subtest("btf_type_tag_sys_user_vmlinux")) test_btf_type_tag_vmlinux_user(); + + if (test__start_subtest("btf_type_tag_percpu_mod1")) + test_btf_type_tag_mod_percpu(true); + if (test__start_subtest("btf_type_tag_percpu_mod2")) + test_btf_type_tag_mod_percpu(false); + if (test__start_subtest("btf_type_tag_percpu_vmlinux_load")) + test_btf_type_tag_vmlinux_percpu(true); + if (test__start_subtest("btf_type_tag_percpu_vmlinux_helper")) + test_btf_type_tag_vmlinux_percpu(false); } diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c index 858916d11e2e..9367bd2f0ae1 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c @@ -14,7 +14,7 @@ static int prog_load(void) BPF_MOV64_IMM(BPF_REG_0, 1), /* r0 = 1 */ BPF_EXIT_INSN(), }; - size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); + size_t insns_cnt = ARRAY_SIZE(prog); return bpf_test_load_program(BPF_PROG_TYPE_CGROUP_SKB, prog, insns_cnt, "GPL", 0, diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c index 38b3c47293da..db0b7bac78d1 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c @@ -63,7 +63,7 @@ static int prog_load_cnt(int verdict, int val) BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */ BPF_EXIT_INSN(), }; - size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); + size_t insns_cnt = ARRAY_SIZE(prog); int ret; ret = bpf_test_load_program(BPF_PROG_TYPE_CGROUP_SKB, diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c index 356547e849e2..9421a5b7f4e1 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c @@ -16,7 +16,7 @@ static int prog_load(int verdict) BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */ BPF_EXIT_INSN(), }; - size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); + size_t insns_cnt = ARRAY_SIZE(prog); return bpf_test_load_program(BPF_PROG_TYPE_CGROUP_SKB, prog, insns_cnt, "GPL", 0, diff --git a/tools/testing/selftests/bpf/prog_tests/custom_sec_handlers.c b/tools/testing/selftests/bpf/prog_tests/custom_sec_handlers.c new file mode 100644 index 000000000000..b2dfc5954aea --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/custom_sec_handlers.c @@ -0,0 +1,176 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Facebook */ + +#include <test_progs.h> +#include "test_custom_sec_handlers.skel.h" + +#define COOKIE_ABC1 1 +#define COOKIE_ABC2 2 +#define COOKIE_CUSTOM 3 +#define COOKIE_FALLBACK 4 +#define COOKIE_KPROBE 5 + +static int custom_setup_prog(struct bpf_program *prog, long cookie) +{ + if (cookie == COOKIE_ABC1) + bpf_program__set_autoload(prog, false); + + return 0; +} + +static int custom_prepare_load_prog(struct bpf_program *prog, + struct bpf_prog_load_opts *opts, long cookie) +{ + if (cookie == COOKIE_FALLBACK) + opts->prog_flags |= BPF_F_SLEEPABLE; + else if (cookie == COOKIE_ABC1) + ASSERT_FALSE(true, "unexpected preload for abc"); + + return 0; +} + +static int custom_attach_prog(const struct bpf_program *prog, long cookie, + struct bpf_link **link) +{ + switch (cookie) { + case COOKIE_ABC2: + *link = bpf_program__attach_raw_tracepoint(prog, "sys_enter"); + return libbpf_get_error(*link); + case COOKIE_CUSTOM: + *link = bpf_program__attach_tracepoint(prog, "syscalls", "sys_enter_nanosleep"); + return libbpf_get_error(*link); + case COOKIE_KPROBE: + case COOKIE_FALLBACK: + /* no auto-attach for SEC("xyz") and SEC("kprobe") */ + *link = NULL; + return 0; + default: + ASSERT_FALSE(true, "unexpected cookie"); + return -EINVAL; + } +} + +static int abc1_id; +static int abc2_id; +static int custom_id; +static int fallback_id; +static int kprobe_id; + +__attribute__((constructor)) +static void register_sec_handlers(void) +{ + LIBBPF_OPTS(libbpf_prog_handler_opts, abc1_opts, + .cookie = COOKIE_ABC1, + .prog_setup_fn = custom_setup_prog, + .prog_prepare_load_fn = custom_prepare_load_prog, + .prog_attach_fn = NULL, + ); + LIBBPF_OPTS(libbpf_prog_handler_opts, abc2_opts, + .cookie = COOKIE_ABC2, + .prog_setup_fn = custom_setup_prog, + .prog_prepare_load_fn = custom_prepare_load_prog, + .prog_attach_fn = custom_attach_prog, + ); + LIBBPF_OPTS(libbpf_prog_handler_opts, custom_opts, + .cookie = COOKIE_CUSTOM, + .prog_setup_fn = NULL, + .prog_prepare_load_fn = NULL, + .prog_attach_fn = custom_attach_prog, + ); + + abc1_id = libbpf_register_prog_handler("abc", BPF_PROG_TYPE_RAW_TRACEPOINT, 0, &abc1_opts); + abc2_id = libbpf_register_prog_handler("abc/", BPF_PROG_TYPE_RAW_TRACEPOINT, 0, &abc2_opts); + custom_id = libbpf_register_prog_handler("custom+", BPF_PROG_TYPE_TRACEPOINT, 0, &custom_opts); +} + +__attribute__((destructor)) +static void unregister_sec_handlers(void) +{ + libbpf_unregister_prog_handler(abc1_id); + libbpf_unregister_prog_handler(abc2_id); + libbpf_unregister_prog_handler(custom_id); +} + +void test_custom_sec_handlers(void) +{ + LIBBPF_OPTS(libbpf_prog_handler_opts, opts, + .prog_setup_fn = custom_setup_prog, + .prog_prepare_load_fn = custom_prepare_load_prog, + .prog_attach_fn = custom_attach_prog, + ); + struct test_custom_sec_handlers* skel; + int err; + + ASSERT_GT(abc1_id, 0, "abc1_id"); + ASSERT_GT(abc2_id, 0, "abc2_id"); + ASSERT_GT(custom_id, 0, "custom_id"); + + /* override libbpf's handle of SEC("kprobe/...") but also allow pure + * SEC("kprobe") due to "kprobe+" specifier. Register it as + * TRACEPOINT, just for fun. + */ + opts.cookie = COOKIE_KPROBE; + kprobe_id = libbpf_register_prog_handler("kprobe+", BPF_PROG_TYPE_TRACEPOINT, 0, &opts); + /* fallback treats everything as BPF_PROG_TYPE_SYSCALL program to test + * setting custom BPF_F_SLEEPABLE bit in preload handler + */ + opts.cookie = COOKIE_FALLBACK; + fallback_id = libbpf_register_prog_handler(NULL, BPF_PROG_TYPE_SYSCALL, 0, &opts); + + if (!ASSERT_GT(fallback_id, 0, "fallback_id") /* || !ASSERT_GT(kprobe_id, 0, "kprobe_id")*/) { + if (fallback_id > 0) + libbpf_unregister_prog_handler(fallback_id); + if (kprobe_id > 0) + libbpf_unregister_prog_handler(kprobe_id); + return; + } + + /* open skeleton and validate assumptions */ + skel = test_custom_sec_handlers__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + ASSERT_EQ(bpf_program__type(skel->progs.abc1), BPF_PROG_TYPE_RAW_TRACEPOINT, "abc1_type"); + ASSERT_FALSE(bpf_program__autoload(skel->progs.abc1), "abc1_autoload"); + + ASSERT_EQ(bpf_program__type(skel->progs.abc2), BPF_PROG_TYPE_RAW_TRACEPOINT, "abc2_type"); + ASSERT_EQ(bpf_program__type(skel->progs.custom1), BPF_PROG_TYPE_TRACEPOINT, "custom1_type"); + ASSERT_EQ(bpf_program__type(skel->progs.custom2), BPF_PROG_TYPE_TRACEPOINT, "custom2_type"); + ASSERT_EQ(bpf_program__type(skel->progs.kprobe1), BPF_PROG_TYPE_TRACEPOINT, "kprobe1_type"); + ASSERT_EQ(bpf_program__type(skel->progs.xyz), BPF_PROG_TYPE_SYSCALL, "xyz_type"); + + skel->rodata->my_pid = getpid(); + + /* now attempt to load everything */ + err = test_custom_sec_handlers__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + /* now try to auto-attach everything */ + err = test_custom_sec_handlers__attach(skel); + if (!ASSERT_OK(err, "skel_attach")) + goto cleanup; + + skel->links.xyz = bpf_program__attach(skel->progs.kprobe1); + ASSERT_EQ(errno, EOPNOTSUPP, "xyz_attach_err"); + ASSERT_ERR_PTR(skel->links.xyz, "xyz_attach"); + + /* trigger programs */ + usleep(1); + + /* SEC("abc") is set to not auto-loaded */ + ASSERT_FALSE(skel->bss->abc1_called, "abc1_called"); + ASSERT_TRUE(skel->bss->abc2_called, "abc2_called"); + ASSERT_TRUE(skel->bss->custom1_called, "custom1_called"); + ASSERT_TRUE(skel->bss->custom2_called, "custom2_called"); + /* SEC("kprobe") shouldn't be auto-attached */ + ASSERT_FALSE(skel->bss->kprobe1_called, "kprobe1_called"); + /* SEC("xyz") shouldn't be auto-attached */ + ASSERT_FALSE(skel->bss->xyz_called, "xyz_called"); + +cleanup: + test_custom_sec_handlers__destroy(skel); + + ASSERT_OK(libbpf_unregister_prog_handler(fallback_id), "unregister_fallback"); + ASSERT_OK(libbpf_unregister_prog_handler(kprobe_id), "unregister_kprobe"); +} diff --git a/tools/testing/selftests/bpf/prog_tests/find_vma.c b/tools/testing/selftests/bpf/prog_tests/find_vma.c index b74b3c0c555a..5165b38f0e59 100644 --- a/tools/testing/selftests/bpf/prog_tests/find_vma.c +++ b/tools/testing/selftests/bpf/prog_tests/find_vma.c @@ -7,12 +7,14 @@ #include "find_vma_fail1.skel.h" #include "find_vma_fail2.skel.h" -static void test_and_reset_skel(struct find_vma *skel, int expected_find_zero_ret) +static void test_and_reset_skel(struct find_vma *skel, int expected_find_zero_ret, bool need_test) { - ASSERT_EQ(skel->bss->found_vm_exec, 1, "found_vm_exec"); - ASSERT_EQ(skel->data->find_addr_ret, 0, "find_addr_ret"); - ASSERT_EQ(skel->data->find_zero_ret, expected_find_zero_ret, "find_zero_ret"); - ASSERT_OK_PTR(strstr(skel->bss->d_iname, "test_progs"), "find_test_progs"); + if (need_test) { + ASSERT_EQ(skel->bss->found_vm_exec, 1, "found_vm_exec"); + ASSERT_EQ(skel->data->find_addr_ret, 0, "find_addr_ret"); + ASSERT_EQ(skel->data->find_zero_ret, expected_find_zero_ret, "find_zero_ret"); + ASSERT_OK_PTR(strstr(skel->bss->d_iname, "test_progs"), "find_test_progs"); + } skel->bss->found_vm_exec = 0; skel->data->find_addr_ret = -1; @@ -30,17 +32,26 @@ static int open_pe(void) attr.type = PERF_TYPE_HARDWARE; attr.config = PERF_COUNT_HW_CPU_CYCLES; attr.freq = 1; - attr.sample_freq = 4000; + attr.sample_freq = 1000; pfd = syscall(__NR_perf_event_open, &attr, 0, -1, -1, PERF_FLAG_FD_CLOEXEC); return pfd >= 0 ? pfd : -errno; } +static bool find_vma_pe_condition(struct find_vma *skel) +{ + return skel->bss->found_vm_exec == 0 || + skel->data->find_addr_ret != 0 || + skel->data->find_zero_ret == -1 || + strcmp(skel->bss->d_iname, "test_progs") != 0; +} + static void test_find_vma_pe(struct find_vma *skel) { struct bpf_link *link = NULL; volatile int j = 0; int pfd, i; + const int one_bn = 1000000000; pfd = open_pe(); if (pfd < 0) { @@ -57,10 +68,10 @@ static void test_find_vma_pe(struct find_vma *skel) if (!ASSERT_OK_PTR(link, "attach_perf_event")) goto cleanup; - for (i = 0; i < 1000000; ++i) + for (i = 0; i < one_bn && find_vma_pe_condition(skel); ++i) ++j; - test_and_reset_skel(skel, -EBUSY /* in nmi, irq_work is busy */); + test_and_reset_skel(skel, -EBUSY /* in nmi, irq_work is busy */, i == one_bn); cleanup: bpf_link__destroy(link); close(pfd); @@ -75,7 +86,7 @@ static void test_find_vma_kprobe(struct find_vma *skel) return; getpgid(skel->bss->target_pid); - test_and_reset_skel(skel, -ENOENT /* could not find vma for ptr 0 */); + test_and_reset_skel(skel, -ENOENT /* could not find vma for ptr 0 */, true); } static void test_illegal_write_vma(void) @@ -108,7 +119,6 @@ void serial_test_find_vma(void) skel->bss->addr = (__u64)(uintptr_t)test_find_vma_pe; test_find_vma_pe(skel); - usleep(100000); /* allow the irq_work to finish */ test_find_vma_kprobe(skel); find_vma__destroy(skel); diff --git a/tools/testing/selftests/bpf/prog_tests/global_data.c b/tools/testing/selftests/bpf/prog_tests/global_data.c index 6fb3d3155c35..027685858925 100644 --- a/tools/testing/selftests/bpf/prog_tests/global_data.c +++ b/tools/testing/selftests/bpf/prog_tests/global_data.c @@ -29,7 +29,7 @@ static void test_global_data_number(struct bpf_object *obj, __u32 duration) { "relocate .rodata reference", 10, ~0 }, }; - for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) { + for (i = 0; i < ARRAY_SIZE(tests); i++) { err = bpf_map_lookup_elem(map_fd, &tests[i].key, &num); CHECK(err || num != tests[i].num, tests[i].name, "err %d result %llx expected %llx\n", @@ -58,7 +58,7 @@ static void test_global_data_string(struct bpf_object *obj, __u32 duration) { "relocate .bss reference", 4, "\0\0hello" }, }; - for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) { + for (i = 0; i < ARRAY_SIZE(tests); i++) { err = bpf_map_lookup_elem(map_fd, &tests[i].key, str); CHECK(err || memcmp(str, tests[i].str, sizeof(str)), tests[i].name, "err %d result \'%s\' expected \'%s\'\n", @@ -92,7 +92,7 @@ static void test_global_data_struct(struct bpf_object *obj, __u32 duration) { "relocate .data reference", 3, { 41, 0xeeeeefef, 0x2111111111111111ULL, } }, }; - for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) { + for (i = 0; i < ARRAY_SIZE(tests); i++) { err = bpf_map_lookup_elem(map_fd, &tests[i].key, &val); CHECK(err || memcmp(&val, &tests[i].val, sizeof(val)), tests[i].name, "err %d result { %u, %u, %llu } expected { %u, %u, %llu }\n", diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c new file mode 100644 index 000000000000..b9876b55fc0c --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c @@ -0,0 +1,323 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include "kprobe_multi.skel.h" +#include "trace_helpers.h" + +static void kprobe_multi_test_run(struct kprobe_multi *skel, bool test_return) +{ + LIBBPF_OPTS(bpf_test_run_opts, topts); + int err, prog_fd; + + prog_fd = bpf_program__fd(skel->progs.trigger); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, 0, "test_run"); + + ASSERT_EQ(skel->bss->kprobe_test1_result, 1, "kprobe_test1_result"); + ASSERT_EQ(skel->bss->kprobe_test2_result, 1, "kprobe_test2_result"); + ASSERT_EQ(skel->bss->kprobe_test3_result, 1, "kprobe_test3_result"); + ASSERT_EQ(skel->bss->kprobe_test4_result, 1, "kprobe_test4_result"); + ASSERT_EQ(skel->bss->kprobe_test5_result, 1, "kprobe_test5_result"); + ASSERT_EQ(skel->bss->kprobe_test6_result, 1, "kprobe_test6_result"); + ASSERT_EQ(skel->bss->kprobe_test7_result, 1, "kprobe_test7_result"); + ASSERT_EQ(skel->bss->kprobe_test8_result, 1, "kprobe_test8_result"); + + if (test_return) { + ASSERT_EQ(skel->bss->kretprobe_test1_result, 1, "kretprobe_test1_result"); + ASSERT_EQ(skel->bss->kretprobe_test2_result, 1, "kretprobe_test2_result"); + ASSERT_EQ(skel->bss->kretprobe_test3_result, 1, "kretprobe_test3_result"); + ASSERT_EQ(skel->bss->kretprobe_test4_result, 1, "kretprobe_test4_result"); + ASSERT_EQ(skel->bss->kretprobe_test5_result, 1, "kretprobe_test5_result"); + ASSERT_EQ(skel->bss->kretprobe_test6_result, 1, "kretprobe_test6_result"); + ASSERT_EQ(skel->bss->kretprobe_test7_result, 1, "kretprobe_test7_result"); + ASSERT_EQ(skel->bss->kretprobe_test8_result, 1, "kretprobe_test8_result"); + } +} + +static void test_skel_api(void) +{ + struct kprobe_multi *skel = NULL; + int err; + + skel = kprobe_multi__open_and_load(); + if (!ASSERT_OK_PTR(skel, "kprobe_multi__open_and_load")) + goto cleanup; + + skel->bss->pid = getpid(); + err = kprobe_multi__attach(skel); + if (!ASSERT_OK(err, "kprobe_multi__attach")) + goto cleanup; + + kprobe_multi_test_run(skel, true); + +cleanup: + kprobe_multi__destroy(skel); +} + +static void test_link_api(struct bpf_link_create_opts *opts) +{ + int prog_fd, link1_fd = -1, link2_fd = -1; + struct kprobe_multi *skel = NULL; + + skel = kprobe_multi__open_and_load(); + if (!ASSERT_OK_PTR(skel, "fentry_raw_skel_load")) + goto cleanup; + + skel->bss->pid = getpid(); + prog_fd = bpf_program__fd(skel->progs.test_kprobe); + link1_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_KPROBE_MULTI, opts); + if (!ASSERT_GE(link1_fd, 0, "link_fd")) + goto cleanup; + + opts->kprobe_multi.flags = BPF_F_KPROBE_MULTI_RETURN; + prog_fd = bpf_program__fd(skel->progs.test_kretprobe); + link2_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_KPROBE_MULTI, opts); + if (!ASSERT_GE(link2_fd, 0, "link_fd")) + goto cleanup; + + kprobe_multi_test_run(skel, true); + +cleanup: + if (link1_fd != -1) + close(link1_fd); + if (link2_fd != -1) + close(link2_fd); + kprobe_multi__destroy(skel); +} + +#define GET_ADDR(__sym, __addr) ({ \ + __addr = ksym_get_addr(__sym); \ + if (!ASSERT_NEQ(__addr, 0, "kallsyms load failed for " #__sym)) \ + return; \ +}) + +static void test_link_api_addrs(void) +{ + LIBBPF_OPTS(bpf_link_create_opts, opts); + unsigned long long addrs[8]; + + GET_ADDR("bpf_fentry_test1", addrs[0]); + GET_ADDR("bpf_fentry_test2", addrs[1]); + GET_ADDR("bpf_fentry_test3", addrs[2]); + GET_ADDR("bpf_fentry_test4", addrs[3]); + GET_ADDR("bpf_fentry_test5", addrs[4]); + GET_ADDR("bpf_fentry_test6", addrs[5]); + GET_ADDR("bpf_fentry_test7", addrs[6]); + GET_ADDR("bpf_fentry_test8", addrs[7]); + + opts.kprobe_multi.addrs = (const unsigned long*) addrs; + opts.kprobe_multi.cnt = ARRAY_SIZE(addrs); + test_link_api(&opts); +} + +static void test_link_api_syms(void) +{ + LIBBPF_OPTS(bpf_link_create_opts, opts); + const char *syms[8] = { + "bpf_fentry_test1", + "bpf_fentry_test2", + "bpf_fentry_test3", + "bpf_fentry_test4", + "bpf_fentry_test5", + "bpf_fentry_test6", + "bpf_fentry_test7", + "bpf_fentry_test8", + }; + + opts.kprobe_multi.syms = syms; + opts.kprobe_multi.cnt = ARRAY_SIZE(syms); + test_link_api(&opts); +} + +static void +test_attach_api(const char *pattern, struct bpf_kprobe_multi_opts *opts) +{ + struct bpf_link *link1 = NULL, *link2 = NULL; + struct kprobe_multi *skel = NULL; + + skel = kprobe_multi__open_and_load(); + if (!ASSERT_OK_PTR(skel, "fentry_raw_skel_load")) + goto cleanup; + + skel->bss->pid = getpid(); + link1 = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe, + pattern, opts); + if (!ASSERT_OK_PTR(link1, "bpf_program__attach_kprobe_multi_opts")) + goto cleanup; + + if (opts) { + opts->retprobe = true; + link2 = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kretprobe, + pattern, opts); + if (!ASSERT_OK_PTR(link2, "bpf_program__attach_kprobe_multi_opts")) + goto cleanup; + } + + kprobe_multi_test_run(skel, !!opts); + +cleanup: + bpf_link__destroy(link2); + bpf_link__destroy(link1); + kprobe_multi__destroy(skel); +} + +static void test_attach_api_pattern(void) +{ + LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); + + test_attach_api("bpf_fentry_test*", &opts); + test_attach_api("bpf_fentry_test?", NULL); +} + +static void test_attach_api_addrs(void) +{ + LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); + unsigned long long addrs[8]; + + GET_ADDR("bpf_fentry_test1", addrs[0]); + GET_ADDR("bpf_fentry_test2", addrs[1]); + GET_ADDR("bpf_fentry_test3", addrs[2]); + GET_ADDR("bpf_fentry_test4", addrs[3]); + GET_ADDR("bpf_fentry_test5", addrs[4]); + GET_ADDR("bpf_fentry_test6", addrs[5]); + GET_ADDR("bpf_fentry_test7", addrs[6]); + GET_ADDR("bpf_fentry_test8", addrs[7]); + + opts.addrs = (const unsigned long *) addrs; + opts.cnt = ARRAY_SIZE(addrs); + test_attach_api(NULL, &opts); +} + +static void test_attach_api_syms(void) +{ + LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); + const char *syms[8] = { + "bpf_fentry_test1", + "bpf_fentry_test2", + "bpf_fentry_test3", + "bpf_fentry_test4", + "bpf_fentry_test5", + "bpf_fentry_test6", + "bpf_fentry_test7", + "bpf_fentry_test8", + }; + + opts.syms = syms; + opts.cnt = ARRAY_SIZE(syms); + test_attach_api(NULL, &opts); +} + +static void test_attach_api_fails(void) +{ + LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); + struct kprobe_multi *skel = NULL; + struct bpf_link *link = NULL; + unsigned long long addrs[2]; + const char *syms[2] = { + "bpf_fentry_test1", + "bpf_fentry_test2", + }; + __u64 cookies[2]; + + addrs[0] = ksym_get_addr("bpf_fentry_test1"); + addrs[1] = ksym_get_addr("bpf_fentry_test2"); + + if (!ASSERT_FALSE(!addrs[0] || !addrs[1], "ksym_get_addr")) + goto cleanup; + + skel = kprobe_multi__open_and_load(); + if (!ASSERT_OK_PTR(skel, "fentry_raw_skel_load")) + goto cleanup; + + skel->bss->pid = getpid(); + + /* fail_1 - pattern and opts NULL */ + link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe, + NULL, NULL); + if (!ASSERT_ERR_PTR(link, "fail_1")) + goto cleanup; + + if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_1_error")) + goto cleanup; + + /* fail_2 - both addrs and syms set */ + opts.addrs = (const unsigned long *) addrs; + opts.syms = syms; + opts.cnt = ARRAY_SIZE(syms); + opts.cookies = NULL; + + link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe, + NULL, &opts); + if (!ASSERT_ERR_PTR(link, "fail_2")) + goto cleanup; + + if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_2_error")) + goto cleanup; + + /* fail_3 - pattern and addrs set */ + opts.addrs = (const unsigned long *) addrs; + opts.syms = NULL; + opts.cnt = ARRAY_SIZE(syms); + opts.cookies = NULL; + + link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe, + "ksys_*", &opts); + if (!ASSERT_ERR_PTR(link, "fail_3")) + goto cleanup; + + if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_3_error")) + goto cleanup; + + /* fail_4 - pattern and cnt set */ + opts.addrs = NULL; + opts.syms = NULL; + opts.cnt = ARRAY_SIZE(syms); + opts.cookies = NULL; + + link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe, + "ksys_*", &opts); + if (!ASSERT_ERR_PTR(link, "fail_4")) + goto cleanup; + + if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_4_error")) + goto cleanup; + + /* fail_5 - pattern and cookies */ + opts.addrs = NULL; + opts.syms = NULL; + opts.cnt = 0; + opts.cookies = cookies; + + link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe, + "ksys_*", &opts); + if (!ASSERT_ERR_PTR(link, "fail_5")) + goto cleanup; + + if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_5_error")) + goto cleanup; + +cleanup: + bpf_link__destroy(link); + kprobe_multi__destroy(skel); +} + +void test_kprobe_multi_test(void) +{ + if (!ASSERT_OK(load_kallsyms(), "load_kallsyms")) + return; + + if (test__start_subtest("skel_api")) + test_skel_api(); + if (test__start_subtest("link_api_addrs")) + test_link_api_syms(); + if (test__start_subtest("link_api_syms")) + test_link_api_addrs(); + if (test__start_subtest("attach_api_pattern")) + test_attach_api_pattern(); + if (test__start_subtest("attach_api_addrs")) + test_attach_api_addrs(); + if (test__start_subtest("attach_api_syms")) + test_attach_api_syms(); + if (test__start_subtest("attach_api_fails")) + test_attach_api_fails(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/obj_name.c b/tools/testing/selftests/bpf/prog_tests/obj_name.c index 6194b776a28b..7093edca6e08 100644 --- a/tools/testing/selftests/bpf/prog_tests/obj_name.c +++ b/tools/testing/selftests/bpf/prog_tests/obj_name.c @@ -20,7 +20,7 @@ void test_obj_name(void) __u32 duration = 0; int i; - for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) { + for (i = 0; i < ARRAY_SIZE(tests); i++) { size_t name_len = strlen(tests[i].name) + 1; union bpf_attr attr; size_t ncopy; diff --git a/tools/testing/selftests/bpf/prog_tests/perf_branches.c b/tools/testing/selftests/bpf/prog_tests/perf_branches.c index 12c4f45cee1a..bc24f83339d6 100644 --- a/tools/testing/selftests/bpf/prog_tests/perf_branches.c +++ b/tools/testing/selftests/bpf/prog_tests/perf_branches.c @@ -110,7 +110,7 @@ static void test_perf_branches_hw(void) attr.type = PERF_TYPE_HARDWARE; attr.config = PERF_COUNT_HW_CPU_CYCLES; attr.freq = 1; - attr.sample_freq = 4000; + attr.sample_freq = 1000; attr.sample_type = PERF_SAMPLE_BRANCH_STACK; attr.branch_sample_type = PERF_SAMPLE_BRANCH_USER | PERF_SAMPLE_BRANCH_ANY; pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC); @@ -151,7 +151,7 @@ static void test_perf_branches_no_hw(void) attr.type = PERF_TYPE_SOFTWARE; attr.config = PERF_COUNT_SW_CPU_CLOCK; attr.freq = 1; - attr.sample_freq = 4000; + attr.sample_freq = 1000; pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC); if (CHECK(pfd < 0, "perf_event_open", "err %d\n", pfd)) return; diff --git a/tools/testing/selftests/bpf/prog_tests/perf_link.c b/tools/testing/selftests/bpf/prog_tests/perf_link.c index ede07344f264..224eba6fef2e 100644 --- a/tools/testing/selftests/bpf/prog_tests/perf_link.c +++ b/tools/testing/selftests/bpf/prog_tests/perf_link.c @@ -39,7 +39,7 @@ void serial_test_perf_link(void) attr.type = PERF_TYPE_SOFTWARE; attr.config = PERF_COUNT_SW_CPU_CLOCK; attr.freq = 1; - attr.sample_freq = 4000; + attr.sample_freq = 1000; pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC); if (!ASSERT_GE(pfd, 0, "perf_fd")) goto cleanup; diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c index 776916b61c40..d71226e34c34 100644 --- a/tools/testing/selftests/bpf/prog_tests/send_signal.c +++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c @@ -4,11 +4,11 @@ #include <sys/resource.h> #include "test_send_signal_kern.skel.h" -int sigusr1_received = 0; +static int sigusr1_received; static void sigusr1_handler(int signum) { - sigusr1_received++; + sigusr1_received = 1; } static void test_send_signal_common(struct perf_event_attr *attr, @@ -40,9 +40,10 @@ static void test_send_signal_common(struct perf_event_attr *attr, if (pid == 0) { int old_prio; + volatile int j = 0; /* install signal handler and notify parent */ - signal(SIGUSR1, sigusr1_handler); + ASSERT_NEQ(signal(SIGUSR1, sigusr1_handler), SIG_ERR, "signal"); close(pipe_c2p[0]); /* close read */ close(pipe_p2c[1]); /* close write */ @@ -63,9 +64,11 @@ static void test_send_signal_common(struct perf_event_attr *attr, ASSERT_EQ(read(pipe_p2c[0], buf, 1), 1, "pipe_read"); /* wait a little for signal handler */ - sleep(1); + for (int i = 0; i < 100000000 && !sigusr1_received; i++) + j /= i + j + 1; buf[0] = sigusr1_received ? '2' : '0'; + ASSERT_EQ(sigusr1_received, 1, "sigusr1_received"); ASSERT_EQ(write(pipe_c2p[1], buf, 1), 1, "pipe_write"); /* wait for parent notification and exit */ @@ -93,7 +96,7 @@ static void test_send_signal_common(struct perf_event_attr *attr, goto destroy_skel; } } else { - pmu_fd = syscall(__NR_perf_event_open, attr, pid, -1, + pmu_fd = syscall(__NR_perf_event_open, attr, pid, -1 /* cpu */, -1 /* group id */, 0 /* flags */); if (!ASSERT_GE(pmu_fd, 0, "perf_event_open")) { err = -1; @@ -110,9 +113,9 @@ static void test_send_signal_common(struct perf_event_attr *attr, ASSERT_EQ(read(pipe_c2p[0], buf, 1), 1, "pipe_read"); /* trigger the bpf send_signal */ - skel->bss->pid = pid; - skel->bss->sig = SIGUSR1; skel->bss->signal_thread = signal_thread; + skel->bss->sig = SIGUSR1; + skel->bss->pid = pid; /* notify child that bpf program can send_signal now */ ASSERT_EQ(write(pipe_p2c[1], buf, 1), 1, "pipe_write"); diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_skip.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_skip.c new file mode 100644 index 000000000000..1932b1e0685c --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_skip.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include "stacktrace_map_skip.skel.h" + +#define TEST_STACK_DEPTH 2 + +void test_stacktrace_map_skip(void) +{ + struct stacktrace_map_skip *skel; + int stackid_hmap_fd, stackmap_fd, stack_amap_fd; + int err, stack_trace_len; + + skel = stacktrace_map_skip__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open_and_load")) + return; + + /* find map fds */ + stackid_hmap_fd = bpf_map__fd(skel->maps.stackid_hmap); + if (!ASSERT_GE(stackid_hmap_fd, 0, "stackid_hmap fd")) + goto out; + + stackmap_fd = bpf_map__fd(skel->maps.stackmap); + if (!ASSERT_GE(stackmap_fd, 0, "stackmap fd")) + goto out; + + stack_amap_fd = bpf_map__fd(skel->maps.stack_amap); + if (!ASSERT_GE(stack_amap_fd, 0, "stack_amap fd")) + goto out; + + skel->bss->pid = getpid(); + + err = stacktrace_map_skip__attach(skel); + if (!ASSERT_OK(err, "skel_attach")) + goto out; + + /* give some time for bpf program run */ + sleep(1); + + /* disable stack trace collection */ + skel->bss->control = 1; + + /* for every element in stackid_hmap, we can find a corresponding one + * in stackmap, and vise versa. + */ + err = compare_map_keys(stackid_hmap_fd, stackmap_fd); + if (!ASSERT_OK(err, "compare_map_keys stackid_hmap vs. stackmap")) + goto out; + + err = compare_map_keys(stackmap_fd, stackid_hmap_fd); + if (!ASSERT_OK(err, "compare_map_keys stackmap vs. stackid_hmap")) + goto out; + + stack_trace_len = TEST_STACK_DEPTH * sizeof(__u64); + err = compare_stack_ips(stackmap_fd, stack_amap_fd, stack_trace_len); + if (!ASSERT_OK(err, "compare_stack_ips stackmap vs. stack_amap")) + goto out; + + if (!ASSERT_EQ(skel->bss->failed, 0, "skip_failed")) + goto out; + +out: + stacktrace_map_skip__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/subprogs.c b/tools/testing/selftests/bpf/prog_tests/subprogs.c index 3f3d2ac4dd57..903f35a9e62e 100644 --- a/tools/testing/selftests/bpf/prog_tests/subprogs.c +++ b/tools/testing/selftests/bpf/prog_tests/subprogs.c @@ -1,32 +1,83 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020 Facebook */ #include <test_progs.h> -#include <time.h> #include "test_subprogs.skel.h" #include "test_subprogs_unused.skel.h" -static int duration; +struct toggler_ctx { + int fd; + bool stop; +}; -void test_subprogs(void) +static void *toggle_jit_harden(void *arg) +{ + struct toggler_ctx *ctx = arg; + char two = '2'; + char zero = '0'; + + while (!ctx->stop) { + lseek(ctx->fd, SEEK_SET, 0); + write(ctx->fd, &two, sizeof(two)); + lseek(ctx->fd, SEEK_SET, 0); + write(ctx->fd, &zero, sizeof(zero)); + } + + return NULL; +} + +static void test_subprogs_with_jit_harden_toggling(void) +{ + struct toggler_ctx ctx; + pthread_t toggler; + int err; + unsigned int i, loop = 10; + + ctx.fd = open("/proc/sys/net/core/bpf_jit_harden", O_RDWR); + if (!ASSERT_GE(ctx.fd, 0, "open bpf_jit_harden")) + return; + + ctx.stop = false; + err = pthread_create(&toggler, NULL, toggle_jit_harden, &ctx); + if (!ASSERT_OK(err, "new toggler")) + goto out; + + /* Make toggler thread to run */ + usleep(1); + + for (i = 0; i < loop; i++) { + struct test_subprogs *skel = test_subprogs__open_and_load(); + + if (!ASSERT_OK_PTR(skel, "skel open")) + break; + test_subprogs__destroy(skel); + } + + ctx.stop = true; + pthread_join(toggler, NULL); +out: + close(ctx.fd); +} + +static void test_subprogs_alone(void) { struct test_subprogs *skel; struct test_subprogs_unused *skel2; int err; skel = test_subprogs__open_and_load(); - if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) + if (!ASSERT_OK_PTR(skel, "skel_open")) return; err = test_subprogs__attach(skel); - if (CHECK(err, "skel_attach", "failed to attach skeleton: %d\n", err)) + if (!ASSERT_OK(err, "skel attach")) goto cleanup; usleep(1); - CHECK(skel->bss->res1 != 12, "res1", "got %d, exp %d\n", skel->bss->res1, 12); - CHECK(skel->bss->res2 != 17, "res2", "got %d, exp %d\n", skel->bss->res2, 17); - CHECK(skel->bss->res3 != 19, "res3", "got %d, exp %d\n", skel->bss->res3, 19); - CHECK(skel->bss->res4 != 36, "res4", "got %d, exp %d\n", skel->bss->res4, 36); + ASSERT_EQ(skel->bss->res1, 12, "res1"); + ASSERT_EQ(skel->bss->res2, 17, "res2"); + ASSERT_EQ(skel->bss->res3, 19, "res3"); + ASSERT_EQ(skel->bss->res4, 36, "res4"); skel2 = test_subprogs_unused__open_and_load(); ASSERT_OK_PTR(skel2, "unused_progs_skel"); @@ -35,3 +86,11 @@ void test_subprogs(void) cleanup: test_subprogs__destroy(skel); } + +void test_subprogs(void) +{ + if (test__start_subtest("subprogs_alone")) + test_subprogs_alone(); + if (test__start_subtest("subprogs_and_jit_harden")) + test_subprogs_with_jit_harden_toggling(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/subskeleton.c b/tools/testing/selftests/bpf/prog_tests/subskeleton.c new file mode 100644 index 000000000000..9c31b7004f9c --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/subskeleton.c @@ -0,0 +1,78 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) Meta Platforms, Inc. and affiliates. */ + +#include <test_progs.h> +#include "test_subskeleton.skel.h" +#include "test_subskeleton_lib.subskel.h" + +static void subskeleton_lib_setup(struct bpf_object *obj) +{ + struct test_subskeleton_lib *lib = test_subskeleton_lib__open(obj); + + if (!ASSERT_OK_PTR(lib, "open subskeleton")) + return; + + *lib->rodata.var1 = 1; + *lib->data.var2 = 2; + lib->bss.var3->var3_1 = 3; + lib->bss.var3->var3_2 = 4; + + test_subskeleton_lib__destroy(lib); +} + +static int subskeleton_lib_subresult(struct bpf_object *obj) +{ + struct test_subskeleton_lib *lib = test_subskeleton_lib__open(obj); + int result; + + if (!ASSERT_OK_PTR(lib, "open subskeleton")) + return -EINVAL; + + result = *lib->bss.libout1; + ASSERT_EQ(result, 1 + 2 + 3 + 4 + 5 + 6, "lib subresult"); + + ASSERT_OK_PTR(lib->progs.lib_perf_handler, "lib_perf_handler"); + ASSERT_STREQ(bpf_program__name(lib->progs.lib_perf_handler), + "lib_perf_handler", "program name"); + + ASSERT_OK_PTR(lib->maps.map1, "map1"); + ASSERT_STREQ(bpf_map__name(lib->maps.map1), "map1", "map name"); + + ASSERT_EQ(*lib->data.var5, 5, "__weak var5"); + ASSERT_EQ(*lib->data.var6, 6, "extern var6"); + ASSERT_TRUE(*lib->kconfig.CONFIG_BPF_SYSCALL, "CONFIG_BPF_SYSCALL"); + + test_subskeleton_lib__destroy(lib); + return result; +} + +void test_subskeleton(void) +{ + int err, result; + struct test_subskeleton *skel; + + skel = test_subskeleton__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return; + + skel->rodata->rovar1 = 10; + skel->rodata->var1 = 1; + subskeleton_lib_setup(skel->obj); + + err = test_subskeleton__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + err = test_subskeleton__attach(skel); + if (!ASSERT_OK(err, "skel_attach")) + goto cleanup; + + /* trigger tracepoint */ + usleep(1); + + result = subskeleton_lib_subresult(skel->obj) * 10; + ASSERT_EQ(skel->bss->out1, result, "unexpected calculation"); + +cleanup: + test_subskeleton__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c index 2b255e28ed26..7ad66a247c02 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c @@ -10,8 +10,6 @@ * to drop unexpected traffic. */ -#define _GNU_SOURCE - #include <arpa/inet.h> #include <linux/if.h> #include <linux/if_tun.h> @@ -19,10 +17,8 @@ #include <linux/sysctl.h> #include <linux/time_types.h> #include <linux/net_tstamp.h> -#include <sched.h> #include <stdbool.h> #include <stdio.h> -#include <sys/mount.h> #include <sys/stat.h> #include <unistd.h> @@ -92,91 +88,6 @@ static int write_file(const char *path, const char *newval) return 0; } -struct nstoken { - int orig_netns_fd; -}; - -static int setns_by_fd(int nsfd) -{ - int err; - - err = setns(nsfd, CLONE_NEWNET); - close(nsfd); - - if (!ASSERT_OK(err, "setns")) - return err; - - /* Switch /sys to the new namespace so that e.g. /sys/class/net - * reflects the devices in the new namespace. - */ - err = unshare(CLONE_NEWNS); - if (!ASSERT_OK(err, "unshare")) - return err; - - /* Make our /sys mount private, so the following umount won't - * trigger the global umount in case it's shared. - */ - err = mount("none", "/sys", NULL, MS_PRIVATE, NULL); - if (!ASSERT_OK(err, "remount private /sys")) - return err; - - err = umount2("/sys", MNT_DETACH); - if (!ASSERT_OK(err, "umount2 /sys")) - return err; - - err = mount("sysfs", "/sys", "sysfs", 0, NULL); - if (!ASSERT_OK(err, "mount /sys")) - return err; - - err = mount("bpffs", "/sys/fs/bpf", "bpf", 0, NULL); - if (!ASSERT_OK(err, "mount /sys/fs/bpf")) - return err; - - return 0; -} - -/** - * open_netns() - Switch to specified network namespace by name. - * - * Returns token with which to restore the original namespace - * using close_netns(). - */ -static struct nstoken *open_netns(const char *name) -{ - int nsfd; - char nspath[PATH_MAX]; - int err; - struct nstoken *token; - - token = calloc(1, sizeof(struct nstoken)); - if (!ASSERT_OK_PTR(token, "malloc token")) - return NULL; - - token->orig_netns_fd = open("/proc/self/ns/net", O_RDONLY); - if (!ASSERT_GE(token->orig_netns_fd, 0, "open /proc/self/ns/net")) - goto fail; - - snprintf(nspath, sizeof(nspath), "%s/%s", "/var/run/netns", name); - nsfd = open(nspath, O_RDONLY | O_CLOEXEC); - if (!ASSERT_GE(nsfd, 0, "open netns fd")) - goto fail; - - err = setns_by_fd(nsfd); - if (!ASSERT_OK(err, "setns_by_fd")) - goto fail; - - return token; -fail: - free(token); - return NULL; -} - -static void close_netns(struct nstoken *token) -{ - ASSERT_OK(setns_by_fd(token->orig_netns_fd), "setns_by_fd"); - free(token); -} - static int netns_setup_namespaces(const char *verb) { const char * const *ns = namespaces; diff --git a/tools/testing/selftests/bpf/prog_tests/test_ima.c b/tools/testing/selftests/bpf/prog_tests/test_ima.c index 97d8a6f84f4a..b13feceb38f1 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_ima.c +++ b/tools/testing/selftests/bpf/prog_tests/test_ima.c @@ -13,14 +13,17 @@ #include "ima.skel.h" -static int run_measured_process(const char *measured_dir, u32 *monitored_pid) +#define MAX_SAMPLES 4 + +static int _run_measured_process(const char *measured_dir, u32 *monitored_pid, + const char *cmd) { int child_pid, child_status; child_pid = fork(); if (child_pid == 0) { *monitored_pid = getpid(); - execlp("./ima_setup.sh", "./ima_setup.sh", "run", measured_dir, + execlp("./ima_setup.sh", "./ima_setup.sh", cmd, measured_dir, NULL); exit(errno); @@ -32,19 +35,39 @@ static int run_measured_process(const char *measured_dir, u32 *monitored_pid) return -EINVAL; } -static u64 ima_hash_from_bpf; +static int run_measured_process(const char *measured_dir, u32 *monitored_pid) +{ + return _run_measured_process(measured_dir, monitored_pid, "run"); +} + +static u64 ima_hash_from_bpf[MAX_SAMPLES]; +static int ima_hash_from_bpf_idx; static int process_sample(void *ctx, void *data, size_t len) { - ima_hash_from_bpf = *((u64 *)data); + if (ima_hash_from_bpf_idx >= MAX_SAMPLES) + return -ENOSPC; + + ima_hash_from_bpf[ima_hash_from_bpf_idx++] = *((u64 *)data); return 0; } +static void test_init(struct ima__bss *bss) +{ + ima_hash_from_bpf_idx = 0; + + bss->use_ima_file_hash = false; + bss->enable_bprm_creds_for_exec = false; + bss->enable_kernel_read_file = false; + bss->test_deny = false; +} + void test_test_ima(void) { char measured_dir_template[] = "/tmp/ima_measuredXXXXXX"; struct ring_buffer *ringbuf = NULL; const char *measured_dir; + u64 bin_true_sample; char cmd[256]; int err, duration = 0; @@ -72,13 +95,127 @@ void test_test_ima(void) if (CHECK(err, "failed to run command", "%s, errno = %d\n", cmd, errno)) goto close_clean; + /* + * Test #1 + * - Goal: obtain a sample with the bpf_ima_inode_hash() helper + * - Expected result: 1 sample (/bin/true) + */ + test_init(skel->bss); err = run_measured_process(measured_dir, &skel->bss->monitored_pid); - if (CHECK(err, "run_measured_process", "err = %d\n", err)) + if (CHECK(err, "run_measured_process #1", "err = %d\n", err)) goto close_clean; err = ring_buffer__consume(ringbuf); ASSERT_EQ(err, 1, "num_samples_or_err"); - ASSERT_NEQ(ima_hash_from_bpf, 0, "ima_hash"); + ASSERT_NEQ(ima_hash_from_bpf[0], 0, "ima_hash"); + + /* + * Test #2 + * - Goal: obtain samples with the bpf_ima_file_hash() helper + * - Expected result: 2 samples (./ima_setup.sh, /bin/true) + */ + test_init(skel->bss); + skel->bss->use_ima_file_hash = true; + err = run_measured_process(measured_dir, &skel->bss->monitored_pid); + if (CHECK(err, "run_measured_process #2", "err = %d\n", err)) + goto close_clean; + + err = ring_buffer__consume(ringbuf); + ASSERT_EQ(err, 2, "num_samples_or_err"); + ASSERT_NEQ(ima_hash_from_bpf[0], 0, "ima_hash"); + ASSERT_NEQ(ima_hash_from_bpf[1], 0, "ima_hash"); + bin_true_sample = ima_hash_from_bpf[1]; + + /* + * Test #3 + * - Goal: confirm that bpf_ima_inode_hash() returns a non-fresh digest + * - Expected result: 2 samples (/bin/true: non-fresh, fresh) + */ + test_init(skel->bss); + + err = _run_measured_process(measured_dir, &skel->bss->monitored_pid, + "modify-bin"); + if (CHECK(err, "modify-bin #3", "err = %d\n", err)) + goto close_clean; + + skel->bss->enable_bprm_creds_for_exec = true; + err = run_measured_process(measured_dir, &skel->bss->monitored_pid); + if (CHECK(err, "run_measured_process #3", "err = %d\n", err)) + goto close_clean; + + err = ring_buffer__consume(ringbuf); + ASSERT_EQ(err, 2, "num_samples_or_err"); + ASSERT_NEQ(ima_hash_from_bpf[0], 0, "ima_hash"); + ASSERT_NEQ(ima_hash_from_bpf[1], 0, "ima_hash"); + ASSERT_EQ(ima_hash_from_bpf[0], bin_true_sample, "sample_equal_or_err"); + /* IMA refreshed the digest. */ + ASSERT_NEQ(ima_hash_from_bpf[1], bin_true_sample, + "sample_different_or_err"); + + /* + * Test #4 + * - Goal: verify that bpf_ima_file_hash() returns a fresh digest + * - Expected result: 4 samples (./ima_setup.sh: fresh, fresh; + * /bin/true: fresh, fresh) + */ + test_init(skel->bss); + skel->bss->use_ima_file_hash = true; + skel->bss->enable_bprm_creds_for_exec = true; + err = run_measured_process(measured_dir, &skel->bss->monitored_pid); + if (CHECK(err, "run_measured_process #4", "err = %d\n", err)) + goto close_clean; + + err = ring_buffer__consume(ringbuf); + ASSERT_EQ(err, 4, "num_samples_or_err"); + ASSERT_NEQ(ima_hash_from_bpf[0], 0, "ima_hash"); + ASSERT_NEQ(ima_hash_from_bpf[1], 0, "ima_hash"); + ASSERT_NEQ(ima_hash_from_bpf[2], 0, "ima_hash"); + ASSERT_NEQ(ima_hash_from_bpf[3], 0, "ima_hash"); + ASSERT_NEQ(ima_hash_from_bpf[2], bin_true_sample, + "sample_different_or_err"); + ASSERT_EQ(ima_hash_from_bpf[3], ima_hash_from_bpf[2], + "sample_equal_or_err"); + + skel->bss->use_ima_file_hash = false; + skel->bss->enable_bprm_creds_for_exec = false; + err = _run_measured_process(measured_dir, &skel->bss->monitored_pid, + "restore-bin"); + if (CHECK(err, "restore-bin #3", "err = %d\n", err)) + goto close_clean; + + /* + * Test #5 + * - Goal: obtain a sample from the kernel_read_file hook + * - Expected result: 2 samples (./ima_setup.sh, policy_test) + */ + test_init(skel->bss); + skel->bss->use_ima_file_hash = true; + skel->bss->enable_kernel_read_file = true; + err = _run_measured_process(measured_dir, &skel->bss->monitored_pid, + "load-policy"); + if (CHECK(err, "run_measured_process #5", "err = %d\n", err)) + goto close_clean; + + err = ring_buffer__consume(ringbuf); + ASSERT_EQ(err, 2, "num_samples_or_err"); + ASSERT_NEQ(ima_hash_from_bpf[0], 0, "ima_hash"); + ASSERT_NEQ(ima_hash_from_bpf[1], 0, "ima_hash"); + + /* + * Test #6 + * - Goal: ensure that the kernel_read_file hook denies an operation + * - Expected result: 0 samples + */ + test_init(skel->bss); + skel->bss->enable_kernel_read_file = true; + skel->bss->test_deny = true; + err = _run_measured_process(measured_dir, &skel->bss->monitored_pid, + "load-policy"); + if (CHECK(!err, "run_measured_process #6", "err = %d\n", err)) + goto close_clean; + + err = ring_buffer__consume(ringbuf); + ASSERT_EQ(err, 0, "num_samples_or_err"); close_clean: snprintf(cmd, sizeof(cmd), "./ima_setup.sh cleanup %s", measured_dir); diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c new file mode 100644 index 000000000000..a50971c6cf4a --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c @@ -0,0 +1,201 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include <network_helpers.h> +#include <net/if.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/ipv6.h> +#include <linux/in6.h> +#include <linux/udp.h> +#include <bpf/bpf_endian.h> +#include "test_xdp_do_redirect.skel.h" + +#define SYS(fmt, ...) \ + ({ \ + char cmd[1024]; \ + snprintf(cmd, sizeof(cmd), fmt, ##__VA_ARGS__); \ + if (!ASSERT_OK(system(cmd), cmd)) \ + goto out; \ + }) + +struct udp_packet { + struct ethhdr eth; + struct ipv6hdr iph; + struct udphdr udp; + __u8 payload[64 - sizeof(struct udphdr) + - sizeof(struct ethhdr) - sizeof(struct ipv6hdr)]; +} __packed; + +static struct udp_packet pkt_udp = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IPV6), + .eth.h_dest = {0x00, 0x11, 0x22, 0x33, 0x44, 0x55}, + .eth.h_source = {0x66, 0x77, 0x88, 0x99, 0xaa, 0xbb}, + .iph.version = 6, + .iph.nexthdr = IPPROTO_UDP, + .iph.payload_len = bpf_htons(sizeof(struct udp_packet) + - offsetof(struct udp_packet, udp)), + .iph.hop_limit = 2, + .iph.saddr.s6_addr16 = {bpf_htons(0xfc00), 0, 0, 0, 0, 0, 0, bpf_htons(1)}, + .iph.daddr.s6_addr16 = {bpf_htons(0xfc00), 0, 0, 0, 0, 0, 0, bpf_htons(2)}, + .udp.source = bpf_htons(1), + .udp.dest = bpf_htons(1), + .udp.len = bpf_htons(sizeof(struct udp_packet) + - offsetof(struct udp_packet, udp)), + .payload = {0x42}, /* receiver XDP program matches on this */ +}; + +static int attach_tc_prog(struct bpf_tc_hook *hook, int fd) +{ + DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts, .handle = 1, .priority = 1, .prog_fd = fd); + int ret; + + ret = bpf_tc_hook_create(hook); + if (!ASSERT_OK(ret, "create tc hook")) + return ret; + + ret = bpf_tc_attach(hook, &opts); + if (!ASSERT_OK(ret, "bpf_tc_attach")) { + bpf_tc_hook_destroy(hook); + return ret; + } + + return 0; +} + +/* The maximum permissible size is: PAGE_SIZE - sizeof(struct xdp_page_head) - + * sizeof(struct skb_shared_info) - XDP_PACKET_HEADROOM = 3368 bytes + */ +#define MAX_PKT_SIZE 3368 +static void test_max_pkt_size(int fd) +{ + char data[MAX_PKT_SIZE + 1] = {}; + int err; + DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &data, + .data_size_in = MAX_PKT_SIZE, + .flags = BPF_F_TEST_XDP_LIVE_FRAMES, + .repeat = 1, + ); + err = bpf_prog_test_run_opts(fd, &opts); + ASSERT_OK(err, "prog_run_max_size"); + + opts.data_size_in += 1; + err = bpf_prog_test_run_opts(fd, &opts); + ASSERT_EQ(err, -EINVAL, "prog_run_too_big"); +} + +#define NUM_PKTS 10000 +void test_xdp_do_redirect(void) +{ + int err, xdp_prog_fd, tc_prog_fd, ifindex_src, ifindex_dst; + char data[sizeof(pkt_udp) + sizeof(__u32)]; + struct test_xdp_do_redirect *skel = NULL; + struct nstoken *nstoken = NULL; + struct bpf_link *link; + + struct xdp_md ctx_in = { .data = sizeof(__u32), + .data_end = sizeof(data) }; + DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &data, + .data_size_in = sizeof(data), + .ctx_in = &ctx_in, + .ctx_size_in = sizeof(ctx_in), + .flags = BPF_F_TEST_XDP_LIVE_FRAMES, + .repeat = NUM_PKTS, + .batch_size = 64, + ); + DECLARE_LIBBPF_OPTS(bpf_tc_hook, tc_hook, + .attach_point = BPF_TC_INGRESS); + + memcpy(&data[sizeof(__u32)], &pkt_udp, sizeof(pkt_udp)); + *((__u32 *)data) = 0x42; /* metadata test value */ + + skel = test_xdp_do_redirect__open(); + if (!ASSERT_OK_PTR(skel, "skel")) + return; + + /* The XDP program we run with bpf_prog_run() will cycle through all + * three xmit (PASS/TX/REDIRECT) return codes starting from above, and + * ending up with PASS, so we should end up with two packets on the dst + * iface and NUM_PKTS-2 in the TC hook. We match the packets on the UDP + * payload. + */ + SYS("ip netns add testns"); + nstoken = open_netns("testns"); + if (!ASSERT_OK_PTR(nstoken, "setns")) + goto out; + + SYS("ip link add veth_src type veth peer name veth_dst"); + SYS("ip link set dev veth_src address 00:11:22:33:44:55"); + SYS("ip link set dev veth_dst address 66:77:88:99:aa:bb"); + SYS("ip link set dev veth_src up"); + SYS("ip link set dev veth_dst up"); + SYS("ip addr add dev veth_src fc00::1/64"); + SYS("ip addr add dev veth_dst fc00::2/64"); + SYS("ip neigh add fc00::2 dev veth_src lladdr 66:77:88:99:aa:bb"); + + /* We enable forwarding in the test namespace because that will cause + * the packets that go through the kernel stack (with XDP_PASS) to be + * forwarded back out the same interface (because of the packet dst + * combined with the interface addresses). When this happens, the + * regular forwarding path will end up going through the same + * veth_xdp_xmit() call as the XDP_REDIRECT code, which can cause a + * deadlock if it happens on the same CPU. There's a local_bh_disable() + * in the test_run code to prevent this, but an earlier version of the + * code didn't have this, so we keep the test behaviour to make sure the + * bug doesn't resurface. + */ + SYS("sysctl -qw net.ipv6.conf.all.forwarding=1"); + + ifindex_src = if_nametoindex("veth_src"); + ifindex_dst = if_nametoindex("veth_dst"); + if (!ASSERT_NEQ(ifindex_src, 0, "ifindex_src") || + !ASSERT_NEQ(ifindex_dst, 0, "ifindex_dst")) + goto out; + + memcpy(skel->rodata->expect_dst, &pkt_udp.eth.h_dest, ETH_ALEN); + skel->rodata->ifindex_out = ifindex_src; /* redirect back to the same iface */ + skel->rodata->ifindex_in = ifindex_src; + ctx_in.ingress_ifindex = ifindex_src; + tc_hook.ifindex = ifindex_src; + + if (!ASSERT_OK(test_xdp_do_redirect__load(skel), "load")) + goto out; + + link = bpf_program__attach_xdp(skel->progs.xdp_count_pkts, ifindex_dst); + if (!ASSERT_OK_PTR(link, "prog_attach")) + goto out; + skel->links.xdp_count_pkts = link; + + tc_prog_fd = bpf_program__fd(skel->progs.tc_count_pkts); + if (attach_tc_prog(&tc_hook, tc_prog_fd)) + goto out; + + xdp_prog_fd = bpf_program__fd(skel->progs.xdp_redirect); + err = bpf_prog_test_run_opts(xdp_prog_fd, &opts); + if (!ASSERT_OK(err, "prog_run")) + goto out_tc; + + /* wait for the packets to be flushed */ + kern_sync_rcu(); + + /* There will be one packet sent through XDP_REDIRECT and one through + * XDP_TX; these will show up on the XDP counting program, while the + * rest will be counted at the TC ingress hook (and the counting program + * resets the packet payload so they don't get counted twice even though + * they are re-xmited out the veth device + */ + ASSERT_EQ(skel->bss->pkts_seen_xdp, 2, "pkt_count_xdp"); + ASSERT_EQ(skel->bss->pkts_seen_zero, 2, "pkt_count_zero"); + ASSERT_EQ(skel->bss->pkts_seen_tc, NUM_PKTS - 2, "pkt_count_tc"); + + test_max_pkt_size(bpf_program__fd(skel->progs.xdp_count_pkts)); + +out_tc: + bpf_tc_hook_destroy(&tc_hook); +out: + if (nstoken) + close_netns(nstoken); + system("ip netns del testns"); + test_xdp_do_redirect__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c b/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c new file mode 100644 index 000000000000..8feddb8289cf --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Google */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +struct bpf_testmod_btf_type_tag_1 { + int a; +}; + +struct bpf_testmod_btf_type_tag_2 { + struct bpf_testmod_btf_type_tag_1 *p; +}; + +__u64 g; + +SEC("fentry/bpf_testmod_test_btf_type_tag_percpu_1") +int BPF_PROG(test_percpu1, struct bpf_testmod_btf_type_tag_1 *arg) +{ + g = arg->a; + return 0; +} + +SEC("fentry/bpf_testmod_test_btf_type_tag_percpu_2") +int BPF_PROG(test_percpu2, struct bpf_testmod_btf_type_tag_2 *arg) +{ + g = arg->p->a; + return 0; +} + +/* trace_cgroup_mkdir(struct cgroup *cgrp, const char *path) + * + * struct cgroup_rstat_cpu { + * ... + * struct cgroup *updated_children; + * ... + * }; + * + * struct cgroup { + * ... + * struct cgroup_rstat_cpu __percpu *rstat_cpu; + * ... + * }; + */ +SEC("tp_btf/cgroup_mkdir") +int BPF_PROG(test_percpu_load, struct cgroup *cgrp, const char *path) +{ + g = (__u64)cgrp->rstat_cpu->updated_children; + return 0; +} + +SEC("tp_btf/cgroup_mkdir") +int BPF_PROG(test_percpu_helper, struct cgroup *cgrp, const char *path) +{ + struct cgroup_rstat_cpu *rstat; + __u32 cpu; + + cpu = bpf_get_smp_processor_id(); + rstat = (struct cgroup_rstat_cpu *)bpf_per_cpu_ptr(cgrp->rstat_cpu, cpu); + if (rstat) { + /* READ_ONCE */ + *(volatile int *)rstat; + } + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/ima.c b/tools/testing/selftests/bpf/progs/ima.c index 96060ff4ffc6..e16a2c208481 100644 --- a/tools/testing/selftests/bpf/progs/ima.c +++ b/tools/testing/selftests/bpf/progs/ima.c @@ -18,8 +18,12 @@ struct { char _license[] SEC("license") = "GPL"; -SEC("lsm.s/bprm_committed_creds") -void BPF_PROG(ima, struct linux_binprm *bprm) +bool use_ima_file_hash; +bool enable_bprm_creds_for_exec; +bool enable_kernel_read_file; +bool test_deny; + +static void ima_test_common(struct file *file) { u64 ima_hash = 0; u64 *sample; @@ -28,8 +32,12 @@ void BPF_PROG(ima, struct linux_binprm *bprm) pid = bpf_get_current_pid_tgid() >> 32; if (pid == monitored_pid) { - ret = bpf_ima_inode_hash(bprm->file->f_inode, &ima_hash, - sizeof(ima_hash)); + if (!use_ima_file_hash) + ret = bpf_ima_inode_hash(file->f_inode, &ima_hash, + sizeof(ima_hash)); + else + ret = bpf_ima_file_hash(file, &ima_hash, + sizeof(ima_hash)); if (ret < 0 || ima_hash == 0) return; @@ -43,3 +51,53 @@ void BPF_PROG(ima, struct linux_binprm *bprm) return; } + +static int ima_test_deny(void) +{ + u32 pid; + + pid = bpf_get_current_pid_tgid() >> 32; + if (pid == monitored_pid && test_deny) + return -EPERM; + + return 0; +} + +SEC("lsm.s/bprm_committed_creds") +void BPF_PROG(bprm_committed_creds, struct linux_binprm *bprm) +{ + ima_test_common(bprm->file); +} + +SEC("lsm.s/bprm_creds_for_exec") +int BPF_PROG(bprm_creds_for_exec, struct linux_binprm *bprm) +{ + if (!enable_bprm_creds_for_exec) + return 0; + + ima_test_common(bprm->file); + return 0; +} + +SEC("lsm.s/kernel_read_file") +int BPF_PROG(kernel_read_file, struct file *file, enum kernel_read_file_id id, + bool contents) +{ + int ret; + + if (!enable_kernel_read_file) + return 0; + + if (!contents) + return 0; + + if (id != READING_POLICY) + return 0; + + ret = ima_test_deny(); + if (ret < 0) + return ret; + + ima_test_common(file); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/kprobe_multi.c b/tools/testing/selftests/bpf/progs/kprobe_multi.c new file mode 100644 index 000000000000..600be50800f8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/kprobe_multi.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <stdbool.h> + +char _license[] SEC("license") = "GPL"; + +extern const void bpf_fentry_test1 __ksym; +extern const void bpf_fentry_test2 __ksym; +extern const void bpf_fentry_test3 __ksym; +extern const void bpf_fentry_test4 __ksym; +extern const void bpf_fentry_test5 __ksym; +extern const void bpf_fentry_test6 __ksym; +extern const void bpf_fentry_test7 __ksym; +extern const void bpf_fentry_test8 __ksym; + +int pid = 0; +bool test_cookie = false; + +__u64 kprobe_test1_result = 0; +__u64 kprobe_test2_result = 0; +__u64 kprobe_test3_result = 0; +__u64 kprobe_test4_result = 0; +__u64 kprobe_test5_result = 0; +__u64 kprobe_test6_result = 0; +__u64 kprobe_test7_result = 0; +__u64 kprobe_test8_result = 0; + +__u64 kretprobe_test1_result = 0; +__u64 kretprobe_test2_result = 0; +__u64 kretprobe_test3_result = 0; +__u64 kretprobe_test4_result = 0; +__u64 kretprobe_test5_result = 0; +__u64 kretprobe_test6_result = 0; +__u64 kretprobe_test7_result = 0; +__u64 kretprobe_test8_result = 0; + +extern bool CONFIG_X86_KERNEL_IBT __kconfig __weak; + +static void kprobe_multi_check(void *ctx, bool is_return) +{ + if (bpf_get_current_pid_tgid() >> 32 != pid) + return; + + __u64 cookie = test_cookie ? bpf_get_attach_cookie(ctx) : 0; + __u64 addr = bpf_get_func_ip(ctx) - (CONFIG_X86_KERNEL_IBT ? 4 : 0); + +#define SET(__var, __addr, __cookie) ({ \ + if (((const void *) addr == __addr) && \ + (!test_cookie || (cookie == __cookie))) \ + __var = 1; \ +}) + + if (is_return) { + SET(kretprobe_test1_result, &bpf_fentry_test1, 8); + SET(kretprobe_test2_result, &bpf_fentry_test2, 7); + SET(kretprobe_test3_result, &bpf_fentry_test3, 6); + SET(kretprobe_test4_result, &bpf_fentry_test4, 5); + SET(kretprobe_test5_result, &bpf_fentry_test5, 4); + SET(kretprobe_test6_result, &bpf_fentry_test6, 3); + SET(kretprobe_test7_result, &bpf_fentry_test7, 2); + SET(kretprobe_test8_result, &bpf_fentry_test8, 1); + } else { + SET(kprobe_test1_result, &bpf_fentry_test1, 1); + SET(kprobe_test2_result, &bpf_fentry_test2, 2); + SET(kprobe_test3_result, &bpf_fentry_test3, 3); + SET(kprobe_test4_result, &bpf_fentry_test4, 4); + SET(kprobe_test5_result, &bpf_fentry_test5, 5); + SET(kprobe_test6_result, &bpf_fentry_test6, 6); + SET(kprobe_test7_result, &bpf_fentry_test7, 7); + SET(kprobe_test8_result, &bpf_fentry_test8, 8); + } + +#undef SET +} + +/* + * No tests in here, just to trigger 'bpf_fentry_test*' + * through tracing test_run + */ +SEC("fentry/bpf_modify_return_test") +int BPF_PROG(trigger) +{ + return 0; +} + +SEC("kprobe.multi/bpf_fentry_tes??") +int test_kprobe(struct pt_regs *ctx) +{ + kprobe_multi_check(ctx, false); + return 0; +} + +SEC("kretprobe.multi/bpf_fentry_test*") +int test_kretprobe(struct pt_regs *ctx) +{ + kprobe_multi_check(ctx, true); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/local_storage.c b/tools/testing/selftests/bpf/progs/local_storage.c index 9b1f9b75d5c2..19423ed862e3 100644 --- a/tools/testing/selftests/bpf/progs/local_storage.c +++ b/tools/testing/selftests/bpf/progs/local_storage.c @@ -37,6 +37,13 @@ struct { } sk_storage_map SEC(".maps"); struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC | BPF_F_CLONE); + __type(key, int); + __type(value, struct local_storage); +} sk_storage_map2 SEC(".maps"); + +struct { __uint(type, BPF_MAP_TYPE_TASK_STORAGE); __uint(map_flags, BPF_F_NO_PREALLOC); __type(key, int); @@ -115,7 +122,19 @@ int BPF_PROG(socket_bind, struct socket *sock, struct sockaddr *address, if (storage->value != DUMMY_STORAGE_VALUE) sk_storage_result = -1; + /* This tests that we can associate multiple elements + * with the local storage. + */ + storage = bpf_sk_storage_get(&sk_storage_map2, sock->sk, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!storage) + return 0; + err = bpf_sk_storage_delete(&sk_storage_map, sock->sk); + if (err) + return 0; + + err = bpf_sk_storage_delete(&sk_storage_map2, sock->sk); if (!err) sk_storage_result = err; diff --git a/tools/testing/selftests/bpf/progs/stacktrace_map_skip.c b/tools/testing/selftests/bpf/progs/stacktrace_map_skip.c new file mode 100644 index 000000000000..2eb297df3dd6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/stacktrace_map_skip.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> + +#define TEST_STACK_DEPTH 2 +#define TEST_MAX_ENTRIES 16384 + +typedef __u64 stack_trace_t[TEST_STACK_DEPTH]; + +struct { + __uint(type, BPF_MAP_TYPE_STACK_TRACE); + __uint(max_entries, TEST_MAX_ENTRIES); + __type(key, __u32); + __type(value, stack_trace_t); +} stackmap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, TEST_MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} stackid_hmap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, TEST_MAX_ENTRIES); + __type(key, __u32); + __type(value, stack_trace_t); +} stack_amap SEC(".maps"); + +int pid = 0; +int control = 0; +int failed = 0; + +SEC("tracepoint/sched/sched_switch") +int oncpu(struct trace_event_raw_sched_switch *ctx) +{ + __u32 max_len = TEST_STACK_DEPTH * sizeof(__u64); + __u32 key = 0, val = 0; + __u64 *stack_p; + + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + if (control) + return 0; + + /* it should allow skipping whole buffer size entries */ + key = bpf_get_stackid(ctx, &stackmap, TEST_STACK_DEPTH); + if ((int)key >= 0) { + /* The size of stackmap and stack_amap should be the same */ + bpf_map_update_elem(&stackid_hmap, &key, &val, 0); + stack_p = bpf_map_lookup_elem(&stack_amap, &key); + if (stack_p) { + bpf_get_stack(ctx, stack_p, max_len, TEST_STACK_DEPTH); + /* it wrongly skipped all the entries and filled zero */ + if (stack_p[0] == 0) + failed = 1; + } + } else { + /* old kernel doesn't support skipping that many entries */ + failed = 2; + } + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_custom_sec_handlers.c b/tools/testing/selftests/bpf/progs/test_custom_sec_handlers.c new file mode 100644 index 000000000000..4061f701ca50 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_custom_sec_handlers.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +const volatile int my_pid; + +bool abc1_called; +bool abc2_called; +bool custom1_called; +bool custom2_called; +bool kprobe1_called; +bool xyz_called; + +SEC("abc") +int abc1(void *ctx) +{ + abc1_called = true; + return 0; +} + +SEC("abc/whatever") +int abc2(void *ctx) +{ + abc2_called = true; + return 0; +} + +SEC("custom") +int custom1(void *ctx) +{ + custom1_called = true; + return 0; +} + +SEC("custom/something") +int custom2(void *ctx) +{ + custom2_called = true; + return 0; +} + +SEC("kprobe") +int kprobe1(void *ctx) +{ + kprobe1_called = true; + return 0; +} + +SEC("xyz/blah") +int xyz(void *ctx) +{ + int whatever; + + /* use sleepable helper, custom handler should set sleepable flag */ + bpf_copy_from_user(&whatever, sizeof(whatever), NULL); + xyz_called = true; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_send_signal_kern.c b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c index b4233d3efac2..92354cd72044 100644 --- a/tools/testing/selftests/bpf/progs/test_send_signal_kern.c +++ b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c @@ -10,7 +10,7 @@ static __always_inline int bpf_send_signal_test(void *ctx) { int ret; - if (status != 0 || sig == 0 || pid == 0) + if (status != 0 || pid == 0) return 0; if ((bpf_get_current_pid_tgid() >> 32) == pid) { diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup.c b/tools/testing/selftests/bpf/progs/test_sk_lookup.c index bf5b7caefdd0..6058dcb11b36 100644 --- a/tools/testing/selftests/bpf/progs/test_sk_lookup.c +++ b/tools/testing/selftests/bpf/progs/test_sk_lookup.c @@ -413,15 +413,20 @@ int ctx_narrow_access(struct bpf_sk_lookup *ctx) /* Narrow loads from remote_port field. Expect SRC_PORT. */ if (LSB(ctx->remote_port, 0) != ((SRC_PORT >> 0) & 0xff) || - LSB(ctx->remote_port, 1) != ((SRC_PORT >> 8) & 0xff) || - LSB(ctx->remote_port, 2) != 0 || LSB(ctx->remote_port, 3) != 0) + LSB(ctx->remote_port, 1) != ((SRC_PORT >> 8) & 0xff)) return SK_DROP; if (LSW(ctx->remote_port, 0) != SRC_PORT) return SK_DROP; - /* Load from remote_port field with zero padding (backward compatibility) */ + /* + * NOTE: 4-byte load from bpf_sk_lookup at remote_port offset + * is quirky. It gets rewritten by the access converter to a + * 2-byte load for backward compatibility. Treating the load + * result as a be16 value makes the code portable across + * little- and big-endian platforms. + */ val_u32 = *(__u32 *)&ctx->remote_port; - if (val_u32 != bpf_htonl(bpf_ntohs(SRC_PORT) << 16)) + if (val_u32 != SRC_PORT) return SK_DROP; /* Narrow loads from local_port field. Expect DST_PORT. */ diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields.c b/tools/testing/selftests/bpf/progs/test_sock_fields.c index 246f1f001813..9f4b8f9f1181 100644 --- a/tools/testing/selftests/bpf/progs/test_sock_fields.c +++ b/tools/testing/selftests/bpf/progs/test_sock_fields.c @@ -114,7 +114,7 @@ static void tpcpy(struct bpf_tcp_sock *dst, #define RET_LOG() ({ \ linum = __LINE__; \ - bpf_map_update_elem(&linum_map, &linum_idx, &linum, BPF_NOEXIST); \ + bpf_map_update_elem(&linum_map, &linum_idx, &linum, BPF_ANY); \ return CG_OK; \ }) @@ -134,11 +134,11 @@ int egress_read_sock_fields(struct __sk_buff *skb) if (!sk) RET_LOG(); - /* Not the testing egress traffic or - * TCP_LISTEN (10) socket will be copied at the ingress side. + /* Not testing the egress traffic or the listening socket, + * which are covered by the cgroup_skb/ingress test program. */ if (sk->family != AF_INET6 || !is_loopback6(sk->src_ip6) || - sk->state == 10) + sk->state == BPF_TCP_LISTEN) return CG_OK; if (sk->src_port == bpf_ntohs(srv_sa6.sin6_port)) { @@ -232,8 +232,8 @@ int ingress_read_sock_fields(struct __sk_buff *skb) sk->src_port != bpf_ntohs(srv_sa6.sin6_port)) return CG_OK; - /* Only interested in TCP_LISTEN */ - if (sk->state != 10) + /* Only interested in the listening socket */ + if (sk->state != BPF_TCP_LISTEN) return CG_OK; /* It must be a fullsock for cgroup_skb/ingress prog */ @@ -251,10 +251,16 @@ int ingress_read_sock_fields(struct __sk_buff *skb) return CG_OK; } +/* + * NOTE: 4-byte load from bpf_sock at dst_port offset is quirky. It + * gets rewritten by the access converter to a 2-byte load for + * backward compatibility. Treating the load result as a be16 value + * makes the code portable across little- and big-endian platforms. + */ static __noinline bool sk_dst_port__load_word(struct bpf_sock *sk) { __u32 *word = (__u32 *)&sk->dst_port; - return word[0] == bpf_htonl(0xcafe0000); + return word[0] == bpf_htons(0xcafe); } static __noinline bool sk_dst_port__load_half(struct bpf_sock *sk) @@ -281,6 +287,10 @@ int read_sk_dst_port(struct __sk_buff *skb) if (!sk) RET_LOG(); + /* Ignore everything but the SYN from the client socket */ + if (sk->state != BPF_TCP_SYN_SENT) + return CG_OK; + if (!sk_dst_port__load_word(sk)) RET_LOG(); if (!sk_dst_port__load_half(sk)) diff --git a/tools/testing/selftests/bpf/progs/test_subskeleton.c b/tools/testing/selftests/bpf/progs/test_subskeleton.c new file mode 100644 index 000000000000..006417974372 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_subskeleton.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) Meta Platforms, Inc. and affiliates. */ + +#include <stdbool.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +/* volatile to force a read, compiler may assume 0 otherwise */ +const volatile int rovar1; +int out1; + +/* Override weak symbol in test_subskeleton_lib */ +int var5 = 5; + +extern volatile bool CONFIG_BPF_SYSCALL __kconfig; + +extern int lib_routine(void); + +SEC("raw_tp/sys_enter") +int handler1(const void *ctx) +{ + (void) CONFIG_BPF_SYSCALL; + + out1 = lib_routine() * rovar1; + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_subskeleton_lib.c b/tools/testing/selftests/bpf/progs/test_subskeleton_lib.c new file mode 100644 index 000000000000..ecfafe812c36 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_subskeleton_lib.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) Meta Platforms, Inc. and affiliates. */ + +#include <stdbool.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +/* volatile to force a read */ +const volatile int var1; +volatile int var2 = 1; +struct { + int var3_1; + __s64 var3_2; +} var3; +int libout1; + +extern volatile bool CONFIG_BPF_SYSCALL __kconfig; + +int var4[4]; + +__weak int var5 SEC(".data"); + +/* Fully contained within library extern-and-definition */ +extern int var6; + +int var7 SEC(".data.custom"); + +int (*fn_ptr)(void); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, __u32); + __type(value, __u32); + __uint(max_entries, 16); +} map1 SEC(".maps"); + +extern struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, __u32); + __type(value, __u32); + __uint(max_entries, 16); +} map2 SEC(".maps"); + +int lib_routine(void) +{ + __u32 key = 1, value = 2; + + (void) CONFIG_BPF_SYSCALL; + bpf_map_update_elem(&map2, &key, &value, BPF_ANY); + + libout1 = var1 + var2 + var3.var3_1 + var3.var3_2 + var5 + var6; + return libout1; +} + +SEC("perf_event") +int lib_perf_handler(struct pt_regs *ctx) +{ + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_subskeleton_lib2.c b/tools/testing/selftests/bpf/progs/test_subskeleton_lib2.c new file mode 100644 index 000000000000..80238486b7ce --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_subskeleton_lib2.c @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) Meta Platforms, Inc. and affiliates. */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +int var6 = 6; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, __u32); + __type(value, __u32); + __uint(max_entries, 16); +} map2 SEC(".maps"); + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tc_dtime.c b/tools/testing/selftests/bpf/progs/test_tc_dtime.c index 9d9e8e17b8a0..06f300d06dbd 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_dtime.c +++ b/tools/testing/selftests/bpf/progs/test_tc_dtime.c @@ -174,13 +174,13 @@ int egress_host(struct __sk_buff *skb) return TC_ACT_OK; if (skb_proto(skb_type) == IPPROTO_TCP) { - if (skb->delivery_time_type == BPF_SKB_DELIVERY_TIME_MONO && + if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO && skb->tstamp) inc_dtimes(EGRESS_ENDHOST); else inc_errs(EGRESS_ENDHOST); } else { - if (skb->delivery_time_type == BPF_SKB_DELIVERY_TIME_UNSPEC && + if (skb->tstamp_type == BPF_SKB_TSTAMP_UNSPEC && skb->tstamp) inc_dtimes(EGRESS_ENDHOST); else @@ -204,7 +204,7 @@ int ingress_host(struct __sk_buff *skb) if (!skb_type) return TC_ACT_OK; - if (skb->delivery_time_type == BPF_SKB_DELIVERY_TIME_MONO && + if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO && skb->tstamp == EGRESS_FWDNS_MAGIC) inc_dtimes(INGRESS_ENDHOST); else @@ -226,7 +226,7 @@ int ingress_fwdns_prio100(struct __sk_buff *skb) return TC_ACT_OK; /* delivery_time is only available to the ingress - * if the tc-bpf checks the skb->delivery_time_type. + * if the tc-bpf checks the skb->tstamp_type. */ if (skb->tstamp == EGRESS_ENDHOST_MAGIC) inc_errs(INGRESS_FWDNS_P100); @@ -250,7 +250,7 @@ int egress_fwdns_prio100(struct __sk_buff *skb) return TC_ACT_OK; /* delivery_time is always available to egress even - * the tc-bpf did not use the delivery_time_type. + * the tc-bpf did not use the tstamp_type. */ if (skb->tstamp == INGRESS_FWDNS_MAGIC) inc_dtimes(EGRESS_FWDNS_P100); @@ -278,9 +278,9 @@ int ingress_fwdns_prio101(struct __sk_buff *skb) if (skb_proto(skb_type) == IPPROTO_UDP) expected_dtime = 0; - if (skb->delivery_time_type) { + if (skb->tstamp_type) { if (fwdns_clear_dtime() || - skb->delivery_time_type != BPF_SKB_DELIVERY_TIME_MONO || + skb->tstamp_type != BPF_SKB_TSTAMP_DELIVERY_MONO || skb->tstamp != expected_dtime) inc_errs(INGRESS_FWDNS_P101); else @@ -290,14 +290,14 @@ int ingress_fwdns_prio101(struct __sk_buff *skb) inc_errs(INGRESS_FWDNS_P101); } - if (skb->delivery_time_type == BPF_SKB_DELIVERY_TIME_MONO) { + if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO) { skb->tstamp = INGRESS_FWDNS_MAGIC; } else { - if (bpf_skb_set_delivery_time(skb, INGRESS_FWDNS_MAGIC, - BPF_SKB_DELIVERY_TIME_MONO)) + if (bpf_skb_set_tstamp(skb, INGRESS_FWDNS_MAGIC, + BPF_SKB_TSTAMP_DELIVERY_MONO)) inc_errs(SET_DTIME); - if (!bpf_skb_set_delivery_time(skb, INGRESS_FWDNS_MAGIC, - BPF_SKB_DELIVERY_TIME_UNSPEC)) + if (!bpf_skb_set_tstamp(skb, INGRESS_FWDNS_MAGIC, + BPF_SKB_TSTAMP_UNSPEC)) inc_errs(SET_DTIME); } @@ -320,9 +320,9 @@ int egress_fwdns_prio101(struct __sk_buff *skb) /* Should have handled in prio100 */ return TC_ACT_SHOT; - if (skb->delivery_time_type) { + if (skb->tstamp_type) { if (fwdns_clear_dtime() || - skb->delivery_time_type != BPF_SKB_DELIVERY_TIME_MONO || + skb->tstamp_type != BPF_SKB_TSTAMP_DELIVERY_MONO || skb->tstamp != INGRESS_FWDNS_MAGIC) inc_errs(EGRESS_FWDNS_P101); else @@ -332,14 +332,14 @@ int egress_fwdns_prio101(struct __sk_buff *skb) inc_errs(EGRESS_FWDNS_P101); } - if (skb->delivery_time_type == BPF_SKB_DELIVERY_TIME_MONO) { + if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO) { skb->tstamp = EGRESS_FWDNS_MAGIC; } else { - if (bpf_skb_set_delivery_time(skb, EGRESS_FWDNS_MAGIC, - BPF_SKB_DELIVERY_TIME_MONO)) + if (bpf_skb_set_tstamp(skb, EGRESS_FWDNS_MAGIC, + BPF_SKB_TSTAMP_DELIVERY_MONO)) inc_errs(SET_DTIME); - if (!bpf_skb_set_delivery_time(skb, EGRESS_FWDNS_MAGIC, - BPF_SKB_DELIVERY_TIME_UNSPEC)) + if (!bpf_skb_set_tstamp(skb, INGRESS_FWDNS_MAGIC, + BPF_SKB_TSTAMP_UNSPEC)) inc_errs(SET_DTIME); } diff --git a/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c b/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c new file mode 100644 index 000000000000..77a123071940 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> + +#define ETH_ALEN 6 +#define HDR_SZ (sizeof(struct ethhdr) + sizeof(struct ipv6hdr) + sizeof(struct udphdr)) +const volatile int ifindex_out; +const volatile int ifindex_in; +const volatile __u8 expect_dst[ETH_ALEN]; +volatile int pkts_seen_xdp = 0; +volatile int pkts_seen_zero = 0; +volatile int pkts_seen_tc = 0; +volatile int retcode = XDP_REDIRECT; + +SEC("xdp") +int xdp_redirect(struct xdp_md *xdp) +{ + __u32 *metadata = (void *)(long)xdp->data_meta; + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + + __u8 *payload = data + HDR_SZ; + int ret = retcode; + + if (payload + 1 > data_end) + return XDP_ABORTED; + + if (xdp->ingress_ifindex != ifindex_in) + return XDP_ABORTED; + + if (metadata + 1 > data) + return XDP_ABORTED; + + if (*metadata != 0x42) + return XDP_ABORTED; + + if (*payload == 0) { + *payload = 0x42; + pkts_seen_zero++; + } + + if (bpf_xdp_adjust_meta(xdp, 4)) + return XDP_ABORTED; + + if (retcode > XDP_PASS) + retcode--; + + if (ret == XDP_REDIRECT) + return bpf_redirect(ifindex_out, 0); + + return ret; +} + +static bool check_pkt(void *data, void *data_end) +{ + struct ipv6hdr *iph = data + sizeof(struct ethhdr); + __u8 *payload = data + HDR_SZ; + + if (payload + 1 > data_end) + return false; + + if (iph->nexthdr != IPPROTO_UDP || *payload != 0x42) + return false; + + /* reset the payload so the same packet doesn't get counted twice when + * it cycles back through the kernel path and out the dst veth + */ + *payload = 0; + return true; +} + +SEC("xdp") +int xdp_count_pkts(struct xdp_md *xdp) +{ + void *data = (void *)(long)xdp->data; + void *data_end = (void *)(long)xdp->data_end; + + if (check_pkt(data, data_end)) + pkts_seen_xdp++; + + /* Return XDP_DROP to make sure the data page is recycled, like when it + * exits a physical NIC. Recycled pages will be counted in the + * pkts_seen_zero counter above. + */ + return XDP_DROP; +} + +SEC("tc") +int tc_count_pkts(struct __sk_buff *skb) +{ + void *data = (void *)(long)skb->data; + void *data_end = (void *)(long)skb->data_end; + + if (check_pkt(data, data_end)) + pkts_seen_tc++; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_cgroup_storage.c b/tools/testing/selftests/bpf/test_cgroup_storage.c index 5b8314cd77fd..d6a1be4d8020 100644 --- a/tools/testing/selftests/bpf/test_cgroup_storage.c +++ b/tools/testing/selftests/bpf/test_cgroup_storage.c @@ -36,7 +36,7 @@ int main(int argc, char **argv) BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), BPF_EXIT_INSN(), }; - size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); + size_t insns_cnt = ARRAY_SIZE(prog); int error = EXIT_FAILURE; int map_fd, percpu_map_fd, prog_fd, cgroup_fd; struct bpf_cgroup_storage_key key; diff --git a/tools/testing/selftests/bpf/test_lirc_mode2.sh b/tools/testing/selftests/bpf/test_lirc_mode2.sh index ec4e15948e40..5252b91f48a1 100755 --- a/tools/testing/selftests/bpf/test_lirc_mode2.sh +++ b/tools/testing/selftests/bpf/test_lirc_mode2.sh @@ -3,6 +3,7 @@ # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 +ret=$ksft_skip msg="skip all tests:" if [ $UID != 0 ]; then @@ -25,7 +26,7 @@ do fi done -if [ -n $LIRCDEV ]; +if [ -n "$LIRCDEV" ]; then TYPE=lirc_mode2 ./test_lirc_mode2_user $LIRCDEV $INPUTDEV @@ -36,3 +37,5 @@ then echo -e ${GREEN}"PASS: $TYPE"${NC} fi fi + +exit $ret diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c index 6e6235185a86..563bbe18c172 100644 --- a/tools/testing/selftests/bpf/test_lru_map.c +++ b/tools/testing/selftests/bpf/test_lru_map.c @@ -878,11 +878,11 @@ int main(int argc, char **argv) assert(nr_cpus != -1); printf("nr_cpus:%d\n\n", nr_cpus); - for (f = 0; f < sizeof(map_flags) / sizeof(*map_flags); f++) { + for (f = 0; f < ARRAY_SIZE(map_flags); f++) { unsigned int tgt_free = (map_flags[f] & BPF_F_NO_COMMON_LRU) ? PERCPU_FREE_TARGET : LOCAL_FREE_TARGET; - for (t = 0; t < sizeof(map_types) / sizeof(*map_types); t++) { + for (t = 0; t < ARRAY_SIZE(map_types); t++) { test_lru_sanity0(map_types[t], map_flags[f]); test_lru_sanity1(map_types[t], map_flags[f], tgt_free); test_lru_sanity2(map_types[t], map_flags[f], tgt_free); diff --git a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh index b497bb85b667..6c69c42b1d60 100755 --- a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh +++ b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh @@ -120,6 +120,14 @@ setup() ip netns exec ${NS2} sysctl -wq net.ipv4.conf.default.rp_filter=0 ip netns exec ${NS3} sysctl -wq net.ipv4.conf.default.rp_filter=0 + # disable IPv6 DAD because it sometimes takes too long and fails tests + ip netns exec ${NS1} sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec ${NS2} sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec ${NS3} sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec ${NS1} sysctl -wq net.ipv6.conf.default.accept_dad=0 + ip netns exec ${NS2} sysctl -wq net.ipv6.conf.default.accept_dad=0 + ip netns exec ${NS3} sysctl -wq net.ipv6.conf.default.accept_dad=0 + ip link add veth1 type veth peer name veth2 ip link add veth3 type veth peer name veth4 ip link add veth5 type veth peer name veth6 @@ -289,7 +297,7 @@ test_ping() ip netns exec ${NS1} ping -c 1 -W 1 -I veth1 ${IPv4_DST} 2>&1 > /dev/null RET=$? elif [ "${PROTO}" == "IPv6" ] ; then - ip netns exec ${NS1} ping6 -c 1 -W 6 -I veth1 ${IPv6_DST} 2>&1 > /dev/null + ip netns exec ${NS1} ping6 -c 1 -W 1 -I veth1 ${IPv6_DST} 2>&1 > /dev/null RET=$? else echo " test_ping: unknown PROTO: ${PROTO}" diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c index f0c8d05ba6d1..f3d5d7ac6505 100644 --- a/tools/testing/selftests/bpf/test_sock_addr.c +++ b/tools/testing/selftests/bpf/test_sock_addr.c @@ -723,7 +723,7 @@ static int xmsg_ret_only_prog_load(const struct sock_addr_test *test, BPF_MOV64_IMM(BPF_REG_0, rc), BPF_EXIT_INSN(), }; - return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn)); + return load_insns(test, insns, ARRAY_SIZE(insns)); } static int sendmsg_allow_prog_load(const struct sock_addr_test *test) @@ -795,7 +795,7 @@ static int sendmsg4_rw_asm_prog_load(const struct sock_addr_test *test) BPF_EXIT_INSN(), }; - return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn)); + return load_insns(test, insns, ARRAY_SIZE(insns)); } static int recvmsg4_rw_c_prog_load(const struct sock_addr_test *test) @@ -858,7 +858,7 @@ static int sendmsg6_rw_dst_asm_prog_load(const struct sock_addr_test *test, BPF_EXIT_INSN(), }; - return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn)); + return load_insns(test, insns, ARRAY_SIZE(insns)); } static int sendmsg6_rw_asm_prog_load(const struct sock_addr_test *test) diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index 1ba7e7346afb..dfb4f5c0fcb9 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -1786,7 +1786,7 @@ static int populate_progs(char *bpf_file) i++; } - for (i = 0; i < sizeof(map_fd)/sizeof(int); i++) { + for (i = 0; i < ARRAY_SIZE(map_fd); i++) { maps[i] = bpf_object__find_map_by_name(obj, map_names[i]); map_fd[i] = bpf_map__fd(maps[i]); if (map_fd[i] < 0) { @@ -1867,7 +1867,7 @@ static int __test_selftests(int cg_fd, struct sockmap_options *opt) } /* Tests basic commands and APIs */ - for (i = 0; i < sizeof(test)/sizeof(struct _test); i++) { + for (i = 0; i < ARRAY_SIZE(test); i++) { struct _test t = test[i]; if (check_whitelist(&t, opt) != 0) diff --git a/tools/testing/selftests/bpf/test_tunnel.sh b/tools/testing/selftests/bpf/test_tunnel.sh index ca1372924023..2817d9948d59 100755 --- a/tools/testing/selftests/bpf/test_tunnel.sh +++ b/tools/testing/selftests/bpf/test_tunnel.sh @@ -39,7 +39,7 @@ # from root namespace, the following operations happen: # 1) Route lookup shows 10.1.1.100/24 belongs to tnl dev, fwd to tnl dev. # 2) Tnl device's egress BPF program is triggered and set the tunnel metadata, -# with remote_ip=172.16.1.200 and others. +# with remote_ip=172.16.1.100 and others. # 3) Outer tunnel header is prepended and route the packet to veth1's egress # 4) veth0's ingress queue receive the tunneled packet at namespace at_ns0 # 5) Tunnel protocol handler, ex: vxlan_rcv, decap the packet diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 92e3465fbae8..a2cd236c32eb 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -22,8 +22,6 @@ #include <limits.h> #include <assert.h> -#include <sys/capability.h> - #include <linux/unistd.h> #include <linux/filter.h> #include <linux/bpf_perf_event.h> @@ -42,6 +40,7 @@ # define CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS 1 # endif #endif +#include "cap_helpers.h" #include "bpf_rand.h" #include "bpf_util.h" #include "test_btf.h" @@ -62,6 +61,10 @@ #define F_NEEDS_EFFICIENT_UNALIGNED_ACCESS (1 << 0) #define F_LOAD_WITH_STRICT_ALIGNMENT (1 << 1) +/* need CAP_BPF, CAP_NET_ADMIN, CAP_PERFMON to load progs */ +#define ADMIN_CAPS (1ULL << CAP_NET_ADMIN | \ + 1ULL << CAP_PERFMON | \ + 1ULL << CAP_BPF) #define UNPRIV_SYSCTL "kernel/unprivileged_bpf_disabled" static bool unpriv_disabled = false; static int skips; @@ -973,47 +976,19 @@ struct libcap { static int set_admin(bool admin) { - cap_t caps; - /* need CAP_BPF, CAP_NET_ADMIN, CAP_PERFMON to load progs */ - const cap_value_t cap_net_admin = CAP_NET_ADMIN; - const cap_value_t cap_sys_admin = CAP_SYS_ADMIN; - struct libcap *cap; - int ret = -1; - - caps = cap_get_proc(); - if (!caps) { - perror("cap_get_proc"); - return -1; - } - cap = (struct libcap *)caps; - if (cap_set_flag(caps, CAP_EFFECTIVE, 1, &cap_sys_admin, CAP_CLEAR)) { - perror("cap_set_flag clear admin"); - goto out; - } - if (cap_set_flag(caps, CAP_EFFECTIVE, 1, &cap_net_admin, - admin ? CAP_SET : CAP_CLEAR)) { - perror("cap_set_flag set_or_clear net"); - goto out; - } - /* libcap is likely old and simply ignores CAP_BPF and CAP_PERFMON, - * so update effective bits manually - */ + int err; + if (admin) { - cap->data[1].effective |= 1 << (38 /* CAP_PERFMON */ - 32); - cap->data[1].effective |= 1 << (39 /* CAP_BPF */ - 32); + err = cap_enable_effective(ADMIN_CAPS, NULL); + if (err) + perror("cap_enable_effective(ADMIN_CAPS)"); } else { - cap->data[1].effective &= ~(1 << (38 - 32)); - cap->data[1].effective &= ~(1 << (39 - 32)); - } - if (cap_set_proc(caps)) { - perror("cap_set_proc"); - goto out; + err = cap_disable_effective(ADMIN_CAPS, NULL); + if (err) + perror("cap_disable_effective(ADMIN_CAPS)"); } - ret = 0; -out: - if (cap_free(caps)) - perror("cap_free"); - return ret; + + return err; } static int do_prog_test_run(int fd_prog, bool unpriv, uint32_t expected_val, @@ -1291,31 +1266,18 @@ fail_log: static bool is_admin(void) { - cap_flag_value_t net_priv = CAP_CLEAR; - bool perfmon_priv = false; - bool bpf_priv = false; - struct libcap *cap; - cap_t caps; - -#ifdef CAP_IS_SUPPORTED - if (!CAP_IS_SUPPORTED(CAP_SETFCAP)) { - perror("cap_get_flag"); - return false; - } -#endif - caps = cap_get_proc(); - if (!caps) { - perror("cap_get_proc"); + __u64 caps; + + /* The test checks for finer cap as CAP_NET_ADMIN, + * CAP_PERFMON, and CAP_BPF instead of CAP_SYS_ADMIN. + * Thus, disable CAP_SYS_ADMIN at the beginning. + */ + if (cap_disable_effective(1ULL << CAP_SYS_ADMIN, &caps)) { + perror("cap_disable_effective(CAP_SYS_ADMIN)"); return false; } - cap = (struct libcap *)caps; - bpf_priv = cap->data[1].effective & (1 << (39/* CAP_BPF */ - 32)); - perfmon_priv = cap->data[1].effective & (1 << (38/* CAP_PERFMON */ - 32)); - if (cap_get_flag(caps, CAP_NET_ADMIN, CAP_EFFECTIVE, &net_priv)) - perror("cap_get_flag NET"); - if (cap_free(caps)) - perror("cap_free"); - return bpf_priv && perfmon_priv && net_priv == CAP_SET; + + return (caps & ADMIN_CAPS) == ADMIN_CAPS; } static void get_unpriv_disabled() diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index ca6abae9b09c..3d6217e3aff7 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -34,6 +34,13 @@ int load_kallsyms(void) if (!f) return -ENOENT; + /* + * This is called/used from multiplace places, + * load symbols just once. + */ + if (sym_cnt) + return 0; + while (fgets(buf, sizeof(buf), f)) { if (sscanf(buf, "%p %c %s", &addr, &symbol, func) != 3) break; diff --git a/tools/testing/selftests/bpf/verifier/bounds_deduction.c b/tools/testing/selftests/bpf/verifier/bounds_deduction.c index 91869aea6d64..3931c481e30c 100644 --- a/tools/testing/selftests/bpf/verifier/bounds_deduction.c +++ b/tools/testing/selftests/bpf/verifier/bounds_deduction.c @@ -105,7 +105,7 @@ BPF_EXIT_INSN(), }, .errstr_unpriv = "R1 has pointer with unsupported alu operation", - .errstr = "dereference of modified ctx ptr", + .errstr = "negative offset ctx ptr R1 off=-1 disallowed", .result = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index f890333259ad..2e03decb11b6 100644 --- a/tools/testing/selftests/bpf/verifier/calls.c +++ b/tools/testing/selftests/bpf/verifier/calls.c @@ -116,6 +116,89 @@ }, }, { + "calls: invalid kfunc call: reg->off must be zero when passed to release kfunc", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "R1 must have zero offset when passed to release func", + .fixup_kfunc_btf_id = { + { "bpf_kfunc_call_test_acquire", 3 }, + { "bpf_kfunc_call_memb_release", 8 }, + }, +}, +{ + "calls: invalid kfunc call: PTR_TO_BTF_ID with negative offset", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, 16), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -4), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .fixup_kfunc_btf_id = { + { "bpf_kfunc_call_test_acquire", 3 }, + { "bpf_kfunc_call_test_release", 9 }, + }, + .result_unpriv = REJECT, + .result = REJECT, + .errstr = "negative offset ptr_ ptr R1 off=-4 disallowed", +}, +{ + "calls: invalid kfunc call: PTR_TO_BTF_ID with variable offset", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_0, 4), + BPF_JMP_IMM(BPF_JLE, BPF_REG_2, 4, 3), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JGE, BPF_REG_2, 0, 3), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_2), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .fixup_kfunc_btf_id = { + { "bpf_kfunc_call_test_acquire", 3 }, + { "bpf_kfunc_call_test_release", 9 }, + { "bpf_kfunc_call_test_release", 13 }, + { "bpf_kfunc_call_test_release", 17 }, + }, + .result_unpriv = REJECT, + .result = REJECT, + .errstr = "variable ptr_ access var_off=(0x0; 0x7) disallowed", +}, +{ "calls: basic sanity", .insns = { BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), diff --git a/tools/testing/selftests/bpf/verifier/ctx.c b/tools/testing/selftests/bpf/verifier/ctx.c index 60f6fbe03f19..c8eaf0536c24 100644 --- a/tools/testing/selftests/bpf/verifier/ctx.c +++ b/tools/testing/selftests/bpf/verifier/ctx.c @@ -58,7 +58,7 @@ }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = REJECT, - .errstr = "dereference of modified ctx ptr", + .errstr = "negative offset ctx ptr R1 off=-612 disallowed", }, { "pass modified ctx pointer to helper, 2", @@ -71,8 +71,8 @@ }, .result_unpriv = REJECT, .result = REJECT, - .errstr_unpriv = "dereference of modified ctx ptr", - .errstr = "dereference of modified ctx ptr", + .errstr_unpriv = "negative offset ctx ptr R1 off=-612 disallowed", + .errstr = "negative offset ctx ptr R1 off=-612 disallowed", }, { "pass modified ctx pointer to helper, 3", @@ -141,7 +141,7 @@ .prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, .expected_attach_type = BPF_CGROUP_UDP6_SENDMSG, .result = REJECT, - .errstr = "dereference of modified ctx ptr", + .errstr = "negative offset ctx ptr R1 off=-612 disallowed", }, { "pass ctx or null check, 5: null (connect)", |