diff options
Diffstat (limited to 'tools')
122 files changed, 8506 insertions, 1269 deletions
diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index 11250c4734fe..3b7ba037af95 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -28,7 +28,7 @@ MAP COMMANDS | **bpftool** **map** { **show** | **list** } [*MAP*] | **bpftool** **map create** *FILE* **type** *TYPE* **key** *KEY_SIZE* **value** *VALUE_SIZE* \ | **entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**inner_map** *MAP*] \ -| [**dev** *NAME*] +| [**offload_dev** *NAME*] | **bpftool** **map dump** *MAP* | **bpftool** **map update** *MAP* [**key** *DATA*] [**value** *VALUE*] [*UPDATE_FLAGS*] | **bpftool** **map lookup** *MAP* [**key** *DATA*] @@ -73,7 +73,7 @@ DESCRIPTION maps. On such kernels bpftool will automatically emit this information as well. - **bpftool map create** *FILE* **type** *TYPE* **key** *KEY_SIZE* **value** *VALUE_SIZE* **entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**inner_map** *MAP*] [**dev** *NAME*] + **bpftool map create** *FILE* **type** *TYPE* **key** *KEY_SIZE* **value** *VALUE_SIZE* **entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**inner_map** *MAP*] [**offload_dev** *NAME*] Create a new map with given parameters and pin it to *bpffs* as *FILE*. @@ -86,8 +86,8 @@ DESCRIPTION kernel needs it to collect metadata related to the inner maps that the new map will work with. - Keyword **dev** expects a network interface name, and is used - to request hardware offload for the map. + Keyword **offload_dev** expects a network interface name, + and is used to request hardware offload for the map. **bpftool map dump** *MAP* Dump all entries in a given *MAP*. In case of **name**, diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 9443c524bb76..dcae81bd27ed 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -31,7 +31,7 @@ PROG COMMANDS | **bpftool** **prog dump xlated** *PROG* [{ **file** *FILE* | [**opcodes**] [**linum**] [**visual**] }] | **bpftool** **prog dump jited** *PROG* [{ **file** *FILE* | [**opcodes**] [**linum**] }] | **bpftool** **prog pin** *PROG* *FILE* -| **bpftool** **prog** { **load** | **loadall** } *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*] [**pinmaps** *MAP_DIR*] [**autoattach**] +| **bpftool** **prog** { **load** | **loadall** } *OBJ* *PATH* [**type** *TYPE*] [**map** { **idx** *IDX* | **name** *NAME* } *MAP*] [{ **offload_dev** | **xdpmeta_dev** } *NAME*] [**pinmaps** *MAP_DIR*] [**autoattach**] | **bpftool** **prog attach** *PROG* *ATTACH_TYPE* [*MAP*] | **bpftool** **prog detach** *PROG* *ATTACH_TYPE* [*MAP*] | **bpftool** **prog tracelog** @@ -129,7 +129,7 @@ DESCRIPTION contain a dot character ('.'), which is reserved for future extensions of *bpffs*. - **bpftool prog { load | loadall }** *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*] [**pinmaps** *MAP_DIR*] [**autoattach**] + **bpftool prog { load | loadall }** *OBJ* *PATH* [**type** *TYPE*] [**map** { **idx** *IDX* | **name** *NAME* } *MAP*] [{ **offload_dev** | **xdpmeta_dev** } *NAME*] [**pinmaps** *MAP_DIR*] [**autoattach**] Load bpf program(s) from binary *OBJ* and pin as *PATH*. **bpftool prog load** pins only the first program from the *OBJ* as *PATH*. **bpftool prog loadall** pins all programs @@ -143,8 +143,11 @@ DESCRIPTION to be replaced in the ELF file counting from 0, while *NAME* allows to replace a map by name. *MAP* specifies the map to use, referring to it by **id** or through a **pinned** file. - If **dev** *NAME* is specified program will be loaded onto - given networking device (offload). + If **offload_dev** *NAME* is specified program will be loaded + onto given networking device (offload). + If **xdpmeta_dev** *NAME* is specified program will become + device-bound without offloading, this facilitates access + to XDP metadata. Optional **pinmaps** argument can be provided to pin all maps under *MAP_DIR* directory. diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index e7234d1a5306..085bf18f3659 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -278,7 +278,7 @@ _bpftool() _bpftool_get_prog_tags return 0 ;; - dev) + dev|offload_dev|xdpmeta_dev) _sysfs_get_netdevs return 0 ;; @@ -508,7 +508,8 @@ _bpftool() ;; *) COMPREPLY=( $( compgen -W "map" -- "$cur" ) ) - _bpftool_once_attr 'type dev pinmaps autoattach' + _bpftool_once_attr 'type pinmaps autoattach' + _bpftool_one_of_list 'offload_dev xdpmeta_dev' return 0 ;; esac @@ -733,7 +734,7 @@ _bpftool() esac ;; *) - _bpftool_once_attr 'type key value entries name flags dev' + _bpftool_once_attr 'type key value entries name flags offload_dev' if _bpftool_search_list 'array_of_maps' 'hash_of_maps'; then _bpftool_once_attr 'inner_map' fi diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 1360c82ae732..cc6e6aae2447 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -68,7 +68,7 @@ void p_info(const char *fmt, ...) va_end(ap); } -static bool is_bpffs(char *path) +static bool is_bpffs(const char *path) { struct statfs st_fs; @@ -244,13 +244,16 @@ int open_obj_pinned_any(const char *path, enum bpf_obj_type exp_type) return fd; } -int mount_bpffs_for_pin(const char *name) +int mount_bpffs_for_pin(const char *name, bool is_dir) { char err_str[ERR_MAX_LEN]; char *file; char *dir; int err = 0; + if (is_dir && is_bpffs(name)) + return err; + file = malloc(strlen(name) + 1); if (!file) { p_err("mem alloc failed"); @@ -286,7 +289,7 @@ int do_pin_fd(int fd, const char *name) { int err; - err = mount_bpffs_for_pin(name); + err = mount_bpffs_for_pin(name, false); if (err) return err; diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index da16e6a27ccc..0675d6a46413 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -167,12 +167,12 @@ static int get_vendor_id(int ifindex) return strtol(buf, NULL, 0); } -static int read_procfs(const char *path) +static long read_procfs(const char *path) { char *endptr, *line = NULL; size_t len = 0; FILE *fd; - int res; + long res; fd = fopen(path, "r"); if (!fd) @@ -194,7 +194,7 @@ static int read_procfs(const char *path) static void probe_unprivileged_disabled(void) { - int res; + long res; /* No support for C-style ouptut */ @@ -216,14 +216,14 @@ static void probe_unprivileged_disabled(void) printf("Unable to retrieve required privileges for bpf() syscall\n"); break; default: - printf("bpf() syscall restriction has unknown value %d\n", res); + printf("bpf() syscall restriction has unknown value %ld\n", res); } } } static void probe_jit_enable(void) { - int res; + long res; /* No support for C-style ouptut */ @@ -245,7 +245,7 @@ static void probe_jit_enable(void) printf("Unable to retrieve JIT-compiler status\n"); break; default: - printf("JIT-compiler status has unknown value %d\n", + printf("JIT-compiler status has unknown value %ld\n", res); } } @@ -253,7 +253,7 @@ static void probe_jit_enable(void) static void probe_jit_harden(void) { - int res; + long res; /* No support for C-style ouptut */ @@ -275,7 +275,7 @@ static void probe_jit_harden(void) printf("Unable to retrieve JIT hardening status\n"); break; default: - printf("JIT hardening status has unknown value %d\n", + printf("JIT hardening status has unknown value %ld\n", res); } } @@ -283,7 +283,7 @@ static void probe_jit_harden(void) static void probe_jit_kallsyms(void) { - int res; + long res; /* No support for C-style ouptut */ @@ -302,14 +302,14 @@ static void probe_jit_kallsyms(void) printf("Unable to retrieve JIT kallsyms export status\n"); break; default: - printf("JIT kallsyms exports status has unknown value %d\n", res); + printf("JIT kallsyms exports status has unknown value %ld\n", res); } } } static void probe_jit_limit(void) { - int res; + long res; /* No support for C-style ouptut */ @@ -322,7 +322,7 @@ static void probe_jit_limit(void) printf("Unable to retrieve global memory limit for JIT compiler for unprivileged users\n"); break; default: - printf("Global memory limit for JIT compiler for unprivileged users is %d bytes\n", res); + printf("Global memory limit for JIT compiler for unprivileged users is %ld bytes\n", res); } } } diff --git a/tools/bpf/bpftool/iter.c b/tools/bpf/bpftool/iter.c index 9a1d2365a297..6b0e5202ca7a 100644 --- a/tools/bpf/bpftool/iter.c +++ b/tools/bpf/bpftool/iter.c @@ -76,7 +76,7 @@ static int do_pin(int argc, char **argv) goto close_obj; } - err = mount_bpffs_for_pin(path); + err = mount_bpffs_for_pin(path, false); if (err) goto close_link; diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c index d98dbc50cf4c..2d786072ed0d 100644 --- a/tools/bpf/bpftool/link.c +++ b/tools/bpf/bpftool/link.c @@ -195,6 +195,8 @@ static int show_link_close_json(int fd, struct bpf_link_info *info) show_link_attach_type_json(info->tracing.attach_type, json_wtr); + jsonw_uint_field(json_wtr, "target_obj_id", info->tracing.target_obj_id); + jsonw_uint_field(json_wtr, "target_btf_id", info->tracing.target_btf_id); break; case BPF_LINK_TYPE_CGROUP: jsonw_lluint_field(json_wtr, "cgroup_id", @@ -212,7 +214,10 @@ static int show_link_close_json(int fd, struct bpf_link_info *info) case BPF_LINK_TYPE_NETFILTER: netfilter_dump_json(info, json_wtr); break; - + case BPF_LINK_TYPE_STRUCT_OPS: + jsonw_uint_field(json_wtr, "map_id", + info->struct_ops.map_id); + break; default: break; } @@ -245,7 +250,10 @@ static void show_link_header_plain(struct bpf_link_info *info) else printf("type %u ", info->type); - printf("prog %u ", info->prog_id); + if (info->type == BPF_LINK_TYPE_STRUCT_OPS) + printf("map %u ", info->struct_ops.map_id); + else + printf("prog %u ", info->prog_id); } static void show_link_attach_type_plain(__u32 attach_type) @@ -369,6 +377,10 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info) printf("\n\tprog_type %u ", prog_info.type); show_link_attach_type_plain(info->tracing.attach_type); + if (info->tracing.target_obj_id || info->tracing.target_btf_id) + printf("\n\ttarget_obj_id %u target_btf_id %u ", + info->tracing.target_obj_id, + info->tracing.target_btf_id); break; case BPF_LINK_TYPE_CGROUP: printf("\n\tcgroup_id %zu ", (size_t)info->cgroup.cgroup_id); diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index a49534d7eafa..b8bb08d10dec 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -142,7 +142,7 @@ const char *get_fd_type_name(enum bpf_obj_type type); char *get_fdinfo(int fd, const char *key); int open_obj_pinned(const char *path, bool quiet); int open_obj_pinned_any(const char *path, enum bpf_obj_type exp_type); -int mount_bpffs_for_pin(const char *name); +int mount_bpffs_for_pin(const char *name, bool is_dir); int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(int *, char ***)); int do_pin_fd(int fd, const char *name); diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index aaeb8939e137..f98f7bbea2b1 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -139,6 +139,9 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key, print_hex_data_json(key, info->key_size); jsonw_name(json_wtr, "value"); print_hex_data_json(value, info->value_size); + if (map_is_map_of_maps(info->type)) + jsonw_uint_field(json_wtr, "inner_map_id", + *(unsigned int *)value); if (btf) { struct btf_dumper d = { .btf = btf, @@ -259,8 +262,13 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key, } if (info->value_size) { - printf("value:%c", break_names ? '\n' : ' '); - fprint_hex(stdout, value, info->value_size, " "); + if (map_is_map_of_maps(info->type)) { + printf("inner_map_id:%c", break_names ? '\n' : ' '); + printf("%u ", *(unsigned int *)value); + } else { + printf("value:%c", break_names ? '\n' : ' '); + fprint_hex(stdout, value, info->value_size, " "); + } } printf("\n"); @@ -1279,6 +1287,11 @@ static int do_create(int argc, char **argv) "flags")) goto exit; } else if (is_prefix(*argv, "dev")) { + p_info("Warning: 'bpftool map create [...] dev <ifname>' syntax is deprecated.\n" + "Going further, please use 'offload_dev <ifname>' to request hardware offload for the map."); + goto offload_dev; + } else if (is_prefix(*argv, "offload_dev")) { +offload_dev: NEXT_ARG(); if (attr.map_ifindex) { @@ -1423,7 +1436,7 @@ static int do_help(int argc, char **argv) "Usage: %1$s %2$s { show | list } [MAP]\n" " %1$s %2$s create FILE type TYPE key KEY_SIZE value VALUE_SIZE \\\n" " entries MAX_ENTRIES name NAME [flags FLAGS] \\\n" - " [inner_map MAP] [dev NAME]\n" + " [inner_map MAP] [offload_dev NAME]\n" " %1$s %2$s dump MAP\n" " %1$s %2$s update MAP [key DATA] [value VALUE] [UPDATE_FLAGS]\n" " %1$s %2$s lookup MAP [key DATA]\n" diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 91b6075b2db3..8443a149dd17 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -1517,12 +1517,13 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) struct bpf_program *prog = NULL, *pos; unsigned int old_map_fds = 0; const char *pinmaps = NULL; + __u32 xdpmeta_ifindex = 0; + __u32 offload_ifindex = 0; bool auto_attach = false; struct bpf_object *obj; struct bpf_map *map; const char *pinfile; unsigned int i, j; - __u32 ifindex = 0; const char *file; int idx, err; @@ -1614,17 +1615,46 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) map_replace[old_map_fds].fd = fd; old_map_fds++; } else if (is_prefix(*argv, "dev")) { + p_info("Warning: 'bpftool prog load [...] dev <ifname>' syntax is deprecated.\n" + "Going further, please use 'offload_dev <ifname>' to offload program to device.\n" + "For applications using XDP hints only, use 'xdpmeta_dev <ifname>'."); + goto offload_dev; + } else if (is_prefix(*argv, "offload_dev")) { +offload_dev: NEXT_ARG(); - if (ifindex) { - p_err("offload device already specified"); + if (offload_ifindex) { + p_err("offload_dev already specified"); + goto err_free_reuse_maps; + } else if (xdpmeta_ifindex) { + p_err("xdpmeta_dev and offload_dev are mutually exclusive"); + goto err_free_reuse_maps; + } + if (!REQ_ARGS(1)) + goto err_free_reuse_maps; + + offload_ifindex = if_nametoindex(*argv); + if (!offload_ifindex) { + p_err("unrecognized netdevice '%s': %s", + *argv, strerror(errno)); + goto err_free_reuse_maps; + } + NEXT_ARG(); + } else if (is_prefix(*argv, "xdpmeta_dev")) { + NEXT_ARG(); + + if (xdpmeta_ifindex) { + p_err("xdpmeta_dev already specified"); + goto err_free_reuse_maps; + } else if (offload_ifindex) { + p_err("xdpmeta_dev and offload_dev are mutually exclusive"); goto err_free_reuse_maps; } if (!REQ_ARGS(1)) goto err_free_reuse_maps; - ifindex = if_nametoindex(*argv); - if (!ifindex) { + xdpmeta_ifindex = if_nametoindex(*argv); + if (!xdpmeta_ifindex) { p_err("unrecognized netdevice '%s': %s", *argv, strerror(errno)); goto err_free_reuse_maps; @@ -1671,7 +1701,12 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) goto err_close_obj; } - bpf_program__set_ifindex(pos, ifindex); + if (prog_type == BPF_PROG_TYPE_XDP && xdpmeta_ifindex) { + bpf_program__set_flags(pos, BPF_F_XDP_DEV_BOUND_ONLY); + bpf_program__set_ifindex(pos, xdpmeta_ifindex); + } else { + bpf_program__set_ifindex(pos, offload_ifindex); + } if (bpf_program__type(pos) != prog_type) bpf_program__set_type(pos, prog_type); bpf_program__set_expected_attach_type(pos, expected_attach_type); @@ -1709,7 +1744,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) idx = 0; bpf_object__for_each_map(map, obj) { if (bpf_map__type(map) != BPF_MAP_TYPE_PERF_EVENT_ARRAY) - bpf_map__set_ifindex(map, ifindex); + bpf_map__set_ifindex(map, offload_ifindex); if (j < old_map_fds && idx == map_replace[j].idx) { err = bpf_map__reuse_fd(map, map_replace[j++].fd); @@ -1739,7 +1774,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) goto err_close_obj; } - err = mount_bpffs_for_pin(pinfile); + err = mount_bpffs_for_pin(pinfile, !first_prog_only); if (err) goto err_close_obj; @@ -2416,7 +2451,7 @@ static int do_help(int argc, char **argv) " %1$s %2$s dump jited PROG [{ file FILE | [opcodes] [linum] }]\n" " %1$s %2$s pin PROG FILE\n" " %1$s %2$s { load | loadall } OBJ PATH \\\n" - " [type TYPE] [dev NAME] \\\n" + " [type TYPE] [{ offload_dev | xdpmeta_dev } NAME] \\\n" " [map { idx IDX | name NAME } MAP]\\\n" " [pinmaps MAP_DIR]\n" " [autoattach]\n" diff --git a/tools/bpf/bpftool/struct_ops.c b/tools/bpf/bpftool/struct_ops.c index 57c3da70aa31..3ebc9fe91e0e 100644 --- a/tools/bpf/bpftool/struct_ops.c +++ b/tools/bpf/bpftool/struct_ops.c @@ -509,7 +509,7 @@ static int do_register(int argc, char **argv) if (argc == 1) linkdir = GET_ARG(); - if (linkdir && mount_bpffs_for_pin(linkdir)) { + if (linkdir && mount_bpffs_for_pin(linkdir, true)) { p_err("can't mount bpffs for pinning"); return -1; } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index c994ff5b157c..6961a7b70028 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1273,6 +1273,9 @@ enum { /* Create a map that will be registered/unregesitered by the backed bpf_link */ BPF_F_LINK = (1U << 13), + +/* Get path from provided FD in BPF_OBJ_PIN/BPF_OBJ_GET commands */ + BPF_F_PATH_FD = (1U << 14), }; /* Flags for BPF_PROG_QUERY. */ @@ -1421,6 +1424,13 @@ union bpf_attr { __aligned_u64 pathname; __u32 bpf_fd; __u32 file_flags; + /* Same as dirfd in openat() syscall; see openat(2) + * manpage for details of path FD and pathname semantics; + * path_fd should accompanied by BPF_F_PATH_FD flag set in + * file_flags field, otherwise it should be set to zero; + * if BPF_F_PATH_FD flag is not set, AT_FDCWD is assumed. + */ + __s32 path_fd; }; struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */ diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 128ac723c4ea..ed86b37d8024 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -572,20 +572,30 @@ int bpf_map_update_batch(int fd, const void *keys, const void *values, __u32 *co (void *)keys, (void *)values, count, opts); } -int bpf_obj_pin(int fd, const char *pathname) +int bpf_obj_pin_opts(int fd, const char *pathname, const struct bpf_obj_pin_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, file_flags); + const size_t attr_sz = offsetofend(union bpf_attr, path_fd); union bpf_attr attr; int ret; + if (!OPTS_VALID(opts, bpf_obj_pin_opts)) + return libbpf_err(-EINVAL); + memset(&attr, 0, attr_sz); + attr.path_fd = OPTS_GET(opts, path_fd, 0); attr.pathname = ptr_to_u64((void *)pathname); + attr.file_flags = OPTS_GET(opts, file_flags, 0); attr.bpf_fd = fd; ret = sys_bpf(BPF_OBJ_PIN, &attr, attr_sz); return libbpf_err_errno(ret); } +int bpf_obj_pin(int fd, const char *pathname) +{ + return bpf_obj_pin_opts(fd, pathname, NULL); +} + int bpf_obj_get(const char *pathname) { return bpf_obj_get_opts(pathname, NULL); @@ -593,7 +603,7 @@ int bpf_obj_get(const char *pathname) int bpf_obj_get_opts(const char *pathname, const struct bpf_obj_get_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, file_flags); + const size_t attr_sz = offsetofend(union bpf_attr, path_fd); union bpf_attr attr; int fd; @@ -601,6 +611,7 @@ int bpf_obj_get_opts(const char *pathname, const struct bpf_obj_get_opts *opts) return libbpf_err(-EINVAL); memset(&attr, 0, attr_sz); + attr.path_fd = OPTS_GET(opts, path_fd, 0); attr.pathname = ptr_to_u64((void *)pathname); attr.file_flags = OPTS_GET(opts, file_flags, 0); diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index a2c091389b18..9aa0ee473754 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -284,16 +284,30 @@ LIBBPF_API int bpf_map_update_batch(int fd, const void *keys, const void *values __u32 *count, const struct bpf_map_batch_opts *opts); -struct bpf_obj_get_opts { +struct bpf_obj_pin_opts { size_t sz; /* size of this struct for forward/backward compatibility */ __u32 file_flags; + int path_fd; size_t :0; }; -#define bpf_obj_get_opts__last_field file_flags +#define bpf_obj_pin_opts__last_field path_fd LIBBPF_API int bpf_obj_pin(int fd, const char *pathname); +LIBBPF_API int bpf_obj_pin_opts(int fd, const char *pathname, + const struct bpf_obj_pin_opts *opts); + +struct bpf_obj_get_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + + __u32 file_flags; + int path_fd; + + size_t :0; +}; +#define bpf_obj_get_opts__last_field path_fd + LIBBPF_API int bpf_obj_get(const char *pathname); LIBBPF_API int bpf_obj_get_opts(const char *pathname, const struct bpf_obj_get_opts *opts); diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index 929a3baca8ef..bbab9ad9dc5a 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -77,16 +77,21 @@ /* * Helper macros to manipulate data structures */ -#ifndef offsetof -#define offsetof(TYPE, MEMBER) ((unsigned long)&((TYPE *)0)->MEMBER) -#endif -#ifndef container_of + +/* offsetof() definition that uses __builtin_offset() might not preserve field + * offset CO-RE relocation properly, so force-redefine offsetof() using + * old-school approach which works with CO-RE correctly + */ +#undef offsetof +#define offsetof(type, member) ((unsigned long)&((type *)0)->member) + +/* redefined container_of() to ensure we use the above offsetof() macro */ +#undef container_of #define container_of(ptr, type, member) \ ({ \ void *__mptr = (void *)(ptr); \ ((type *)(__mptr - offsetof(type, member))); \ }) -#endif /* * Compiler (optimization) barrier. diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h index 6fb3d0f9af17..be076a4041ab 100644 --- a/tools/lib/bpf/bpf_tracing.h +++ b/tools/lib/bpf/bpf_tracing.h @@ -351,6 +351,7 @@ struct pt_regs___arm64 { * https://github.com/riscv-non-isa/riscv-elf-psabi-doc/blob/master/riscv-cc.adoc#risc-v-calling-conventions */ +/* riscv provides struct user_regs_struct instead of struct pt_regs to userspace */ #define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x)) #define __PT_PARM1_REG a0 #define __PT_PARM2_REG a1 @@ -383,7 +384,7 @@ struct pt_regs___arm64 { * https://raw.githubusercontent.com/wiki/foss-for-synopsys-dwc-arc-processors/toolchain/files/ARCv2_ABI.pdf */ -/* arc provides struct user_pt_regs instead of struct pt_regs to userspace */ +/* arc provides struct user_regs_struct instead of struct pt_regs to userspace */ #define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x)) #define __PT_PARM1_REG scratch.r0 #define __PT_PARM2_REG scratch.r1 diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 0a2c079244b6..8484b563b53d 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -1064,7 +1064,7 @@ static struct btf *btf_parse_raw(const char *path, struct btf *base_btf) int err = 0; long sz; - f = fopen(path, "rb"); + f = fopen(path, "rbe"); if (!f) { err = -errno; goto err_out; diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index 580985ee5545..4d9f30bf7f01 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -2250,9 +2250,25 @@ static int btf_dump_type_data_check_overflow(struct btf_dump *d, const struct btf_type *t, __u32 id, const void *data, - __u8 bits_offset) + __u8 bits_offset, + __u8 bit_sz) { - __s64 size = btf__resolve_size(d->btf, id); + __s64 size; + + if (bit_sz) { + /* bits_offset is at most 7. bit_sz is at most 128. */ + __u8 nr_bytes = (bits_offset + bit_sz + 7) / 8; + + /* When bit_sz is non zero, it is called from + * btf_dump_struct_data() where it only cares about + * negative error value. + * Return nr_bytes in success case to make it + * consistent as the regular integer case below. + */ + return data + nr_bytes > d->typed_dump->data_end ? -E2BIG : nr_bytes; + } + + size = btf__resolve_size(d->btf, id); if (size < 0 || size >= INT_MAX) { pr_warn("unexpected size [%zu] for id [%u]\n", @@ -2407,7 +2423,7 @@ static int btf_dump_dump_type_data(struct btf_dump *d, { int size, err = 0; - size = btf_dump_type_data_check_overflow(d, t, id, data, bits_offset); + size = btf_dump_type_data_check_overflow(d, t, id, data, bits_offset, bit_sz); if (size < 0) return size; err = btf_dump_type_data_check_zero(d, t, id, data, bits_offset, bit_sz); diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c index 83e8e3bfd8ff..cf3323fd47b8 100644 --- a/tools/lib/bpf/gen_loader.c +++ b/tools/lib/bpf/gen_loader.c @@ -703,17 +703,17 @@ static void emit_relo_kfunc_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo /* obtain fd in BPF_REG_9 */ emit(gen, BPF_MOV64_REG(BPF_REG_9, BPF_REG_7)); emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_9, 32)); - /* jump to fd_array store if fd denotes module BTF */ - emit(gen, BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 0, 2)); - /* set the default value for off */ - emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), 0)); - /* skip BTF fd store for vmlinux BTF */ - emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 4)); /* load fd_array slot pointer */ emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE, 0, 0, 0, blob_fd_array_off(gen, btf_fd_idx))); - /* store BTF fd in slot */ + /* store BTF fd in slot, 0 for vmlinux */ emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_9, 0)); + /* jump to insn[insn_idx].off store if fd denotes module BTF */ + emit(gen, BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 0, 2)); + /* set the default value for off */ + emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), 0)); + /* skip BTF fd store for vmlinux BTF */ + emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 1)); /* store index into insn[insn_idx].off */ emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), btf_fd_idx)); log: diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index a27f6e9ccce7..214f828ece6b 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -1501,16 +1501,36 @@ static struct bpf_map *bpf_object__add_map(struct bpf_object *obj) return map; } -static size_t bpf_map_mmap_sz(const struct bpf_map *map) +static size_t bpf_map_mmap_sz(unsigned int value_sz, unsigned int max_entries) { - long page_sz = sysconf(_SC_PAGE_SIZE); + const long page_sz = sysconf(_SC_PAGE_SIZE); size_t map_sz; - map_sz = (size_t)roundup(map->def.value_size, 8) * map->def.max_entries; + map_sz = (size_t)roundup(value_sz, 8) * max_entries; map_sz = roundup(map_sz, page_sz); return map_sz; } +static int bpf_map_mmap_resize(struct bpf_map *map, size_t old_sz, size_t new_sz) +{ + void *mmaped; + + if (!map->mmaped) + return -EINVAL; + + if (old_sz == new_sz) + return 0; + + mmaped = mmap(NULL, new_sz, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0); + if (mmaped == MAP_FAILED) + return -errno; + + memcpy(mmaped, map->mmaped, min(old_sz, new_sz)); + munmap(map->mmaped, old_sz); + map->mmaped = mmaped; + return 0; +} + static char *internal_map_name(struct bpf_object *obj, const char *real_name) { char map_name[BPF_OBJ_NAME_LEN], *p; @@ -1609,6 +1629,7 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, { struct bpf_map_def *def; struct bpf_map *map; + size_t mmap_sz; int err; map = bpf_object__add_map(obj); @@ -1643,7 +1664,8 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, pr_debug("map '%s' (global data): at sec_idx %d, offset %zu, flags %x.\n", map->name, map->sec_idx, map->sec_offset, def->map_flags); - map->mmaped = mmap(NULL, bpf_map_mmap_sz(map), PROT_READ | PROT_WRITE, + mmap_sz = bpf_map_mmap_sz(map->def.value_size, map->def.max_entries); + map->mmaped = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0); if (map->mmaped == MAP_FAILED) { err = -errno; @@ -4330,7 +4352,7 @@ static int bpf_get_map_info_from_fdinfo(int fd, struct bpf_map_info *info) snprintf(file, sizeof(file), "/proc/%d/fdinfo/%d", getpid(), fd); memset(info, 0, sizeof(*info)); - fp = fopen(file, "r"); + fp = fopen(file, "re"); if (!fp) { err = -errno; pr_warn("failed to open %s: %d. No procfs support?\n", file, @@ -4393,18 +4415,17 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd) if (!new_name) return libbpf_err(-errno); - new_fd = open("/", O_RDONLY | O_CLOEXEC); + /* + * Like dup(), but make sure new FD is >= 3 and has O_CLOEXEC set. + * This is similar to what we do in ensure_good_fd(), but without + * closing original FD. + */ + new_fd = fcntl(fd, F_DUPFD_CLOEXEC, 3); if (new_fd < 0) { err = -errno; goto err_free_new_name; } - new_fd = dup3(fd, new_fd, O_CLOEXEC); - if (new_fd < 0) { - err = -errno; - goto err_close_new_fd; - } - err = zclose(map->fd); if (err) { err = -errno; @@ -7434,7 +7455,7 @@ int libbpf_kallsyms_parse(kallsyms_cb_t cb, void *ctx) int ret, err = 0; FILE *f; - f = fopen("/proc/kallsyms", "r"); + f = fopen("/proc/kallsyms", "re"); if (!f) { err = -errno; pr_warn("failed to open /proc/kallsyms: %d\n", err); @@ -8295,7 +8316,10 @@ static void bpf_map__destroy(struct bpf_map *map) map->init_slots_sz = 0; if (map->mmaped) { - munmap(map->mmaped, bpf_map_mmap_sz(map)); + size_t mmap_sz; + + mmap_sz = bpf_map_mmap_sz(map->def.value_size, map->def.max_entries); + munmap(map->mmaped, mmap_sz); map->mmaped = NULL; } @@ -9413,10 +9437,103 @@ __u32 bpf_map__value_size(const struct bpf_map *map) return map->def.value_size; } +static int map_btf_datasec_resize(struct bpf_map *map, __u32 size) +{ + struct btf *btf; + struct btf_type *datasec_type, *var_type; + struct btf_var_secinfo *var; + const struct btf_type *array_type; + const struct btf_array *array; + int vlen, element_sz, new_array_id; + __u32 nr_elements; + + /* check btf existence */ + btf = bpf_object__btf(map->obj); + if (!btf) + return -ENOENT; + + /* verify map is datasec */ + datasec_type = btf_type_by_id(btf, bpf_map__btf_value_type_id(map)); + if (!btf_is_datasec(datasec_type)) { + pr_warn("map '%s': cannot be resized, map value type is not a datasec\n", + bpf_map__name(map)); + return -EINVAL; + } + + /* verify datasec has at least one var */ + vlen = btf_vlen(datasec_type); + if (vlen == 0) { + pr_warn("map '%s': cannot be resized, map value datasec is empty\n", + bpf_map__name(map)); + return -EINVAL; + } + + /* verify last var in the datasec is an array */ + var = &btf_var_secinfos(datasec_type)[vlen - 1]; + var_type = btf_type_by_id(btf, var->type); + array_type = skip_mods_and_typedefs(btf, var_type->type, NULL); + if (!btf_is_array(array_type)) { + pr_warn("map '%s': cannot be resized, last var must be an array\n", + bpf_map__name(map)); + return -EINVAL; + } + + /* verify request size aligns with array */ + array = btf_array(array_type); + element_sz = btf__resolve_size(btf, array->type); + if (element_sz <= 0 || (size - var->offset) % element_sz != 0) { + pr_warn("map '%s': cannot be resized, element size (%d) doesn't align with new total size (%u)\n", + bpf_map__name(map), element_sz, size); + return -EINVAL; + } + + /* create a new array based on the existing array, but with new length */ + nr_elements = (size - var->offset) / element_sz; + new_array_id = btf__add_array(btf, array->index_type, array->type, nr_elements); + if (new_array_id < 0) + return new_array_id; + + /* adding a new btf type invalidates existing pointers to btf objects, + * so refresh pointers before proceeding + */ + datasec_type = btf_type_by_id(btf, map->btf_value_type_id); + var = &btf_var_secinfos(datasec_type)[vlen - 1]; + var_type = btf_type_by_id(btf, var->type); + + /* finally update btf info */ + datasec_type->size = size; + var->size = size - var->offset; + var_type->type = new_array_id; + + return 0; +} + int bpf_map__set_value_size(struct bpf_map *map, __u32 size) { if (map->fd >= 0) return libbpf_err(-EBUSY); + + if (map->mmaped) { + int err; + size_t mmap_old_sz, mmap_new_sz; + + mmap_old_sz = bpf_map_mmap_sz(map->def.value_size, map->def.max_entries); + mmap_new_sz = bpf_map_mmap_sz(size, map->def.max_entries); + err = bpf_map_mmap_resize(map, mmap_old_sz, mmap_new_sz); + if (err) { + pr_warn("map '%s': failed to resize memory-mapped region: %d\n", + bpf_map__name(map), err); + return err; + } + err = map_btf_datasec_resize(map, size); + if (err && err != -ENOENT) { + pr_warn("map '%s': failed to adjust resized BTF, clearing BTF key/value info: %d\n", + bpf_map__name(map), err); + map->btf_value_type_id = 0; + map->btf_key_type_id = 0; + } + } + map->def.value_size = size; return 0; } @@ -9442,7 +9559,7 @@ int bpf_map__set_initial_value(struct bpf_map *map, return 0; } -const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize) +void *bpf_map__initial_value(struct bpf_map *map, size_t *psize) { if (!map->mmaped) return NULL; @@ -9958,7 +10075,7 @@ static int parse_uint_from_file(const char *file, const char *fmt) int err, ret; FILE *f; - f = fopen(file, "r"); + f = fopen(file, "re"); if (!f) { err = -errno; pr_debug("failed to open '%s': %s\n", file, @@ -12694,7 +12811,7 @@ int bpf_object__load_skeleton(struct bpf_object_skeleton *s) for (i = 0; i < s->map_cnt; i++) { struct bpf_map *map = *s->maps[i].map; - size_t mmap_sz = bpf_map_mmap_sz(map); + size_t mmap_sz = bpf_map_mmap_sz(map->def.value_size, map->def.max_entries); int prot, map_fd = bpf_map__fd(map); void **mmaped = s->maps[i].mmaped; @@ -12721,8 +12838,7 @@ int bpf_object__load_skeleton(struct bpf_object_skeleton *s) * as per normal clean up procedure, so we don't need to worry * about it from skeleton's clean up perspective. */ - *mmaped = mmap(map->mmaped, mmap_sz, prot, - MAP_SHARED | MAP_FIXED, map_fd, 0); + *mmaped = mmap(map->mmaped, mmap_sz, prot, MAP_SHARED | MAP_FIXED, map_fd, 0); if (*mmaped == MAP_FAILED) { err = -errno; *mmaped = NULL; diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 0b7362397ea3..754da73c643b 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -869,8 +869,22 @@ LIBBPF_API int bpf_map__set_numa_node(struct bpf_map *map, __u32 numa_node); /* get/set map key size */ LIBBPF_API __u32 bpf_map__key_size(const struct bpf_map *map); LIBBPF_API int bpf_map__set_key_size(struct bpf_map *map, __u32 size); -/* get/set map value size */ +/* get map value size */ LIBBPF_API __u32 bpf_map__value_size(const struct bpf_map *map); +/** + * @brief **bpf_map__set_value_size()** sets map value size. + * @param map the BPF map instance + * @return 0, on success; negative error, otherwise + * + * There is a special case for maps with associated memory-mapped regions, like + * the global data section maps (bss, data, rodata). When this function is used + * on such a map, the mapped region is resized. Afterward, an attempt is made to + * adjust the corresponding BTF info. This attempt is best-effort and can only + * succeed if the last variable of the data section map is an array. The array + * BTF type is replaced by a new BTF array type with a different length. + * Any previously existing pointers returned from bpf_map__initial_value() or + * corresponding data section skeleton pointer must be reinitialized. + */ LIBBPF_API int bpf_map__set_value_size(struct bpf_map *map, __u32 size); /* get map key/value BTF type IDs */ LIBBPF_API __u32 bpf_map__btf_key_type_id(const struct bpf_map *map); @@ -884,7 +898,7 @@ LIBBPF_API int bpf_map__set_map_extra(struct bpf_map *map, __u64 map_extra); LIBBPF_API int bpf_map__set_initial_value(struct bpf_map *map, const void *data, size_t size); -LIBBPF_API const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize); +LIBBPF_API void *bpf_map__initial_value(struct bpf_map *map, size_t *psize); /** * @brief **bpf_map__is_internal()** tells the caller whether or not the diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index a5aa3a383d69..7521a2fb7626 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -391,3 +391,8 @@ LIBBPF_1.2.0 { bpf_map_get_info_by_fd; bpf_prog_get_info_by_fd; } LIBBPF_1.1.0; + +LIBBPF_1.3.0 { + global: + bpf_obj_pin_opts; +} LIBBPF_1.2.0; diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index b7d443129f1c..9c4db90b92b6 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -38,7 +38,7 @@ static __u32 get_ubuntu_kernel_version(void) if (faccessat(AT_FDCWD, ubuntu_kver_file, R_OK, AT_EACCESS) != 0) return 0; - f = fopen(ubuntu_kver_file, "r"); + f = fopen(ubuntu_kver_file, "re"); if (!f) return 0; diff --git a/tools/lib/bpf/libbpf_version.h b/tools/lib/bpf/libbpf_version.h index 1fd2eeac5cfc..290411ddb39e 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 1 -#define LIBBPF_MINOR_VERSION 2 +#define LIBBPF_MINOR_VERSION 3 #endif /* __LIBBPF_VERSION_H */ diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c index 086eef355ab3..f1a141555f08 100644 --- a/tools/lib/bpf/usdt.c +++ b/tools/lib/bpf/usdt.c @@ -466,7 +466,7 @@ static int parse_vma_segs(int pid, const char *lib_path, struct elf_seg **segs, proceed: sprintf(line, "/proc/%d/maps", pid); - f = fopen(line, "r"); + f = fopen(line, "re"); if (!f) { err = -errno; pr_warn("usdt: failed to open '%s' to get base addr of '%s': %d\n", @@ -954,8 +954,7 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct spec_map_fd = bpf_map__fd(man->specs_map); ip_map_fd = bpf_map__fd(man->ip_to_spec_id_map); - /* TODO: perform path resolution similar to uprobe's */ - fd = open(path, O_RDONLY); + fd = open(path, O_RDONLY | O_CLOEXEC); if (fd < 0) { err = -errno; pr_warn("usdt: failed to open ELF binary '%s': %d\n", path, err); diff --git a/tools/net/ynl/Makefile b/tools/net/ynl/Makefile new file mode 100644 index 000000000000..d664b36deb5b --- /dev/null +++ b/tools/net/ynl/Makefile @@ -0,0 +1,19 @@ +# SPDX-License-Identifier: GPL-2.0 + +SUBDIRS = lib generated samples + +all: $(SUBDIRS) + +$(SUBDIRS): + @if [ -f "$@/Makefile" ] ; then \ + $(MAKE) -C $@ ; \ + fi + +clean hardclean: + @for dir in $(SUBDIRS) ; do \ + if [ -f "$$dir/Makefile" ] ; then \ + $(MAKE) -C $$dir $@; \ + fi \ + done + +.PHONY: clean all $(SUBDIRS) diff --git a/tools/net/ynl/generated/Makefile b/tools/net/ynl/generated/Makefile new file mode 100644 index 000000000000..916723193b60 --- /dev/null +++ b/tools/net/ynl/generated/Makefile @@ -0,0 +1,45 @@ +# SPDX-License-Identifier: GPL-2.0 + +CC=gcc +CFLAGS=-std=gnu11 -O2 -W -Wall -Wextra -Wno-unused-parameter -Wshadow \ + -I../lib/ +ifeq ("$(DEBUG)","1") + CFLAGS += -g -fsanitize=address -fsanitize=leak -static-libasan +endif + +TOOL:=../ynl-gen-c.py + +GENS:=handshake fou netdev +SRCS=$(patsubst %,%-user.c,${GENS}) +HDRS=$(patsubst %,%-user.h,${GENS}) +OBJS=$(patsubst %,%-user.o,${GENS}) + +all: protos.a $(HDRS) $(SRCS) $(KHDRS) $(KSRCS) $(UAPI) regen + +protos.a: $(OBJS) + @echo -e "\tAR $@" + @ar rcs $@ $(OBJS) + +%-user.h: ../../../../Documentation/netlink/specs/%.yaml $(TOOL) + @echo -e "\tGEN $@" + @$(TOOL) --mode user --header --spec $< > $@ + +%-user.c: ../../../../Documentation/netlink/specs/%.yaml $(TOOL) + @echo -e "\tGEN $@" + @$(TOOL) --mode user --source --spec $< > $@ + +%-user.o: %-user.c %-user.h + @echo -e "\tCC $@" + @$(COMPILE.c) -c -o $@ $< + +clean: + rm -f *.o + +hardclean: clean + rm -f *.c *.h *.a + +regen: + @../ynl-regen.sh + +.PHONY: all clean hardclean regen +.DEFAULT_GOAL: all diff --git a/tools/net/ynl/generated/fou-user.c b/tools/net/ynl/generated/fou-user.c new file mode 100644 index 000000000000..c99b5d438021 --- /dev/null +++ b/tools/net/ynl/generated/fou-user.c @@ -0,0 +1,340 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/fou.yaml */ +/* YNL-GEN user source */ + +#include <stdlib.h> +#include "fou-user.h" +#include "ynl.h" +#include <linux/fou.h> + +#include <stdlib.h> +#include <stdio.h> +#include <string.h> +#include <libmnl/libmnl.h> +#include <linux/genetlink.h> + +/* Enums */ +static const char * const fou_op_strmap[] = { + [FOU_CMD_UNSPEC] = "unspec", + [FOU_CMD_ADD] = "add", + [FOU_CMD_DEL] = "del", + [FOU_CMD_GET] = "get", +}; + +const char *fou_op_str(int op) +{ + if (op < 0 || op >= (int)MNL_ARRAY_SIZE(fou_op_strmap)) + return NULL; + return fou_op_strmap[op]; +} + +static const char * const fou_encap_type_strmap[] = { + [0] = "unspec", + [1] = "direct", + [2] = "gue", +}; + +const char *fou_encap_type_str(int value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(fou_encap_type_strmap)) + return NULL; + return fou_encap_type_strmap[value]; +} + +/* Policies */ +extern struct ynl_policy_nest fou_nest; + +struct ynl_policy_attr fou_policy[FOU_ATTR_MAX + 1] = { + [FOU_ATTR_UNSPEC] = { .name = "unspec", .type = YNL_PT_REJECT, }, + [FOU_ATTR_PORT] = { .name = "port", .type = YNL_PT_U16, }, + [FOU_ATTR_AF] = { .name = "af", .type = YNL_PT_U8, }, + [FOU_ATTR_IPPROTO] = { .name = "ipproto", .type = YNL_PT_U8, }, + [FOU_ATTR_TYPE] = { .name = "type", .type = YNL_PT_U8, }, + [FOU_ATTR_REMCSUM_NOPARTIAL] = { .name = "remcsum_nopartial", .type = YNL_PT_FLAG, }, + [FOU_ATTR_LOCAL_V4] = { .name = "local_v4", .type = YNL_PT_U32, }, + [FOU_ATTR_LOCAL_V6] = { .name = "local_v6", .type = YNL_PT_BINARY,}, + [FOU_ATTR_PEER_V4] = { .name = "peer_v4", .type = YNL_PT_U32, }, + [FOU_ATTR_PEER_V6] = { .name = "peer_v6", .type = YNL_PT_BINARY,}, + [FOU_ATTR_PEER_PORT] = { .name = "peer_port", .type = YNL_PT_U16, }, + [FOU_ATTR_IFINDEX] = { .name = "ifindex", .type = YNL_PT_U32, }, +}; + +struct ynl_policy_nest fou_nest = { + .max_attr = FOU_ATTR_MAX, + .table = fou_policy, +}; + +/* Common nested types */ +/* ============== FOU_CMD_ADD ============== */ +/* FOU_CMD_ADD - do */ +void fou_add_req_free(struct fou_add_req *req) +{ + free(req->local_v6); + free(req->peer_v6); + free(req); +} + +int fou_add(struct ynl_sock *ys, struct fou_add_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, FOU_CMD_ADD, 1); + ys->req_policy = &fou_nest; + + if (req->_present.port) + mnl_attr_put_u16(nlh, FOU_ATTR_PORT, req->port); + if (req->_present.ipproto) + mnl_attr_put_u8(nlh, FOU_ATTR_IPPROTO, req->ipproto); + if (req->_present.type) + mnl_attr_put_u8(nlh, FOU_ATTR_TYPE, req->type); + if (req->_present.remcsum_nopartial) + mnl_attr_put(nlh, FOU_ATTR_REMCSUM_NOPARTIAL, 0, NULL); + if (req->_present.local_v4) + mnl_attr_put_u32(nlh, FOU_ATTR_LOCAL_V4, req->local_v4); + if (req->_present.peer_v4) + mnl_attr_put_u32(nlh, FOU_ATTR_PEER_V4, req->peer_v4); + if (req->_present.local_v6_len) + mnl_attr_put(nlh, FOU_ATTR_LOCAL_V6, req->_present.local_v6_len, req->local_v6); + if (req->_present.peer_v6_len) + mnl_attr_put(nlh, FOU_ATTR_PEER_V6, req->_present.peer_v6_len, req->peer_v6); + if (req->_present.peer_port) + mnl_attr_put_u16(nlh, FOU_ATTR_PEER_PORT, req->peer_port); + if (req->_present.ifindex) + mnl_attr_put_u32(nlh, FOU_ATTR_IFINDEX, req->ifindex); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== FOU_CMD_DEL ============== */ +/* FOU_CMD_DEL - do */ +void fou_del_req_free(struct fou_del_req *req) +{ + free(req->local_v6); + free(req->peer_v6); + free(req); +} + +int fou_del(struct ynl_sock *ys, struct fou_del_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, FOU_CMD_DEL, 1); + ys->req_policy = &fou_nest; + + if (req->_present.af) + mnl_attr_put_u8(nlh, FOU_ATTR_AF, req->af); + if (req->_present.ifindex) + mnl_attr_put_u32(nlh, FOU_ATTR_IFINDEX, req->ifindex); + if (req->_present.port) + mnl_attr_put_u16(nlh, FOU_ATTR_PORT, req->port); + if (req->_present.peer_port) + mnl_attr_put_u16(nlh, FOU_ATTR_PEER_PORT, req->peer_port); + if (req->_present.local_v4) + mnl_attr_put_u32(nlh, FOU_ATTR_LOCAL_V4, req->local_v4); + if (req->_present.peer_v4) + mnl_attr_put_u32(nlh, FOU_ATTR_PEER_V4, req->peer_v4); + if (req->_present.local_v6_len) + mnl_attr_put(nlh, FOU_ATTR_LOCAL_V6, req->_present.local_v6_len, req->local_v6); + if (req->_present.peer_v6_len) + mnl_attr_put(nlh, FOU_ATTR_PEER_V6, req->_present.peer_v6_len, req->peer_v6); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== FOU_CMD_GET ============== */ +/* FOU_CMD_GET - do */ +void fou_get_req_free(struct fou_get_req *req) +{ + free(req->local_v6); + free(req->peer_v6); + free(req); +} + +void fou_get_rsp_free(struct fou_get_rsp *rsp) +{ + free(rsp->local_v6); + free(rsp->peer_v6); + free(rsp); +} + +int fou_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + struct fou_get_rsp *dst; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + if (mnl_attr_get_type(attr) == FOU_ATTR_PORT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.port = 1; + dst->port = mnl_attr_get_u16(attr); + } + else if (mnl_attr_get_type(attr) == FOU_ATTR_IPPROTO) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.ipproto = 1; + dst->ipproto = mnl_attr_get_u8(attr); + } + else if (mnl_attr_get_type(attr) == FOU_ATTR_TYPE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.type = 1; + dst->type = mnl_attr_get_u8(attr); + } + else if (mnl_attr_get_type(attr) == FOU_ATTR_REMCSUM_NOPARTIAL) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.remcsum_nopartial = 1; + } + else if (mnl_attr_get_type(attr) == FOU_ATTR_LOCAL_V4) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.local_v4 = 1; + dst->local_v4 = mnl_attr_get_u32(attr); + } + else if (mnl_attr_get_type(attr) == FOU_ATTR_PEER_V4) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.peer_v4 = 1; + dst->peer_v4 = mnl_attr_get_u32(attr); + } + else if (mnl_attr_get_type(attr) == FOU_ATTR_LOCAL_V6) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = mnl_attr_get_payload_len(attr); + dst->_present.local_v6_len = len; + dst->local_v6 = malloc(len); + memcpy(dst->local_v6, mnl_attr_get_payload(attr), len); + } + else if (mnl_attr_get_type(attr) == FOU_ATTR_PEER_V6) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = mnl_attr_get_payload_len(attr); + dst->_present.peer_v6_len = len; + dst->peer_v6 = malloc(len); + memcpy(dst->peer_v6, mnl_attr_get_payload(attr), len); + } + else if (mnl_attr_get_type(attr) == FOU_ATTR_PEER_PORT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.peer_port = 1; + dst->peer_port = mnl_attr_get_u16(attr); + } + else if (mnl_attr_get_type(attr) == FOU_ATTR_IFINDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.ifindex = 1; + dst->ifindex = mnl_attr_get_u32(attr); + } + } + + return MNL_CB_OK; +} + +struct fou_get_rsp *fou_get(struct ynl_sock *ys, struct fou_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct fou_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, FOU_CMD_GET, 1); + ys->req_policy = &fou_nest; + yrs.yarg.rsp_policy = &fou_nest; + + if (req->_present.af) + mnl_attr_put_u8(nlh, FOU_ATTR_AF, req->af); + if (req->_present.ifindex) + mnl_attr_put_u32(nlh, FOU_ATTR_IFINDEX, req->ifindex); + if (req->_present.port) + mnl_attr_put_u16(nlh, FOU_ATTR_PORT, req->port); + if (req->_present.peer_port) + mnl_attr_put_u16(nlh, FOU_ATTR_PEER_PORT, req->peer_port); + if (req->_present.local_v4) + mnl_attr_put_u32(nlh, FOU_ATTR_LOCAL_V4, req->local_v4); + if (req->_present.peer_v4) + mnl_attr_put_u32(nlh, FOU_ATTR_PEER_V4, req->peer_v4); + if (req->_present.local_v6_len) + mnl_attr_put(nlh, FOU_ATTR_LOCAL_V6, req->_present.local_v6_len, req->local_v6); + if (req->_present.peer_v6_len) + mnl_attr_put(nlh, FOU_ATTR_PEER_V6, req->_present.peer_v6_len, req->peer_v6); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = fou_get_rsp_parse; + yrs.rsp_cmd = FOU_CMD_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + fou_get_rsp_free(rsp); + return NULL; +} + +/* FOU_CMD_GET - dump */ +void fou_get_list_free(struct fou_get_list *rsp) +{ + struct fou_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.local_v6); + free(rsp->obj.peer_v6); + free(rsp); + } +} + +struct fou_get_list *fou_get_dump(struct ynl_sock *ys) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct fou_get_list); + yds.cb = fou_get_rsp_parse; + yds.rsp_cmd = FOU_CMD_GET; + yds.rsp_policy = &fou_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, FOU_CMD_GET, 1); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + fou_get_list_free(yds.first); + return NULL; +} + +const struct ynl_family ynl_fou_family = { + .name = "fou", +}; diff --git a/tools/net/ynl/generated/fou-user.h b/tools/net/ynl/generated/fou-user.h new file mode 100644 index 000000000000..d8ab50579cd1 --- /dev/null +++ b/tools/net/ynl/generated/fou-user.h @@ -0,0 +1,337 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/fou.yaml */ +/* YNL-GEN user header */ + +#ifndef _LINUX_FOU_GEN_H +#define _LINUX_FOU_GEN_H + +#include <stdlib.h> +#include <string.h> +#include <linux/types.h> +#include <linux/fou.h> + +struct ynl_sock; + +extern const struct ynl_family ynl_fou_family; + +/* Enums */ +const char *fou_op_str(int op); +const char *fou_encap_type_str(int value); + +/* Common nested types */ +/* ============== FOU_CMD_ADD ============== */ +/* FOU_CMD_ADD - do */ +struct fou_add_req { + struct { + __u32 port:1; + __u32 ipproto:1; + __u32 type:1; + __u32 remcsum_nopartial:1; + __u32 local_v4:1; + __u32 peer_v4:1; + __u32 local_v6_len; + __u32 peer_v6_len; + __u32 peer_port:1; + __u32 ifindex:1; + } _present; + + __u16 port /* big-endian */; + __u8 ipproto; + __u8 type; + __u32 local_v4; + __u32 peer_v4; + void *local_v6; + void *peer_v6; + __u16 peer_port /* big-endian */; + __s32 ifindex; +}; + +static inline struct fou_add_req *fou_add_req_alloc(void) +{ + return calloc(1, sizeof(struct fou_add_req)); +} +void fou_add_req_free(struct fou_add_req *req); + +static inline void +fou_add_req_set_port(struct fou_add_req *req, __u16 port /* big-endian */) +{ + req->_present.port = 1; + req->port = port; +} +static inline void +fou_add_req_set_ipproto(struct fou_add_req *req, __u8 ipproto) +{ + req->_present.ipproto = 1; + req->ipproto = ipproto; +} +static inline void fou_add_req_set_type(struct fou_add_req *req, __u8 type) +{ + req->_present.type = 1; + req->type = type; +} +static inline void fou_add_req_set_remcsum_nopartial(struct fou_add_req *req) +{ + req->_present.remcsum_nopartial = 1; +} +static inline void +fou_add_req_set_local_v4(struct fou_add_req *req, __u32 local_v4) +{ + req->_present.local_v4 = 1; + req->local_v4 = local_v4; +} +static inline void +fou_add_req_set_peer_v4(struct fou_add_req *req, __u32 peer_v4) +{ + req->_present.peer_v4 = 1; + req->peer_v4 = peer_v4; +} +static inline void +fou_add_req_set_local_v6(struct fou_add_req *req, const void *local_v6, + size_t len) +{ + free(req->local_v6); + req->local_v6 = malloc(req->_present.local_v6_len); + memcpy(req->local_v6, local_v6, req->_present.local_v6_len); +} +static inline void +fou_add_req_set_peer_v6(struct fou_add_req *req, const void *peer_v6, + size_t len) +{ + free(req->peer_v6); + req->peer_v6 = malloc(req->_present.peer_v6_len); + memcpy(req->peer_v6, peer_v6, req->_present.peer_v6_len); +} +static inline void +fou_add_req_set_peer_port(struct fou_add_req *req, + __u16 peer_port /* big-endian */) +{ + req->_present.peer_port = 1; + req->peer_port = peer_port; +} +static inline void +fou_add_req_set_ifindex(struct fou_add_req *req, __s32 ifindex) +{ + req->_present.ifindex = 1; + req->ifindex = ifindex; +} + +/* + * Add port. + */ +int fou_add(struct ynl_sock *ys, struct fou_add_req *req); + +/* ============== FOU_CMD_DEL ============== */ +/* FOU_CMD_DEL - do */ +struct fou_del_req { + struct { + __u32 af:1; + __u32 ifindex:1; + __u32 port:1; + __u32 peer_port:1; + __u32 local_v4:1; + __u32 peer_v4:1; + __u32 local_v6_len; + __u32 peer_v6_len; + } _present; + + __u8 af; + __s32 ifindex; + __u16 port /* big-endian */; + __u16 peer_port /* big-endian */; + __u32 local_v4; + __u32 peer_v4; + void *local_v6; + void *peer_v6; +}; + +static inline struct fou_del_req *fou_del_req_alloc(void) +{ + return calloc(1, sizeof(struct fou_del_req)); +} +void fou_del_req_free(struct fou_del_req *req); + +static inline void fou_del_req_set_af(struct fou_del_req *req, __u8 af) +{ + req->_present.af = 1; + req->af = af; +} +static inline void +fou_del_req_set_ifindex(struct fou_del_req *req, __s32 ifindex) +{ + req->_present.ifindex = 1; + req->ifindex = ifindex; +} +static inline void +fou_del_req_set_port(struct fou_del_req *req, __u16 port /* big-endian */) +{ + req->_present.port = 1; + req->port = port; +} +static inline void +fou_del_req_set_peer_port(struct fou_del_req *req, + __u16 peer_port /* big-endian */) +{ + req->_present.peer_port = 1; + req->peer_port = peer_port; +} +static inline void +fou_del_req_set_local_v4(struct fou_del_req *req, __u32 local_v4) +{ + req->_present.local_v4 = 1; + req->local_v4 = local_v4; +} +static inline void +fou_del_req_set_peer_v4(struct fou_del_req *req, __u32 peer_v4) +{ + req->_present.peer_v4 = 1; + req->peer_v4 = peer_v4; +} +static inline void +fou_del_req_set_local_v6(struct fou_del_req *req, const void *local_v6, + size_t len) +{ + free(req->local_v6); + req->local_v6 = malloc(req->_present.local_v6_len); + memcpy(req->local_v6, local_v6, req->_present.local_v6_len); +} +static inline void +fou_del_req_set_peer_v6(struct fou_del_req *req, const void *peer_v6, + size_t len) +{ + free(req->peer_v6); + req->peer_v6 = malloc(req->_present.peer_v6_len); + memcpy(req->peer_v6, peer_v6, req->_present.peer_v6_len); +} + +/* + * Delete port. + */ +int fou_del(struct ynl_sock *ys, struct fou_del_req *req); + +/* ============== FOU_CMD_GET ============== */ +/* FOU_CMD_GET - do */ +struct fou_get_req { + struct { + __u32 af:1; + __u32 ifindex:1; + __u32 port:1; + __u32 peer_port:1; + __u32 local_v4:1; + __u32 peer_v4:1; + __u32 local_v6_len; + __u32 peer_v6_len; + } _present; + + __u8 af; + __s32 ifindex; + __u16 port /* big-endian */; + __u16 peer_port /* big-endian */; + __u32 local_v4; + __u32 peer_v4; + void *local_v6; + void *peer_v6; +}; + +static inline struct fou_get_req *fou_get_req_alloc(void) +{ + return calloc(1, sizeof(struct fou_get_req)); +} +void fou_get_req_free(struct fou_get_req *req); + +static inline void fou_get_req_set_af(struct fou_get_req *req, __u8 af) +{ + req->_present.af = 1; + req->af = af; +} +static inline void +fou_get_req_set_ifindex(struct fou_get_req *req, __s32 ifindex) +{ + req->_present.ifindex = 1; + req->ifindex = ifindex; +} +static inline void +fou_get_req_set_port(struct fou_get_req *req, __u16 port /* big-endian */) +{ + req->_present.port = 1; + req->port = port; +} +static inline void +fou_get_req_set_peer_port(struct fou_get_req *req, + __u16 peer_port /* big-endian */) +{ + req->_present.peer_port = 1; + req->peer_port = peer_port; +} +static inline void +fou_get_req_set_local_v4(struct fou_get_req *req, __u32 local_v4) +{ + req->_present.local_v4 = 1; + req->local_v4 = local_v4; +} +static inline void +fou_get_req_set_peer_v4(struct fou_get_req *req, __u32 peer_v4) +{ + req->_present.peer_v4 = 1; + req->peer_v4 = peer_v4; +} +static inline void +fou_get_req_set_local_v6(struct fou_get_req *req, const void *local_v6, + size_t len) +{ + free(req->local_v6); + req->local_v6 = malloc(req->_present.local_v6_len); + memcpy(req->local_v6, local_v6, req->_present.local_v6_len); +} +static inline void +fou_get_req_set_peer_v6(struct fou_get_req *req, const void *peer_v6, + size_t len) +{ + free(req->peer_v6); + req->peer_v6 = malloc(req->_present.peer_v6_len); + memcpy(req->peer_v6, peer_v6, req->_present.peer_v6_len); +} + +struct fou_get_rsp { + struct { + __u32 port:1; + __u32 ipproto:1; + __u32 type:1; + __u32 remcsum_nopartial:1; + __u32 local_v4:1; + __u32 peer_v4:1; + __u32 local_v6_len; + __u32 peer_v6_len; + __u32 peer_port:1; + __u32 ifindex:1; + } _present; + + __u16 port /* big-endian */; + __u8 ipproto; + __u8 type; + __u32 local_v4; + __u32 peer_v4; + void *local_v6; + void *peer_v6; + __u16 peer_port /* big-endian */; + __s32 ifindex; +}; + +void fou_get_rsp_free(struct fou_get_rsp *rsp); + +/* + * Get tunnel info. + */ +struct fou_get_rsp *fou_get(struct ynl_sock *ys, struct fou_get_req *req); + +/* FOU_CMD_GET - dump */ +struct fou_get_list { + struct fou_get_list *next; + struct fou_get_rsp obj __attribute__ ((aligned (8))); +}; + +void fou_get_list_free(struct fou_get_list *rsp); + +struct fou_get_list *fou_get_dump(struct ynl_sock *ys); + +#endif /* _LINUX_FOU_GEN_H */ diff --git a/tools/net/ynl/generated/handshake-user.c b/tools/net/ynl/generated/handshake-user.c new file mode 100644 index 000000000000..fe99c4ef7373 --- /dev/null +++ b/tools/net/ynl/generated/handshake-user.c @@ -0,0 +1,385 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/handshake.yaml */ +/* YNL-GEN user source */ + +#include <stdlib.h> +#include "handshake-user.h" +#include "ynl.h" +#include <linux/handshake.h> + +#include <stdlib.h> +#include <stdio.h> +#include <string.h> +#include <libmnl/libmnl.h> +#include <linux/genetlink.h> + +/* Enums */ +static const char * const handshake_op_strmap[] = { + [HANDSHAKE_CMD_READY] = "ready", + [HANDSHAKE_CMD_ACCEPT] = "accept", + [HANDSHAKE_CMD_DONE] = "done", +}; + +const char *handshake_op_str(int op) +{ + if (op < 0 || op >= (int)MNL_ARRAY_SIZE(handshake_op_strmap)) + return NULL; + return handshake_op_strmap[op]; +} + +static const char * const handshake_handler_class_strmap[] = { + [0] = "none", + [1] = "tlshd", + [2] = "max", +}; + +const char *handshake_handler_class_str(enum handshake_handler_class value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(handshake_handler_class_strmap)) + return NULL; + return handshake_handler_class_strmap[value]; +} + +static const char * const handshake_msg_type_strmap[] = { + [0] = "unspec", + [1] = "clienthello", + [2] = "serverhello", +}; + +const char *handshake_msg_type_str(enum handshake_msg_type value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(handshake_msg_type_strmap)) + return NULL; + return handshake_msg_type_strmap[value]; +} + +static const char * const handshake_auth_strmap[] = { + [0] = "unspec", + [1] = "unauth", + [2] = "psk", + [3] = "x509", +}; + +const char *handshake_auth_str(enum handshake_auth value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(handshake_auth_strmap)) + return NULL; + return handshake_auth_strmap[value]; +} + +/* Policies */ +extern struct ynl_policy_nest handshake_x509_nest; +extern struct ynl_policy_nest handshake_accept_nest; +extern struct ynl_policy_nest handshake_done_nest; + +struct ynl_policy_attr handshake_x509_policy[HANDSHAKE_A_X509_MAX + 1] = { + [HANDSHAKE_A_X509_CERT] = { .name = "cert", .type = YNL_PT_U32, }, + [HANDSHAKE_A_X509_PRIVKEY] = { .name = "privkey", .type = YNL_PT_U32, }, +}; + +struct ynl_policy_nest handshake_x509_nest = { + .max_attr = HANDSHAKE_A_X509_MAX, + .table = handshake_x509_policy, +}; + +struct ynl_policy_attr handshake_accept_policy[HANDSHAKE_A_ACCEPT_MAX + 1] = { + [HANDSHAKE_A_ACCEPT_SOCKFD] = { .name = "sockfd", .type = YNL_PT_U32, }, + [HANDSHAKE_A_ACCEPT_HANDLER_CLASS] = { .name = "handler-class", .type = YNL_PT_U32, }, + [HANDSHAKE_A_ACCEPT_MESSAGE_TYPE] = { .name = "message-type", .type = YNL_PT_U32, }, + [HANDSHAKE_A_ACCEPT_TIMEOUT] = { .name = "timeout", .type = YNL_PT_U32, }, + [HANDSHAKE_A_ACCEPT_AUTH_MODE] = { .name = "auth-mode", .type = YNL_PT_U32, }, + [HANDSHAKE_A_ACCEPT_PEER_IDENTITY] = { .name = "peer-identity", .type = YNL_PT_U32, }, + [HANDSHAKE_A_ACCEPT_CERTIFICATE] = { .name = "certificate", .type = YNL_PT_NEST, .nest = &handshake_x509_nest, }, + [HANDSHAKE_A_ACCEPT_PEERNAME] = { .name = "peername", .type = YNL_PT_NUL_STR, }, +}; + +struct ynl_policy_nest handshake_accept_nest = { + .max_attr = HANDSHAKE_A_ACCEPT_MAX, + .table = handshake_accept_policy, +}; + +struct ynl_policy_attr handshake_done_policy[HANDSHAKE_A_DONE_MAX + 1] = { + [HANDSHAKE_A_DONE_STATUS] = { .name = "status", .type = YNL_PT_U32, }, + [HANDSHAKE_A_DONE_SOCKFD] = { .name = "sockfd", .type = YNL_PT_U32, }, + [HANDSHAKE_A_DONE_REMOTE_AUTH] = { .name = "remote-auth", .type = YNL_PT_U32, }, +}; + +struct ynl_policy_nest handshake_done_nest = { + .max_attr = HANDSHAKE_A_DONE_MAX, + .table = handshake_done_policy, +}; + +/* Common nested types */ +void handshake_x509_free(struct handshake_x509 *obj) +{ +} + +int handshake_x509_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct handshake_x509 *dst = yarg->data; + const struct nlattr *attr; + + mnl_attr_for_each_nested(attr, nested) { + if (mnl_attr_get_type(attr) == HANDSHAKE_A_X509_CERT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.cert = 1; + dst->cert = mnl_attr_get_u32(attr); + } + else if (mnl_attr_get_type(attr) == HANDSHAKE_A_X509_PRIVKEY) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.privkey = 1; + dst->privkey = mnl_attr_get_u32(attr); + } + } + + return 0; +} + +/* ============== HANDSHAKE_CMD_ACCEPT ============== */ +/* HANDSHAKE_CMD_ACCEPT - do */ +void handshake_accept_req_free(struct handshake_accept_req *req) +{ + free(req); +} + +void handshake_accept_rsp_free(struct handshake_accept_rsp *rsp) +{ + unsigned int i; + + free(rsp->peer_identity); + for (i = 0; i < rsp->n_certificate; i++) + handshake_x509_free(&rsp->certificate[i]); + free(rsp->certificate); + free(rsp->peername); + free(rsp); +} + +int handshake_accept_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + struct handshake_accept_rsp *dst; + unsigned int n_peer_identity = 0; + unsigned int n_certificate = 0; + const struct nlattr *attr; + struct ynl_parse_arg parg; + int i; + + dst = yarg->data; + parg.ys = yarg->ys; + + if (dst->certificate) + return ynl_error_parse(yarg, "attribute already present (accept.certificate)"); + if (dst->peer_identity) + return ynl_error_parse(yarg, "attribute already present (accept.peer-identity)"); + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + if (mnl_attr_get_type(attr) == HANDSHAKE_A_ACCEPT_SOCKFD) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.sockfd = 1; + dst->sockfd = mnl_attr_get_u32(attr); + } + else if (mnl_attr_get_type(attr) == HANDSHAKE_A_ACCEPT_MESSAGE_TYPE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.message_type = 1; + dst->message_type = mnl_attr_get_u32(attr); + } + else if (mnl_attr_get_type(attr) == HANDSHAKE_A_ACCEPT_TIMEOUT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.timeout = 1; + dst->timeout = mnl_attr_get_u32(attr); + } + else if (mnl_attr_get_type(attr) == HANDSHAKE_A_ACCEPT_AUTH_MODE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.auth_mode = 1; + dst->auth_mode = mnl_attr_get_u32(attr); + } + else if (mnl_attr_get_type(attr) == HANDSHAKE_A_ACCEPT_PEER_IDENTITY) { + n_peer_identity++; + } + else if (mnl_attr_get_type(attr) == HANDSHAKE_A_ACCEPT_CERTIFICATE) { + n_certificate++; + } + else if (mnl_attr_get_type(attr) == HANDSHAKE_A_ACCEPT_PEERNAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.peername_len = len; + dst->peername = malloc(len + 1); + memcpy(dst->peername, mnl_attr_get_str(attr), len); + dst->peername[len] = 0; + } + } + + if (n_certificate) { + dst->certificate = calloc(n_certificate, sizeof(*dst->certificate)); + dst->n_certificate = n_certificate; + i = 0; + parg.rsp_policy = &handshake_x509_nest; + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + if (mnl_attr_get_type(attr) == HANDSHAKE_A_ACCEPT_CERTIFICATE) { + parg.data = &dst->certificate[i]; + if (handshake_x509_parse(&parg, attr)) + return MNL_CB_ERROR; + i++; + } + } + } + if (n_peer_identity) { + dst->peer_identity = calloc(n_peer_identity, sizeof(*dst->peer_identity)); + dst->n_peer_identity = n_peer_identity; + i = 0; + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + if (mnl_attr_get_type(attr) == HANDSHAKE_A_ACCEPT_PEER_IDENTITY) { + dst->peer_identity[i] = mnl_attr_get_u32(attr); + i++; + } + } + } + + return MNL_CB_OK; +} + +struct handshake_accept_rsp * +handshake_accept(struct ynl_sock *ys, struct handshake_accept_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct handshake_accept_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, HANDSHAKE_CMD_ACCEPT, 1); + ys->req_policy = &handshake_accept_nest; + yrs.yarg.rsp_policy = &handshake_accept_nest; + + if (req->_present.handler_class) + mnl_attr_put_u32(nlh, HANDSHAKE_A_ACCEPT_HANDLER_CLASS, req->handler_class); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = handshake_accept_rsp_parse; + yrs.rsp_cmd = HANDSHAKE_CMD_ACCEPT; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + handshake_accept_rsp_free(rsp); + return NULL; +} + +/* HANDSHAKE_CMD_ACCEPT - notify */ +void handshake_accept_ntf_free(struct handshake_accept_ntf *rsp) +{ + unsigned int i; + + free(rsp->obj.peer_identity); + for (i = 0; i < rsp->obj.n_certificate; i++) + handshake_x509_free(&rsp->obj.certificate[i]); + free(rsp->obj.certificate); + free(rsp->obj.peername); + free(rsp); +} + +/* ============== HANDSHAKE_CMD_DONE ============== */ +/* HANDSHAKE_CMD_DONE - do */ +void handshake_done_req_free(struct handshake_done_req *req) +{ + free(req->remote_auth); + free(req); +} + +int handshake_done(struct ynl_sock *ys, struct handshake_done_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, HANDSHAKE_CMD_DONE, 1); + ys->req_policy = &handshake_done_nest; + + if (req->_present.status) + mnl_attr_put_u32(nlh, HANDSHAKE_A_DONE_STATUS, req->status); + if (req->_present.sockfd) + mnl_attr_put_u32(nlh, HANDSHAKE_A_DONE_SOCKFD, req->sockfd); + for (unsigned int i = 0; i < req->n_remote_auth; i++) + mnl_attr_put_u32(nlh, HANDSHAKE_A_DONE_REMOTE_AUTH, req->remote_auth[i]); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* --------------- Common notification parsing --------------- */ +struct ynl_ntf_base_type *handshake_ntf_parse(struct ynl_sock *ys) +{ + struct ynl_parse_arg yarg = { .ys = ys, }; + struct ynl_ntf_base_type *rsp; + struct genlmsghdr *genlh; + struct nlmsghdr *nlh; + mnl_cb_t parse; + int len, err; + + len = mnl_socket_recvfrom(ys->sock, ys->rx_buf, MNL_SOCKET_BUFFER_SIZE); + if (len < (ssize_t)(sizeof(*nlh) + sizeof(*genlh))) + return NULL; + + nlh = (struct nlmsghdr *)ys->rx_buf; + genlh = mnl_nlmsg_get_payload(nlh); + + switch (genlh->cmd) { + case HANDSHAKE_CMD_READY: + rsp = calloc(1, sizeof(struct handshake_accept_ntf)); + parse = handshake_accept_rsp_parse; + yarg.rsp_policy = &handshake_accept_nest; + rsp->free = (void *)handshake_accept_ntf_free; + break; + default: + ynl_error_unknown_notification(ys, genlh->cmd); + return NULL; + } + + yarg.data = rsp->data; + + err = mnl_cb_run2(ys->rx_buf, len, 0, 0, parse, &yarg, + ynl_cb_array, NLMSG_MIN_TYPE); + if (err < 0) + goto err_free; + + rsp->family = nlh->nlmsg_type; + rsp->cmd = genlh->cmd; + return rsp; + +err_free: + free(rsp); + return NULL; +} + +static const struct ynl_ntf_info handshake_ntf_info[] = { + [HANDSHAKE_CMD_READY] = { + .alloc_sz = sizeof(struct handshake_accept_ntf), + .cb = handshake_accept_rsp_parse, + .policy = &handshake_accept_nest, + .free = (void *)handshake_accept_ntf_free, + }, +}; + +const struct ynl_family ynl_handshake_family = { + .name = "handshake", + .ntf_info = handshake_ntf_info, + .ntf_info_size = MNL_ARRAY_SIZE(handshake_ntf_info), +}; diff --git a/tools/net/ynl/generated/handshake-user.h b/tools/net/ynl/generated/handshake-user.h new file mode 100644 index 000000000000..38e0844f2efd --- /dev/null +++ b/tools/net/ynl/generated/handshake-user.h @@ -0,0 +1,148 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/handshake.yaml */ +/* YNL-GEN user header */ + +#ifndef _LINUX_HANDSHAKE_GEN_H +#define _LINUX_HANDSHAKE_GEN_H + +#include <stdlib.h> +#include <string.h> +#include <linux/types.h> +#include <linux/handshake.h> + +struct ynl_sock; + +extern const struct ynl_family ynl_handshake_family; + +/* Enums */ +const char *handshake_op_str(int op); +const char *handshake_handler_class_str(enum handshake_handler_class value); +const char *handshake_msg_type_str(enum handshake_msg_type value); +const char *handshake_auth_str(enum handshake_auth value); + +/* Common nested types */ +struct handshake_x509 { + struct { + __u32 cert:1; + __u32 privkey:1; + } _present; + + __u32 cert; + __u32 privkey; +}; + +/* ============== HANDSHAKE_CMD_ACCEPT ============== */ +/* HANDSHAKE_CMD_ACCEPT - do */ +struct handshake_accept_req { + struct { + __u32 handler_class:1; + } _present; + + enum handshake_handler_class handler_class; +}; + +static inline struct handshake_accept_req *handshake_accept_req_alloc(void) +{ + return calloc(1, sizeof(struct handshake_accept_req)); +} +void handshake_accept_req_free(struct handshake_accept_req *req); + +static inline void +handshake_accept_req_set_handler_class(struct handshake_accept_req *req, + enum handshake_handler_class handler_class) +{ + req->_present.handler_class = 1; + req->handler_class = handler_class; +} + +struct handshake_accept_rsp { + struct { + __u32 sockfd:1; + __u32 message_type:1; + __u32 timeout:1; + __u32 auth_mode:1; + __u32 peername_len; + } _present; + + __u32 sockfd; + enum handshake_msg_type message_type; + __u32 timeout; + enum handshake_auth auth_mode; + unsigned int n_peer_identity; + __u32 *peer_identity; + unsigned int n_certificate; + struct handshake_x509 *certificate; + char *peername; +}; + +void handshake_accept_rsp_free(struct handshake_accept_rsp *rsp); + +/* + * Handler retrieves next queued handshake request + */ +struct handshake_accept_rsp * +handshake_accept(struct ynl_sock *ys, struct handshake_accept_req *req); + +/* HANDSHAKE_CMD_ACCEPT - notify */ +struct handshake_accept_ntf { + __u16 family; + __u8 cmd; + struct ynl_ntf_base_type *next; + void (*free)(struct handshake_accept_ntf *ntf); + struct handshake_accept_rsp obj __attribute__ ((aligned (8))); +}; + +void handshake_accept_ntf_free(struct handshake_accept_ntf *rsp); + +/* ============== HANDSHAKE_CMD_DONE ============== */ +/* HANDSHAKE_CMD_DONE - do */ +struct handshake_done_req { + struct { + __u32 status:1; + __u32 sockfd:1; + } _present; + + __u32 status; + __u32 sockfd; + unsigned int n_remote_auth; + __u32 *remote_auth; +}; + +static inline struct handshake_done_req *handshake_done_req_alloc(void) +{ + return calloc(1, sizeof(struct handshake_done_req)); +} +void handshake_done_req_free(struct handshake_done_req *req); + +static inline void +handshake_done_req_set_status(struct handshake_done_req *req, __u32 status) +{ + req->_present.status = 1; + req->status = status; +} +static inline void +handshake_done_req_set_sockfd(struct handshake_done_req *req, __u32 sockfd) +{ + req->_present.sockfd = 1; + req->sockfd = sockfd; +} +static inline void +__handshake_done_req_set_remote_auth(struct handshake_done_req *req, + __u32 *remote_auth, + unsigned int n_remote_auth) +{ + free(req->remote_auth); + req->remote_auth = remote_auth; + req->n_remote_auth = n_remote_auth; +} + +/* + * Handler reports handshake completion + */ +int handshake_done(struct ynl_sock *ys, struct handshake_done_req *req); + +/* --------------- Common notification parsing --------------- */ +struct ynl_ntf_base_type *handshake_ntf_parse(struct ynl_sock *ys); + +#endif /* _LINUX_HANDSHAKE_GEN_H */ diff --git a/tools/net/ynl/generated/netdev-user.c b/tools/net/ynl/generated/netdev-user.c new file mode 100644 index 000000000000..aea5c7cc8ead --- /dev/null +++ b/tools/net/ynl/generated/netdev-user.c @@ -0,0 +1,250 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/netdev.yaml */ +/* YNL-GEN user source */ + +#include <stdlib.h> +#include "netdev-user.h" +#include "ynl.h" +#include <linux/netdev.h> + +#include <stdlib.h> +#include <stdio.h> +#include <string.h> +#include <libmnl/libmnl.h> +#include <linux/genetlink.h> + +/* Enums */ +static const char * const netdev_op_strmap[] = { + [NETDEV_CMD_DEV_GET] = "dev-get", + [NETDEV_CMD_DEV_ADD_NTF] = "dev-add-ntf", + [NETDEV_CMD_DEV_DEL_NTF] = "dev-del-ntf", + [NETDEV_CMD_DEV_CHANGE_NTF] = "dev-change-ntf", +}; + +const char *netdev_op_str(int op) +{ + if (op < 0 || op >= (int)MNL_ARRAY_SIZE(netdev_op_strmap)) + return NULL; + return netdev_op_strmap[op]; +} + +static const char * const netdev_xdp_act_strmap[] = { + [0] = "basic", + [1] = "redirect", + [2] = "ndo-xmit", + [3] = "xsk-zerocopy", + [4] = "hw-offload", + [5] = "rx-sg", + [6] = "ndo-xmit-sg", +}; + +const char *netdev_xdp_act_str(enum netdev_xdp_act value) +{ + value = ffs(value) - 1; + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(netdev_xdp_act_strmap)) + return NULL; + return netdev_xdp_act_strmap[value]; +} + +/* Policies */ +extern struct ynl_policy_nest netdev_dev_nest; + +struct ynl_policy_attr netdev_dev_policy[NETDEV_A_DEV_MAX + 1] = { + [NETDEV_A_DEV_IFINDEX] = { .name = "ifindex", .type = YNL_PT_U32, }, + [NETDEV_A_DEV_PAD] = { .name = "pad", .type = YNL_PT_IGNORE, }, + [NETDEV_A_DEV_XDP_FEATURES] = { .name = "xdp-features", .type = YNL_PT_U64, }, +}; + +struct ynl_policy_nest netdev_dev_nest = { + .max_attr = NETDEV_A_DEV_MAX, + .table = netdev_dev_policy, +}; + +/* Common nested types */ +/* ============== NETDEV_CMD_DEV_GET ============== */ +/* NETDEV_CMD_DEV_GET - do */ +void netdev_dev_get_req_free(struct netdev_dev_get_req *req) +{ + free(req); +} + +void netdev_dev_get_rsp_free(struct netdev_dev_get_rsp *rsp) +{ + free(rsp); +} + +int netdev_dev_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + struct netdev_dev_get_rsp *dst; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + if (mnl_attr_get_type(attr) == NETDEV_A_DEV_IFINDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.ifindex = 1; + dst->ifindex = mnl_attr_get_u32(attr); + } + else if (mnl_attr_get_type(attr) == NETDEV_A_DEV_XDP_FEATURES) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.xdp_features = 1; + dst->xdp_features = mnl_attr_get_u64(attr); + } + } + + return MNL_CB_OK; +} + +struct netdev_dev_get_rsp * +netdev_dev_get(struct ynl_sock *ys, struct netdev_dev_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct netdev_dev_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, NETDEV_CMD_DEV_GET, 1); + ys->req_policy = &netdev_dev_nest; + yrs.yarg.rsp_policy = &netdev_dev_nest; + + if (req->_present.ifindex) + mnl_attr_put_u32(nlh, NETDEV_A_DEV_IFINDEX, req->ifindex); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = netdev_dev_get_rsp_parse; + yrs.rsp_cmd = NETDEV_CMD_DEV_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + netdev_dev_get_rsp_free(rsp); + return NULL; +} + +/* NETDEV_CMD_DEV_GET - dump */ +void netdev_dev_get_list_free(struct netdev_dev_get_list *rsp) +{ + struct netdev_dev_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp); + } +} + +struct netdev_dev_get_list *netdev_dev_get_dump(struct ynl_sock *ys) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct netdev_dev_get_list); + yds.cb = netdev_dev_get_rsp_parse; + yds.rsp_cmd = NETDEV_CMD_DEV_GET; + yds.rsp_policy = &netdev_dev_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, NETDEV_CMD_DEV_GET, 1); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + netdev_dev_get_list_free(yds.first); + return NULL; +} + +/* NETDEV_CMD_DEV_GET - notify */ +void netdev_dev_get_ntf_free(struct netdev_dev_get_ntf *rsp) +{ + free(rsp); +} + +/* --------------- Common notification parsing --------------- */ +struct ynl_ntf_base_type *netdev_ntf_parse(struct ynl_sock *ys) +{ + struct ynl_parse_arg yarg = { .ys = ys, }; + struct ynl_ntf_base_type *rsp; + struct genlmsghdr *genlh; + struct nlmsghdr *nlh; + mnl_cb_t parse; + int len, err; + + len = mnl_socket_recvfrom(ys->sock, ys->rx_buf, MNL_SOCKET_BUFFER_SIZE); + if (len < (ssize_t)(sizeof(*nlh) + sizeof(*genlh))) + return NULL; + + nlh = (struct nlmsghdr *)ys->rx_buf; + genlh = mnl_nlmsg_get_payload(nlh); + + switch (genlh->cmd) { + case NETDEV_CMD_DEV_ADD_NTF: + case NETDEV_CMD_DEV_DEL_NTF: + case NETDEV_CMD_DEV_CHANGE_NTF: + rsp = calloc(1, sizeof(struct netdev_dev_get_ntf)); + parse = netdev_dev_get_rsp_parse; + yarg.rsp_policy = &netdev_dev_nest; + rsp->free = (void *)netdev_dev_get_ntf_free; + break; + default: + ynl_error_unknown_notification(ys, genlh->cmd); + return NULL; + } + + yarg.data = rsp->data; + + err = mnl_cb_run2(ys->rx_buf, len, 0, 0, parse, &yarg, + ynl_cb_array, NLMSG_MIN_TYPE); + if (err < 0) + goto err_free; + + rsp->family = nlh->nlmsg_type; + rsp->cmd = genlh->cmd; + return rsp; + +err_free: + free(rsp); + return NULL; +} + +static const struct ynl_ntf_info netdev_ntf_info[] = { + [NETDEV_CMD_DEV_ADD_NTF] = { + .alloc_sz = sizeof(struct netdev_dev_get_ntf), + .cb = netdev_dev_get_rsp_parse, + .policy = &netdev_dev_nest, + .free = (void *)netdev_dev_get_ntf_free, + }, + [NETDEV_CMD_DEV_DEL_NTF] = { + .alloc_sz = sizeof(struct netdev_dev_get_ntf), + .cb = netdev_dev_get_rsp_parse, + .policy = &netdev_dev_nest, + .free = (void *)netdev_dev_get_ntf_free, + }, + [NETDEV_CMD_DEV_CHANGE_NTF] = { + .alloc_sz = sizeof(struct netdev_dev_get_ntf), + .cb = netdev_dev_get_rsp_parse, + .policy = &netdev_dev_nest, + .free = (void *)netdev_dev_get_ntf_free, + }, +}; + +const struct ynl_family ynl_netdev_family = { + .name = "netdev", + .ntf_info = netdev_ntf_info, + .ntf_info_size = MNL_ARRAY_SIZE(netdev_ntf_info), +}; diff --git a/tools/net/ynl/generated/netdev-user.h b/tools/net/ynl/generated/netdev-user.h new file mode 100644 index 000000000000..d146bc4b2112 --- /dev/null +++ b/tools/net/ynl/generated/netdev-user.h @@ -0,0 +1,88 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/netdev.yaml */ +/* YNL-GEN user header */ + +#ifndef _LINUX_NETDEV_GEN_H +#define _LINUX_NETDEV_GEN_H + +#include <stdlib.h> +#include <string.h> +#include <linux/types.h> +#include <linux/netdev.h> + +struct ynl_sock; + +extern const struct ynl_family ynl_netdev_family; + +/* Enums */ +const char *netdev_op_str(int op); +const char *netdev_xdp_act_str(enum netdev_xdp_act value); + +/* Common nested types */ +/* ============== NETDEV_CMD_DEV_GET ============== */ +/* NETDEV_CMD_DEV_GET - do */ +struct netdev_dev_get_req { + struct { + __u32 ifindex:1; + } _present; + + __u32 ifindex; +}; + +static inline struct netdev_dev_get_req *netdev_dev_get_req_alloc(void) +{ + return calloc(1, sizeof(struct netdev_dev_get_req)); +} +void netdev_dev_get_req_free(struct netdev_dev_get_req *req); + +static inline void +netdev_dev_get_req_set_ifindex(struct netdev_dev_get_req *req, __u32 ifindex) +{ + req->_present.ifindex = 1; + req->ifindex = ifindex; +} + +struct netdev_dev_get_rsp { + struct { + __u32 ifindex:1; + __u32 xdp_features:1; + } _present; + + __u32 ifindex; + __u64 xdp_features; +}; + +void netdev_dev_get_rsp_free(struct netdev_dev_get_rsp *rsp); + +/* + * Get / dump information about a netdev. + */ +struct netdev_dev_get_rsp * +netdev_dev_get(struct ynl_sock *ys, struct netdev_dev_get_req *req); + +/* NETDEV_CMD_DEV_GET - dump */ +struct netdev_dev_get_list { + struct netdev_dev_get_list *next; + struct netdev_dev_get_rsp obj __attribute__ ((aligned (8))); +}; + +void netdev_dev_get_list_free(struct netdev_dev_get_list *rsp); + +struct netdev_dev_get_list *netdev_dev_get_dump(struct ynl_sock *ys); + +/* NETDEV_CMD_DEV_GET - notify */ +struct netdev_dev_get_ntf { + __u16 family; + __u8 cmd; + struct ynl_ntf_base_type *next; + void (*free)(struct netdev_dev_get_ntf *ntf); + struct netdev_dev_get_rsp obj __attribute__ ((aligned (8))); +}; + +void netdev_dev_get_ntf_free(struct netdev_dev_get_ntf *rsp); + +/* --------------- Common notification parsing --------------- */ +struct ynl_ntf_base_type *netdev_ntf_parse(struct ynl_sock *ys); + +#endif /* _LINUX_NETDEV_GEN_H */ diff --git a/tools/net/ynl/lib/Makefile b/tools/net/ynl/lib/Makefile new file mode 100644 index 000000000000..d2e50fd0a52d --- /dev/null +++ b/tools/net/ynl/lib/Makefile @@ -0,0 +1,28 @@ +# SPDX-License-Identifier: GPL-2.0 + +CC=gcc +CFLAGS=-std=gnu11 -O2 -W -Wall -Wextra -Wno-unused-parameter -Wshadow +ifeq ("$(DEBUG)","1") + CFLAGS += -g -fsanitize=address -fsanitize=leak -static-libasan +endif + +SRCS=$(wildcard *.c) +OBJS=$(patsubst %.c,%.o,${SRCS}) + +include $(wildcard *.d) + +all: ynl.a + +ynl.a: $(OBJS) + ar rcs $@ $(OBJS) +clean: + rm -f *.o *.d *~ + +hardclean: clean + rm -f *.a + +%.o: %.c + $(COMPILE.c) -MMD -c -o $@ $< + +.PHONY: all clean +.DEFAULT_GOAL=all diff --git a/tools/net/ynl/lib/nlspec.py b/tools/net/ynl/lib/nlspec.py index a0241add3839..ada22b073aa2 100644 --- a/tools/net/ynl/lib/nlspec.py +++ b/tools/net/ynl/lib/nlspec.py @@ -226,11 +226,15 @@ class SpecStructMember(SpecElement): Represents a single struct member attribute. Attributes: - type string, type of the member attribute + type string, type of the member attribute + byte_order string or None for native byte order + enum string, name of the enum definition """ def __init__(self, family, yaml): super().__init__(family, yaml) self.type = yaml['type'] + self.byte_order = yaml.get('byte-order') + self.enum = yaml.get('enum') class SpecStruct(SpecElement): diff --git a/tools/net/ynl/lib/ynl.c b/tools/net/ynl/lib/ynl.c new file mode 100644 index 000000000000..514e0d69e731 --- /dev/null +++ b/tools/net/ynl/lib/ynl.c @@ -0,0 +1,901 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +#include <errno.h> +#include <poll.h> +#include <string.h> +#include <stdlib.h> +#include <linux/types.h> + +#include <libmnl/libmnl.h> +#include <linux/genetlink.h> + +#include "ynl.h" + +#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof(*arr)) + +#define __yerr_msg(yse, _msg...) \ + ({ \ + struct ynl_error *_yse = (yse); \ + \ + if (_yse) { \ + snprintf(_yse->msg, sizeof(_yse->msg) - 1, _msg); \ + _yse->msg[sizeof(_yse->msg) - 1] = 0; \ + } \ + }) + +#define __yerr_code(yse, _code...) \ + ({ \ + struct ynl_error *_yse = (yse); \ + \ + if (_yse) { \ + _yse->code = _code; \ + } \ + }) + +#define __yerr(yse, _code, _msg...) \ + ({ \ + __yerr_msg(yse, _msg); \ + __yerr_code(yse, _code); \ + }) + +#define __perr(yse, _msg) __yerr(yse, errno, _msg) + +#define yerr_msg(_ys, _msg...) __yerr_msg(&(_ys)->err, _msg) +#define yerr(_ys, _code, _msg...) __yerr(&(_ys)->err, _code, _msg) +#define perr(_ys, _msg) __yerr(&(_ys)->err, errno, _msg) + +/* -- Netlink boiler plate */ +static int +ynl_err_walk_report_one(struct ynl_policy_nest *policy, unsigned int type, + char *str, int str_sz, int *n) +{ + if (!policy) { + if (*n < str_sz) + *n += snprintf(str, str_sz, "!policy"); + return 1; + } + + if (type > policy->max_attr) { + if (*n < str_sz) + *n += snprintf(str, str_sz, "!oob"); + return 1; + } + + if (!policy->table[type].name) { + if (*n < str_sz) + *n += snprintf(str, str_sz, "!name"); + return 1; + } + + if (*n < str_sz) + *n += snprintf(str, str_sz - *n, + ".%s", policy->table[type].name); + return 0; +} + +static int +ynl_err_walk(struct ynl_sock *ys, void *start, void *end, unsigned int off, + struct ynl_policy_nest *policy, char *str, int str_sz, + struct ynl_policy_nest **nest_pol) +{ + unsigned int astart_off, aend_off; + const struct nlattr *attr; + unsigned int data_len; + unsigned int type; + bool found = false; + int n = 0; + + if (!policy) { + if (n < str_sz) + n += snprintf(str, str_sz, "!policy"); + return n; + } + + data_len = end - start; + + mnl_attr_for_each_payload(start, data_len) { + astart_off = (char *)attr - (char *)start; + aend_off = astart_off + mnl_attr_get_payload_len(attr); + if (aend_off <= off) + continue; + + found = true; + break; + } + if (!found) + return 0; + + off -= astart_off; + + type = mnl_attr_get_type(attr); + + if (ynl_err_walk_report_one(policy, type, str, str_sz, &n)) + return n; + + if (!off) { + if (nest_pol) + *nest_pol = policy->table[type].nest; + return n; + } + + if (!policy->table[type].nest) { + if (n < str_sz) + n += snprintf(str, str_sz, "!nest"); + return n; + } + + off -= sizeof(struct nlattr); + start = mnl_attr_get_payload(attr); + end = start + mnl_attr_get_payload_len(attr); + + return n + ynl_err_walk(ys, start, end, off, policy->table[type].nest, + &str[n], str_sz - n, nest_pol); +} + +#define NLMSGERR_ATTR_MISS_TYPE (NLMSGERR_ATTR_POLICY + 1) +#define NLMSGERR_ATTR_MISS_NEST (NLMSGERR_ATTR_POLICY + 2) +#define NLMSGERR_ATTR_MAX (NLMSGERR_ATTR_MAX + 2) + +static int +ynl_ext_ack_check(struct ynl_sock *ys, const struct nlmsghdr *nlh, + unsigned int hlen) +{ + const struct nlattr *tb[NLMSGERR_ATTR_MAX + 1] = {}; + char miss_attr[sizeof(ys->err.msg)]; + char bad_attr[sizeof(ys->err.msg)]; + const struct nlattr *attr; + const char *str = NULL; + + if (!(nlh->nlmsg_flags & NLM_F_ACK_TLVS)) + return MNL_CB_OK; + + mnl_attr_for_each(attr, nlh, hlen) { + unsigned int len, type; + + len = mnl_attr_get_payload_len(attr); + type = mnl_attr_get_type(attr); + + if (type > NLMSGERR_ATTR_MAX) + continue; + + tb[type] = attr; + + switch (type) { + case NLMSGERR_ATTR_OFFS: + case NLMSGERR_ATTR_MISS_TYPE: + case NLMSGERR_ATTR_MISS_NEST: + if (len != sizeof(__u32)) + return MNL_CB_ERROR; + break; + case NLMSGERR_ATTR_MSG: + str = mnl_attr_get_payload(attr); + if (str[len - 1]) + return MNL_CB_ERROR; + break; + default: + break; + } + } + + bad_attr[0] = '\0'; + miss_attr[0] = '\0'; + + if (tb[NLMSGERR_ATTR_OFFS]) { + unsigned int n, off; + void *start, *end; + + ys->err.attr_offs = mnl_attr_get_u32(tb[NLMSGERR_ATTR_OFFS]); + + n = snprintf(bad_attr, sizeof(bad_attr), "%sbad attribute: ", + str ? " (" : ""); + + start = mnl_nlmsg_get_payload_offset(ys->nlh, + sizeof(struct genlmsghdr)); + end = mnl_nlmsg_get_payload_tail(ys->nlh); + + off = ys->err.attr_offs; + off -= sizeof(struct nlmsghdr); + off -= sizeof(struct genlmsghdr); + + n += ynl_err_walk(ys, start, end, off, ys->req_policy, + &bad_attr[n], sizeof(bad_attr) - n, NULL); + + if (n >= sizeof(bad_attr)) + n = sizeof(bad_attr) - 1; + bad_attr[n] = '\0'; + } + if (tb[NLMSGERR_ATTR_MISS_TYPE]) { + struct ynl_policy_nest *nest_pol = NULL; + unsigned int n, off, type; + void *start, *end; + int n2; + + type = mnl_attr_get_u32(tb[NLMSGERR_ATTR_MISS_TYPE]); + + n = snprintf(miss_attr, sizeof(miss_attr), "%smissing attribute: ", + bad_attr[0] ? ", " : (str ? " (" : "")); + + start = mnl_nlmsg_get_payload_offset(ys->nlh, + sizeof(struct genlmsghdr)); + end = mnl_nlmsg_get_payload_tail(ys->nlh); + + nest_pol = ys->req_policy; + if (tb[NLMSGERR_ATTR_MISS_NEST]) { + off = mnl_attr_get_u32(tb[NLMSGERR_ATTR_MISS_NEST]); + off -= sizeof(struct nlmsghdr); + off -= sizeof(struct genlmsghdr); + + n += ynl_err_walk(ys, start, end, off, ys->req_policy, + &miss_attr[n], sizeof(miss_attr) - n, + &nest_pol); + } + + n2 = 0; + ynl_err_walk_report_one(nest_pol, type, &miss_attr[n], + sizeof(miss_attr) - n, &n2); + n += n2; + + if (n >= sizeof(miss_attr)) + n = sizeof(miss_attr) - 1; + miss_attr[n] = '\0'; + } + + /* Implicitly depend on ys->err.code already set */ + if (str) + yerr_msg(ys, "Kernel %s: '%s'%s%s%s", + ys->err.code ? "error" : "warning", + str, bad_attr, miss_attr, + bad_attr[0] || miss_attr[0] ? ")" : ""); + else if (bad_attr[0] || miss_attr[0]) + yerr_msg(ys, "Kernel %s: %s%s", + ys->err.code ? "error" : "warning", + bad_attr, miss_attr); + + return MNL_CB_OK; +} + +static int ynl_cb_error(const struct nlmsghdr *nlh, void *data) +{ + const struct nlmsgerr *err = mnl_nlmsg_get_payload(nlh); + struct ynl_parse_arg *yarg = data; + unsigned int hlen; + int code; + + code = err->error >= 0 ? err->error : -err->error; + yarg->ys->err.code = code; + errno = code; + + hlen = sizeof(*err); + if (!(nlh->nlmsg_flags & NLM_F_CAPPED)) + hlen += mnl_nlmsg_get_payload_len(&err->msg); + + ynl_ext_ack_check(yarg->ys, nlh, hlen); + + return code ? MNL_CB_ERROR : MNL_CB_STOP; +} + +static int ynl_cb_done(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + int err; + + err = *(int *)NLMSG_DATA(nlh); + if (err < 0) { + yarg->ys->err.code = -err; + errno = -err; + + ynl_ext_ack_check(yarg->ys, nlh, sizeof(int)); + + return MNL_CB_ERROR; + } + return MNL_CB_STOP; +} + +static int ynl_cb_noop(const struct nlmsghdr *nlh, void *data) +{ + return MNL_CB_OK; +} + +mnl_cb_t ynl_cb_array[NLMSG_MIN_TYPE] = { + [NLMSG_NOOP] = ynl_cb_noop, + [NLMSG_ERROR] = ynl_cb_error, + [NLMSG_DONE] = ynl_cb_done, + [NLMSG_OVERRUN] = ynl_cb_noop, +}; + +/* Attribute validation */ + +int ynl_attr_validate(struct ynl_parse_arg *yarg, const struct nlattr *attr) +{ + struct ynl_policy_attr *policy; + unsigned int type, len; + unsigned char *data; + + data = mnl_attr_get_payload(attr); + len = mnl_attr_get_payload_len(attr); + type = mnl_attr_get_type(attr); + if (type > yarg->rsp_policy->max_attr) { + yerr(yarg->ys, YNL_ERROR_INTERNAL, + "Internal error, validating unknown attribute"); + return -1; + } + + policy = &yarg->rsp_policy->table[type]; + + switch (policy->type) { + case YNL_PT_REJECT: + yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, + "Rejected attribute (%s)", policy->name); + return -1; + case YNL_PT_IGNORE: + break; + case YNL_PT_U8: + if (len == sizeof(__u8)) + break; + yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, + "Invalid attribute (u8 %s)", policy->name); + return -1; + case YNL_PT_U16: + if (len == sizeof(__u16)) + break; + yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, + "Invalid attribute (u16 %s)", policy->name); + return -1; + case YNL_PT_U32: + if (len == sizeof(__u32)) + break; + yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, + "Invalid attribute (u32 %s)", policy->name); + return -1; + case YNL_PT_U64: + if (len == sizeof(__u64)) + break; + yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, + "Invalid attribute (u64 %s)", policy->name); + return -1; + case YNL_PT_FLAG: + /* Let flags grow into real attrs, why not.. */ + break; + case YNL_PT_NEST: + if (!len || len >= sizeof(*attr)) + break; + yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, + "Invalid attribute (nest %s)", policy->name); + return -1; + case YNL_PT_BINARY: + if (!policy->len || len == policy->len) + break; + yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, + "Invalid attribute (binary %s)", policy->name); + return -1; + case YNL_PT_NUL_STR: + if ((!policy->len || len <= policy->len) && !data[len - 1]) + break; + yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, + "Invalid attribute (string %s)", policy->name); + return -1; + default: + yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, + "Invalid attribute (unknown %s)", policy->name); + return -1; + } + + return 0; +} + +/* Generic code */ + +static void ynl_err_reset(struct ynl_sock *ys) +{ + ys->err.code = 0; + ys->err.attr_offs = 0; + ys->err.msg[0] = 0; +} + +struct nlmsghdr *ynl_msg_start(struct ynl_sock *ys, __u32 id, __u16 flags) +{ + struct nlmsghdr *nlh; + + ynl_err_reset(ys); + + nlh = ys->nlh = mnl_nlmsg_put_header(ys->tx_buf); + nlh->nlmsg_type = id; + nlh->nlmsg_flags = flags; + nlh->nlmsg_seq = ++ys->seq; + + return nlh; +} + +struct nlmsghdr * +ynl_gemsg_start(struct ynl_sock *ys, __u32 id, __u16 flags, + __u8 cmd, __u8 version) +{ + struct genlmsghdr gehdr; + struct nlmsghdr *nlh; + void *data; + + nlh = ynl_msg_start(ys, id, flags); + + memset(&gehdr, 0, sizeof(gehdr)); + gehdr.cmd = cmd; + gehdr.version = version; + + data = mnl_nlmsg_put_extra_header(nlh, sizeof(gehdr)); + memcpy(data, &gehdr, sizeof(gehdr)); + + return nlh; +} + +void ynl_msg_start_req(struct ynl_sock *ys, __u32 id) +{ + ynl_msg_start(ys, id, NLM_F_REQUEST | NLM_F_ACK); +} + +void ynl_msg_start_dump(struct ynl_sock *ys, __u32 id) +{ + ynl_msg_start(ys, id, NLM_F_REQUEST | NLM_F_ACK | NLM_F_DUMP); +} + +struct nlmsghdr * +ynl_gemsg_start_req(struct ynl_sock *ys, __u32 id, __u8 cmd, __u8 version) +{ + return ynl_gemsg_start(ys, id, NLM_F_REQUEST | NLM_F_ACK, cmd, version); +} + +struct nlmsghdr * +ynl_gemsg_start_dump(struct ynl_sock *ys, __u32 id, __u8 cmd, __u8 version) +{ + return ynl_gemsg_start(ys, id, NLM_F_REQUEST | NLM_F_ACK | NLM_F_DUMP, + cmd, version); +} + +int ynl_recv_ack(struct ynl_sock *ys, int ret) +{ + if (!ret) { + yerr(ys, YNL_ERROR_EXPECT_ACK, + "Expecting an ACK but nothing received"); + return -1; + } + + ret = mnl_socket_recvfrom(ys->sock, ys->rx_buf, MNL_SOCKET_BUFFER_SIZE); + if (ret < 0) { + perr(ys, "Socket receive failed"); + return ret; + } + return mnl_cb_run(ys->rx_buf, ret, ys->seq, ys->portid, + ynl_cb_null, ys); +} + +int ynl_cb_null(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + + yerr(yarg->ys, YNL_ERROR_UNEXPECT_MSG, + "Received a message when none were expected"); + + return MNL_CB_ERROR; +} + +/* Init/fini and genetlink boiler plate */ +static int +ynl_get_family_info_mcast(struct ynl_sock *ys, const struct nlattr *mcasts) +{ + const struct nlattr *entry, *attr; + unsigned int i; + + mnl_attr_for_each_nested(attr, mcasts) + ys->n_mcast_groups++; + + if (!ys->n_mcast_groups) + return 0; + + ys->mcast_groups = calloc(ys->n_mcast_groups, + sizeof(*ys->mcast_groups)); + if (!ys->mcast_groups) + return MNL_CB_ERROR; + + i = 0; + mnl_attr_for_each_nested(entry, mcasts) { + mnl_attr_for_each_nested(attr, entry) { + if (mnl_attr_get_type(attr) == CTRL_ATTR_MCAST_GRP_ID) + ys->mcast_groups[i].id = mnl_attr_get_u32(attr); + if (mnl_attr_get_type(attr) == CTRL_ATTR_MCAST_GRP_NAME) { + strncpy(ys->mcast_groups[i].name, + mnl_attr_get_str(attr), + GENL_NAMSIZ - 1); + ys->mcast_groups[i].name[GENL_NAMSIZ - 1] = 0; + } + } + } + + return 0; +} + +static int ynl_get_family_info_cb(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + struct ynl_sock *ys = yarg->ys; + const struct nlattr *attr; + bool found_id = true; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + if (mnl_attr_get_type(attr) == CTRL_ATTR_MCAST_GROUPS) + if (ynl_get_family_info_mcast(ys, attr)) + return MNL_CB_ERROR; + + if (mnl_attr_get_type(attr) != CTRL_ATTR_FAMILY_ID) + continue; + + if (mnl_attr_get_payload_len(attr) != sizeof(__u16)) { + yerr(ys, YNL_ERROR_ATTR_INVALID, "Invalid family ID"); + return MNL_CB_ERROR; + } + + ys->family_id = mnl_attr_get_u16(attr); + found_id = true; + } + + if (!found_id) { + yerr(ys, YNL_ERROR_ATTR_MISSING, "Family ID missing"); + return MNL_CB_ERROR; + } + return MNL_CB_OK; +} + +static int ynl_sock_read_family(struct ynl_sock *ys, const char *family_name) +{ + struct ynl_parse_arg yarg = { .ys = ys, }; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, GENL_ID_CTRL, CTRL_CMD_GETFAMILY, 1); + mnl_attr_put_strz(nlh, CTRL_ATTR_FAMILY_NAME, family_name); + + err = mnl_socket_sendto(ys->sock, nlh, nlh->nlmsg_len); + if (err < 0) { + perr(ys, "failed to request socket family info"); + return err; + } + + err = mnl_socket_recvfrom(ys->sock, ys->rx_buf, MNL_SOCKET_BUFFER_SIZE); + if (err <= 0) { + perr(ys, "failed to receive the socket family info"); + return err; + } + err = mnl_cb_run2(ys->rx_buf, err, ys->seq, ys->portid, + ynl_get_family_info_cb, &yarg, + ynl_cb_array, ARRAY_SIZE(ynl_cb_array)); + if (err < 0) { + free(ys->mcast_groups); + perr(ys, "failed to receive the socket family info - no such family?"); + return err; + } + + return ynl_recv_ack(ys, err); +} + +struct ynl_sock * +ynl_sock_create(const struct ynl_family *yf, struct ynl_error *yse) +{ + struct ynl_sock *ys; + int one = 1; + + ys = malloc(sizeof(*ys) + 2 * MNL_SOCKET_BUFFER_SIZE); + if (!ys) + return NULL; + memset(ys, 0, sizeof(*ys)); + + ys->family = yf; + ys->tx_buf = &ys->raw_buf[0]; + ys->rx_buf = &ys->raw_buf[MNL_SOCKET_BUFFER_SIZE]; + ys->ntf_last_next = &ys->ntf_first; + + ys->sock = mnl_socket_open(NETLINK_GENERIC); + if (!ys->sock) { + __perr(yse, "failed to create a netlink socket"); + goto err_free_sock; + } + + if (mnl_socket_setsockopt(ys->sock, NETLINK_CAP_ACK, + &one, sizeof(one))) { + __perr(yse, "failed to enable netlink ACK"); + goto err_close_sock; + } + if (mnl_socket_setsockopt(ys->sock, NETLINK_EXT_ACK, + &one, sizeof(one))) { + __perr(yse, "failed to enable netlink ext ACK"); + goto err_close_sock; + } + + ys->seq = random(); + ys->portid = mnl_socket_get_portid(ys->sock); + + if (ynl_sock_read_family(ys, yf->name)) { + if (yse) + memcpy(yse, &ys->err, sizeof(*yse)); + goto err_close_sock; + } + + return ys; + +err_close_sock: + mnl_socket_close(ys->sock); +err_free_sock: + free(ys); + return NULL; +} + +void ynl_sock_destroy(struct ynl_sock *ys) +{ + struct ynl_ntf_base_type *ntf; + + mnl_socket_close(ys->sock); + while ((ntf = ynl_ntf_dequeue(ys))) + ynl_ntf_free(ntf); + free(ys->mcast_groups); + free(ys); +} + +/* YNL multicast handling */ + +void ynl_ntf_free(struct ynl_ntf_base_type *ntf) +{ + ntf->free(ntf); +} + +int ynl_subscribe(struct ynl_sock *ys, const char *grp_name) +{ + unsigned int i; + int err; + + for (i = 0; i < ys->n_mcast_groups; i++) + if (!strcmp(ys->mcast_groups[i].name, grp_name)) + break; + if (i == ys->n_mcast_groups) { + yerr(ys, ENOENT, "Multicast group '%s' not found", grp_name); + return -1; + } + + err = mnl_socket_setsockopt(ys->sock, NETLINK_ADD_MEMBERSHIP, + &ys->mcast_groups[i].id, + sizeof(ys->mcast_groups[i].id)); + if (err < 0) { + perr(ys, "Subscribing to multicast group failed"); + return -1; + } + + return 0; +} + +int ynl_socket_get_fd(struct ynl_sock *ys) +{ + return mnl_socket_get_fd(ys->sock); +} + +struct ynl_ntf_base_type *ynl_ntf_dequeue(struct ynl_sock *ys) +{ + struct ynl_ntf_base_type *ntf; + + if (!ynl_has_ntf(ys)) + return NULL; + + ntf = ys->ntf_first; + ys->ntf_first = ntf->next; + if (ys->ntf_last_next == &ntf->next) + ys->ntf_last_next = &ys->ntf_first; + + return ntf; +} + +static int ynl_ntf_parse(struct ynl_sock *ys, const struct nlmsghdr *nlh) +{ + struct ynl_parse_arg yarg = { .ys = ys, }; + const struct ynl_ntf_info *info; + struct ynl_ntf_base_type *rsp; + struct genlmsghdr *gehdr; + int ret; + + gehdr = mnl_nlmsg_get_payload(nlh); + if (gehdr->cmd >= ys->family->ntf_info_size) + return MNL_CB_ERROR; + info = &ys->family->ntf_info[gehdr->cmd]; + if (!info->cb) + return MNL_CB_ERROR; + + rsp = calloc(1, info->alloc_sz); + rsp->free = info->free; + yarg.data = rsp->data; + yarg.rsp_policy = info->policy; + + ret = info->cb(nlh, &yarg); + if (ret <= MNL_CB_STOP) + goto err_free; + + rsp->family = nlh->nlmsg_type; + rsp->cmd = gehdr->cmd; + + *ys->ntf_last_next = rsp; + ys->ntf_last_next = &rsp->next; + + return MNL_CB_OK; + +err_free: + info->free(rsp); + return MNL_CB_ERROR; +} + +static int ynl_ntf_trampoline(const struct nlmsghdr *nlh, void *data) +{ + return ynl_ntf_parse((struct ynl_sock *)data, nlh); +} + +int ynl_ntf_check(struct ynl_sock *ys) +{ + ssize_t len; + int err; + + do { + /* libmnl doesn't let us pass flags to the recv to make + * it non-blocking so we need to poll() or peek() :| + */ + struct pollfd pfd = { }; + + pfd.fd = mnl_socket_get_fd(ys->sock); + pfd.events = POLLIN; + err = poll(&pfd, 1, 1); + if (err < 1) + return err; + + len = mnl_socket_recvfrom(ys->sock, ys->rx_buf, + MNL_SOCKET_BUFFER_SIZE); + if (len < 0) + return len; + + err = mnl_cb_run2(ys->rx_buf, len, ys->seq, ys->portid, + ynl_ntf_trampoline, ys, + ynl_cb_array, NLMSG_MIN_TYPE); + if (err < 0) + return err; + } while (err > 0); + + return 0; +} + +/* YNL specific helpers used by the auto-generated code */ + +struct ynl_dump_list_type *YNL_LIST_END = (void *)(0xb4d123); + +void ynl_error_unknown_notification(struct ynl_sock *ys, __u8 cmd) +{ + yerr(ys, YNL_ERROR_UNKNOWN_NTF, + "Unknown notification message type '%d'", cmd); +} + +int ynl_error_parse(struct ynl_parse_arg *yarg, const char *msg) +{ + yerr(yarg->ys, YNL_ERROR_INV_RESP, "Error parsing response: %s", msg); + return MNL_CB_ERROR; +} + +static int +ynl_check_alien(struct ynl_sock *ys, const struct nlmsghdr *nlh, __u32 rsp_cmd) +{ + struct genlmsghdr *gehdr; + + if (mnl_nlmsg_get_payload_len(nlh) < sizeof(*gehdr)) { + yerr(ys, YNL_ERROR_INV_RESP, + "Kernel responded with truncated message"); + return -1; + } + + gehdr = mnl_nlmsg_get_payload(nlh); + if (gehdr->cmd != rsp_cmd) + return ynl_ntf_parse(ys, nlh); + + return 0; +} + +static int ynl_req_trampoline(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_req_state *yrs = data; + int ret; + + ret = ynl_check_alien(yrs->yarg.ys, nlh, yrs->rsp_cmd); + if (ret) + return ret < 0 ? MNL_CB_ERROR : MNL_CB_OK; + + return yrs->cb(nlh, &yrs->yarg); +} + +int ynl_exec(struct ynl_sock *ys, struct nlmsghdr *req_nlh, + struct ynl_req_state *yrs) +{ + ssize_t len; + int err; + + err = mnl_socket_sendto(ys->sock, req_nlh, req_nlh->nlmsg_len); + if (err < 0) + return err; + + do { + len = mnl_socket_recvfrom(ys->sock, ys->rx_buf, + MNL_SOCKET_BUFFER_SIZE); + if (len < 0) + return len; + + err = mnl_cb_run2(ys->rx_buf, len, ys->seq, ys->portid, + ynl_req_trampoline, yrs, + ynl_cb_array, NLMSG_MIN_TYPE); + if (err < 0) + return err; + } while (err > 0); + + return 0; +} + +static int ynl_dump_trampoline(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_dump_state *ds = data; + struct ynl_dump_list_type *obj; + struct ynl_parse_arg yarg = {}; + int ret; + + ret = ynl_check_alien(ds->ys, nlh, ds->rsp_cmd); + if (ret) + return ret < 0 ? MNL_CB_ERROR : MNL_CB_OK; + + obj = calloc(1, ds->alloc_sz); + if (!obj) + return MNL_CB_ERROR; + + if (!ds->first) + ds->first = obj; + if (ds->last) + ds->last->next = obj; + ds->last = obj; + + yarg.ys = ds->ys; + yarg.rsp_policy = ds->rsp_policy; + yarg.data = &obj->data; + + return ds->cb(nlh, &yarg); +} + +static void *ynl_dump_end(struct ynl_dump_state *ds) +{ + if (!ds->first) + return YNL_LIST_END; + + ds->last->next = YNL_LIST_END; + return ds->first; +} + +int ynl_exec_dump(struct ynl_sock *ys, struct nlmsghdr *req_nlh, + struct ynl_dump_state *yds) +{ + ssize_t len; + int err; + + err = mnl_socket_sendto(ys->sock, req_nlh, req_nlh->nlmsg_len); + if (err < 0) + return err; + + do { + len = mnl_socket_recvfrom(ys->sock, ys->rx_buf, + MNL_SOCKET_BUFFER_SIZE); + if (len < 0) + goto err_close_list; + + err = mnl_cb_run2(ys->rx_buf, len, ys->seq, ys->portid, + ynl_dump_trampoline, yds, + ynl_cb_array, NLMSG_MIN_TYPE); + if (err < 0) + goto err_close_list; + } while (err > 0); + + yds->first = ynl_dump_end(yds); + return 0; + +err_close_list: + yds->first = ynl_dump_end(yds); + return -1; +} diff --git a/tools/net/ynl/lib/ynl.h b/tools/net/ynl/lib/ynl.h new file mode 100644 index 000000000000..9eafa3552c16 --- /dev/null +++ b/tools/net/ynl/lib/ynl.h @@ -0,0 +1,237 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +#ifndef __YNL_C_H +#define __YNL_C_H 1 + +#include <stddef.h> +#include <libmnl/libmnl.h> +#include <linux/genetlink.h> +#include <linux/types.h> + +struct mnl_socket; +struct nlmsghdr; + +/* + * User facing code + */ + +struct ynl_ntf_base_type; +struct ynl_ntf_info; +struct ynl_sock; + +enum ynl_error_code { + YNL_ERROR_NONE = 0, + __YNL_ERRNO_END = 4096, + YNL_ERROR_INTERNAL, + YNL_ERROR_EXPECT_ACK, + YNL_ERROR_EXPECT_MSG, + YNL_ERROR_UNEXPECT_MSG, + YNL_ERROR_ATTR_MISSING, + YNL_ERROR_ATTR_INVALID, + YNL_ERROR_UNKNOWN_NTF, + YNL_ERROR_INV_RESP, +}; + +/** + * struct ynl_error - error encountered by YNL + * @code: errno (low values) or YNL error code (enum ynl_error_code) + * @attr_offs: offset of bad attribute (for very advanced users) + * @msg: error message + * + * Error information for when YNL operations fail. + * Users should interact with the err member of struct ynl_sock directly. + * The main exception to that rule is ynl_sock_create(). + */ +struct ynl_error { + enum ynl_error_code code; + unsigned int attr_offs; + char msg[512]; +}; + +/** + * struct ynl_family - YNL family info + * Family description generated by codegen. Pass to ynl_sock_create(). + */ +struct ynl_family { +/* private: */ + const char *name; + const struct ynl_ntf_info *ntf_info; + unsigned int ntf_info_size; +}; + +/** + * struct ynl_sock - YNL wrapped netlink socket + * @err: YNL error descriptor, cleared on every request. + */ +struct ynl_sock { + struct ynl_error err; + +/* private: */ + const struct ynl_family *family; + struct mnl_socket *sock; + __u32 seq; + __u32 portid; + __u16 family_id; + + unsigned int n_mcast_groups; + struct { + unsigned int id; + char name[GENL_NAMSIZ]; + } *mcast_groups; + + struct ynl_ntf_base_type *ntf_first; + struct ynl_ntf_base_type **ntf_last_next; + + struct nlmsghdr *nlh; + struct ynl_policy_nest *req_policy; + unsigned char *tx_buf; + unsigned char *rx_buf; + unsigned char raw_buf[]; +}; + +struct ynl_sock * +ynl_sock_create(const struct ynl_family *yf, struct ynl_error *e); +void ynl_sock_destroy(struct ynl_sock *ys); + +#define ynl_dump_foreach(dump, iter) \ + for (typeof(dump->obj) *iter = &dump->obj; \ + !ynl_dump_obj_is_last(iter); \ + iter = ynl_dump_obj_next(iter)) + +int ynl_subscribe(struct ynl_sock *ys, const char *grp_name); +int ynl_socket_get_fd(struct ynl_sock *ys); +int ynl_ntf_check(struct ynl_sock *ys); + +/** + * ynl_has_ntf() - check if socket has *parsed* notifications + * @ys: active YNL socket + * + * Note that this does not take into account notifications sitting + * in netlink socket, just the notifications which have already been + * read and parsed (e.g. during a ynl_ntf_check() call). + */ +static inline bool ynl_has_ntf(struct ynl_sock *ys) +{ + return ys->ntf_last_next != &ys->ntf_first; +} +struct ynl_ntf_base_type *ynl_ntf_dequeue(struct ynl_sock *ys); + +void ynl_ntf_free(struct ynl_ntf_base_type *ntf); + +/* + * YNL internals / low level stuff + */ + +/* Generic mnl helper code */ + +enum ynl_policy_type { + YNL_PT_REJECT = 1, + YNL_PT_IGNORE, + YNL_PT_NEST, + YNL_PT_FLAG, + YNL_PT_BINARY, + YNL_PT_U8, + YNL_PT_U16, + YNL_PT_U32, + YNL_PT_U64, + YNL_PT_NUL_STR, +}; + +struct ynl_policy_attr { + enum ynl_policy_type type; + unsigned int len; + const char *name; + struct ynl_policy_nest *nest; +}; + +struct ynl_policy_nest { + unsigned int max_attr; + struct ynl_policy_attr *table; +}; + +struct ynl_parse_arg { + struct ynl_sock *ys; + struct ynl_policy_nest *rsp_policy; + void *data; +}; + +struct ynl_dump_list_type { + struct ynl_dump_list_type *next; + unsigned char data[] __attribute__ ((aligned (8))); +}; +extern struct ynl_dump_list_type *YNL_LIST_END; + +static inline bool ynl_dump_obj_is_last(void *obj) +{ + unsigned long uptr = (unsigned long)obj; + + uptr -= offsetof(struct ynl_dump_list_type, data); + return uptr == (unsigned long)YNL_LIST_END; +} + +static inline void *ynl_dump_obj_next(void *obj) +{ + unsigned long uptr = (unsigned long)obj; + struct ynl_dump_list_type *list; + + uptr -= offsetof(struct ynl_dump_list_type, data); + list = (void *)uptr; + uptr = (unsigned long)list->next; + uptr += offsetof(struct ynl_dump_list_type, data); + + return (void *)uptr; +} + +struct ynl_ntf_base_type { + __u16 family; + __u8 cmd; + struct ynl_ntf_base_type *next; + void (*free)(struct ynl_ntf_base_type *ntf); + unsigned char data[] __attribute__ ((aligned (8))); +}; + +extern mnl_cb_t ynl_cb_array[NLMSG_MIN_TYPE]; + +struct nlmsghdr * +ynl_gemsg_start_req(struct ynl_sock *ys, __u32 id, __u8 cmd, __u8 version); +struct nlmsghdr * +ynl_gemsg_start_dump(struct ynl_sock *ys, __u32 id, __u8 cmd, __u8 version); + +int ynl_attr_validate(struct ynl_parse_arg *yarg, const struct nlattr *attr); + +int ynl_recv_ack(struct ynl_sock *ys, int ret); +int ynl_cb_null(const struct nlmsghdr *nlh, void *data); + +/* YNL specific helpers used by the auto-generated code */ + +struct ynl_req_state { + struct ynl_parse_arg yarg; + mnl_cb_t cb; + __u32 rsp_cmd; +}; + +struct ynl_dump_state { + struct ynl_sock *ys; + struct ynl_policy_nest *rsp_policy; + void *first; + struct ynl_dump_list_type *last; + size_t alloc_sz; + mnl_cb_t cb; + __u32 rsp_cmd; +}; + +struct ynl_ntf_info { + struct ynl_policy_nest *policy; + mnl_cb_t cb; + size_t alloc_sz; + void (*free)(struct ynl_ntf_base_type *ntf); +}; + +int ynl_exec(struct ynl_sock *ys, struct nlmsghdr *req_nlh, + struct ynl_req_state *yrs); +int ynl_exec_dump(struct ynl_sock *ys, struct nlmsghdr *req_nlh, + struct ynl_dump_state *yds); + +void ynl_error_unknown_notification(struct ynl_sock *ys, __u8 cmd); +int ynl_error_parse(struct ynl_parse_arg *yarg, const char *msg); + +#endif diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py index 3144f33196be..3b343d6cbbc0 100644 --- a/tools/net/ynl/lib/ynl.py +++ b/tools/net/ynl/lib/ynl.py @@ -1,10 +1,12 @@ # SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +from collections import namedtuple import functools import os import random import socket import struct +from struct import Struct import yaml from .nlspec import SpecFamily @@ -76,10 +78,17 @@ class NlError(Exception): class NlAttr: - type_formats = { 'u8' : ('B', 1), 's8' : ('b', 1), - 'u16': ('H', 2), 's16': ('h', 2), - 'u32': ('I', 4), 's32': ('i', 4), - 'u64': ('Q', 8), 's64': ('q', 8) } + ScalarFormat = namedtuple('ScalarFormat', ['native', 'big', 'little']) + type_formats = { + 'u8' : ScalarFormat(Struct('B'), Struct("B"), Struct("B")), + 's8' : ScalarFormat(Struct('b'), Struct("b"), Struct("b")), + 'u16': ScalarFormat(Struct('H'), Struct(">H"), Struct("<H")), + 's16': ScalarFormat(Struct('h'), Struct(">h"), Struct("<h")), + 'u32': ScalarFormat(Struct('I'), Struct(">I"), Struct("<I")), + 's32': ScalarFormat(Struct('i'), Struct(">i"), Struct("<i")), + 'u64': ScalarFormat(Struct('Q'), Struct(">Q"), Struct("<Q")), + 's64': ScalarFormat(Struct('q'), Struct(">q"), Struct("<q")) + } def __init__(self, raw, offset): self._len, self._type = struct.unpack("HH", raw[offset:offset + 4]) @@ -88,25 +97,17 @@ class NlAttr: self.full_len = (self.payload_len + 3) & ~3 self.raw = raw[offset + 4:offset + self.payload_len] - def format_byte_order(byte_order): + @classmethod + def get_format(cls, attr_type, byte_order=None): + format = cls.type_formats[attr_type] if byte_order: - return ">" if byte_order == "big-endian" else "<" - return "" + return format.big if byte_order == "big-endian" \ + else format.little + return format.native - def as_u8(self): - return struct.unpack("B", self.raw)[0] - - def as_u16(self, byte_order=None): - endian = NlAttr.format_byte_order(byte_order) - return struct.unpack(f"{endian}H", self.raw)[0] - - def as_u32(self, byte_order=None): - endian = NlAttr.format_byte_order(byte_order) - return struct.unpack(f"{endian}I", self.raw)[0] - - def as_u64(self, byte_order=None): - endian = NlAttr.format_byte_order(byte_order) - return struct.unpack(f"{endian}Q", self.raw)[0] + def as_scalar(self, attr_type, byte_order=None): + format = self.get_format(attr_type, byte_order) + return format.unpack(self.raw)[0] def as_strz(self): return self.raw.decode('ascii')[:-1] @@ -115,17 +116,17 @@ class NlAttr: return self.raw def as_c_array(self, type): - format, _ = self.type_formats[type] - return list({ x[0] for x in struct.iter_unpack(format, self.raw) }) + format = self.get_format(type) + return [ x[0] for x in format.iter_unpack(self.raw) ] def as_struct(self, members): value = dict() offset = 0 for m in members: # TODO: handle non-scalar members - format, size = self.type_formats[m.type] - decoded = struct.unpack_from(format, self.raw, offset) - offset += size + format = self.get_format(m.type, m.byte_order) + decoded = format.unpack_from(self.raw, offset) + offset += format.size value[m.name] = decoded[0] return value @@ -184,11 +185,11 @@ class NlMsg: if extack.type == Netlink.NLMSGERR_ATTR_MSG: self.extack['msg'] = extack.as_strz() elif extack.type == Netlink.NLMSGERR_ATTR_MISS_TYPE: - self.extack['miss-type'] = extack.as_u32() + self.extack['miss-type'] = extack.as_scalar('u32') elif extack.type == Netlink.NLMSGERR_ATTR_MISS_NEST: - self.extack['miss-nest'] = extack.as_u32() + self.extack['miss-nest'] = extack.as_scalar('u32') elif extack.type == Netlink.NLMSGERR_ATTR_OFFS: - self.extack['bad-attr-offs'] = extack.as_u32() + self.extack['bad-attr-offs'] = extack.as_scalar('u32') else: if 'unknown' not in self.extack: self.extack['unknown'] = [] @@ -272,11 +273,11 @@ def _genl_load_families(): fam = dict() for attr in gm.raw_attrs: if attr.type == Netlink.CTRL_ATTR_FAMILY_ID: - fam['id'] = attr.as_u16() + fam['id'] = attr.as_scalar('u16') elif attr.type == Netlink.CTRL_ATTR_FAMILY_NAME: fam['name'] = attr.as_strz() elif attr.type == Netlink.CTRL_ATTR_MAXATTR: - fam['maxattr'] = attr.as_u32() + fam['maxattr'] = attr.as_scalar('u32') elif attr.type == Netlink.CTRL_ATTR_MCAST_GROUPS: fam['mcast'] = dict() for entry in NlAttrs(attr.raw): @@ -286,7 +287,7 @@ def _genl_load_families(): if entry_attr.type == Netlink.CTRL_ATTR_MCAST_GRP_NAME: mcast_name = entry_attr.as_strz() elif entry_attr.type == Netlink.CTRL_ATTR_MCAST_GRP_ID: - mcast_id = entry_attr.as_u32() + mcast_id = entry_attr.as_scalar('u32') if mcast_name and mcast_id is not None: fam['mcast'][mcast_name] = mcast_id if 'name' in fam and 'id' in fam: @@ -304,9 +305,9 @@ class GenlMsg: self.fixed_header_attrs = dict() for m in fixed_header_members: - format, size = NlAttr.type_formats[m.type] - decoded = struct.unpack_from(format, nl_msg.raw, offset) - offset += size + format = NlAttr.get_format(m.type, m.byte_order) + decoded = format.unpack_from(nl_msg.raw, offset) + offset += format.size self.fixed_header_attrs[m.name] = decoded[0] self.raw = nl_msg.raw[offset:] @@ -381,21 +382,13 @@ class YnlFamily(SpecFamily): attr_payload += self._add_attr(attr['nested-attributes'], subname, subvalue) elif attr["type"] == 'flag': attr_payload = b'' - elif attr["type"] == 'u8': - attr_payload = struct.pack("B", int(value)) - elif attr["type"] == 'u16': - endian = NlAttr.format_byte_order(attr.byte_order) - attr_payload = struct.pack(f"{endian}H", int(value)) - elif attr["type"] == 'u32': - endian = NlAttr.format_byte_order(attr.byte_order) - attr_payload = struct.pack(f"{endian}I", int(value)) - elif attr["type"] == 'u64': - endian = NlAttr.format_byte_order(attr.byte_order) - attr_payload = struct.pack(f"{endian}Q", int(value)) elif attr["type"] == 'string': attr_payload = str(value).encode('ascii') + b'\x00' elif attr["type"] == 'binary': attr_payload = value + elif attr['type'] in NlAttr.type_formats: + format = NlAttr.get_format(attr['type'], attr.byte_order) + attr_payload = format.pack(int(value)) else: raise Exception(f'Unknown type at {space} {name} {value} {attr["type"]}') @@ -419,7 +412,11 @@ class YnlFamily(SpecFamily): def _decode_binary(self, attr, attr_spec): if attr_spec.struct_name: - decoded = attr.as_struct(self.consts[attr_spec.struct_name]) + members = self.consts[attr_spec.struct_name] + decoded = attr.as_struct(members) + for m in members: + if m.enum: + self._decode_enum(decoded, m) elif attr_spec.sub_type: decoded = attr.as_c_array(attr_spec.sub_type) else: @@ -434,22 +431,16 @@ class YnlFamily(SpecFamily): if attr_spec["type"] == 'nest': subdict = self._decode(NlAttrs(attr.raw), attr_spec['nested-attributes']) decoded = subdict - elif attr_spec['type'] == 'u8': - decoded = attr.as_u8() - elif attr_spec['type'] == 'u16': - decoded = attr.as_u16(attr_spec.byte_order) - elif attr_spec['type'] == 'u32': - decoded = attr.as_u32(attr_spec.byte_order) - elif attr_spec['type'] == 'u64': - decoded = attr.as_u64(attr_spec.byte_order) elif attr_spec["type"] == 'string': decoded = attr.as_strz() elif attr_spec["type"] == 'binary': decoded = self._decode_binary(attr, attr_spec) elif attr_spec["type"] == 'flag': decoded = True + elif attr_spec["type"] in NlAttr.type_formats: + decoded = attr.as_scalar(attr_spec['type'], attr_spec.byte_order) else: - raise Exception(f'Unknown {attr.type} {attr_spec["name"]} {attr_spec["type"]}') + raise Exception(f'Unknown {attr_spec["type"]} with name {attr_spec["name"]}') if not attr_spec.is_multi: rsp[attr_spec['name']] = decoded @@ -554,9 +545,9 @@ class YnlFamily(SpecFamily): if op.fixed_header: fixed_header_members = self.consts[op.fixed_header].members for m in fixed_header_members: - value = vals.pop(m.name) - format, _ = NlAttr.type_formats[m.type] - msg += struct.pack(format, value) + value = vals.pop(m.name) if m.name in vals else 0 + format = NlAttr.get_format(m.type, m.byte_order) + msg += format.pack(value) for name, value in vals.items(): msg += self._add_attr(op.attr_set.name, name, value) msg = _genl_msg_finalize(msg) diff --git a/tools/net/ynl/samples/.gitignore b/tools/net/ynl/samples/.gitignore new file mode 100644 index 000000000000..7b1f5179cb54 --- /dev/null +++ b/tools/net/ynl/samples/.gitignore @@ -0,0 +1 @@ +netdev diff --git a/tools/net/ynl/samples/Makefile b/tools/net/ynl/samples/Makefile new file mode 100644 index 000000000000..714316cad45f --- /dev/null +++ b/tools/net/ynl/samples/Makefile @@ -0,0 +1,28 @@ +# SPDX-License-Identifier: GPL-2.0 + +CC=gcc +CFLAGS=-std=gnu11 -O2 -W -Wall -Wextra -Wno-unused-parameter -Wshadow \ + -I../lib/ -I../generated/ +ifeq ("$(DEBUG)","1") + CFLAGS += -g -fsanitize=address -fsanitize=leak -static-libasan +endif + +LDLIBS=-lmnl ../lib/ynl.a ../generated/protos.a + +SRCS=$(wildcard *.c) +BINS=$(patsubst %.c,%,${SRCS}) + +include $(wildcard *.d) + +all: $(BINS) + +$(BINS): ../lib/ynl.a ../generated/protos.a + +clean: + rm -f *.o *.d *~ + +hardclean: clean + rm -f $(BINS) + +.PHONY: all clean +.DEFAULT_GOAL=all diff --git a/tools/net/ynl/samples/netdev.c b/tools/net/ynl/samples/netdev.c new file mode 100644 index 000000000000..d31268aa47c5 --- /dev/null +++ b/tools/net/ynl/samples/netdev.c @@ -0,0 +1,108 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include <string.h> + +#include <ynl.h> + +#include <net/if.h> + +#include "netdev-user.h" + +/* netdev genetlink family code sample + * This sample shows off basics of the netdev family but also notification + * handling, hence the somewhat odd UI. We subscribe to notifications first + * then wait for ifc selection, so the socket may already accumulate + * notifications as we wait. This allows us to test that YNL can handle + * requests and notifications getting interleaved. + */ + +static void netdev_print_device(struct netdev_dev_get_rsp *d, unsigned int op) +{ + char ifname[IF_NAMESIZE]; + const char *name; + + if (!d->_present.ifindex) + return; + + name = if_indextoname(d->ifindex, ifname); + if (name) + printf("%8s", name); + printf("[%d]\t", d->ifindex); + + if (!d->_present.xdp_features) + return; + + printf("%llx:", d->xdp_features); + for (int i = 0; d->xdp_features > 1U << i; i++) { + if (d->xdp_features & (1U << i)) + printf(" %s", netdev_xdp_act_str(1 << i)); + } + + name = netdev_op_str(op); + if (name) + printf(" (ntf: %s)", name); + printf("\n"); +} + +int main(int argc, char **argv) +{ + struct netdev_dev_get_list *devs; + struct ynl_ntf_base_type *ntf; + struct ynl_error yerr; + struct ynl_sock *ys; + int ifindex = 0; + + if (argc > 1) + ifindex = strtol(argv[1], NULL, 0); + + ys = ynl_sock_create(&ynl_netdev_family, &yerr); + if (!ys) { + fprintf(stderr, "YNL: %s\n", yerr.msg); + return 1; + } + + if (ynl_subscribe(ys, "mgmt")) + goto err_close; + + printf("Select ifc ($ifindex; or 0 = dump; or -2 ntf check): "); + scanf("%d", &ifindex); + + if (ifindex > 0) { + struct netdev_dev_get_req *req; + struct netdev_dev_get_rsp *d; + + req = netdev_dev_get_req_alloc(); + netdev_dev_get_req_set_ifindex(req, ifindex); + + d = netdev_dev_get(ys, req); + netdev_dev_get_req_free(req); + if (!d) + goto err_close; + + netdev_print_device(d, 0); + netdev_dev_get_rsp_free(d); + } else if (!ifindex) { + devs = netdev_dev_get_dump(ys); + if (!devs) + goto err_close; + + ynl_dump_foreach(devs, d) + netdev_print_device(d, 0); + netdev_dev_get_list_free(devs); + } else if (ifindex == -2) { + ynl_ntf_check(ys); + } + while ((ntf = ynl_ntf_dequeue(ys))) { + netdev_print_device((struct netdev_dev_get_rsp *)&ntf->data, + ntf->cmd); + ynl_ntf_free(ntf); + } + + ynl_sock_destroy(ys); + return 0; + +err_close: + fprintf(stderr, "YNL: %s\n", ys->err.msg); + ynl_sock_destroy(ys); + return 2; +} diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py index cc2f8c945340..c07340715601 100755 --- a/tools/net/ynl/ynl-gen-c.py +++ b/tools/net/ynl/ynl-gen-c.py @@ -94,7 +94,10 @@ class Type(SpecAttr): def arg_member(self, ri): member = self._complex_member_type(ri) if member: - return [member + ' *' + self.c_name] + arg = [member + ' *' + self.c_name] + if self.presence_type() == 'count': + arg += ['unsigned int n_' + self.c_name] + return arg raise Exception(f"Struct member not implemented for class type {self.type}") def struct_member(self, ri): @@ -170,6 +173,7 @@ class Type(SpecAttr): for line in lines: ri.cw.p(line) ri.cw.block_end() + return True def _setter_lines(self, ri, member, presence): raise Exception(f"Setter not implemented for class type {self.type}") @@ -187,9 +191,12 @@ class Type(SpecAttr): code.append(presence + ' = 1;') code += self._setter_lines(ri, member, presence) - ri.cw.write_func('static inline void', - f"{op_prefix(ri, direction, deref=deref)}_set_{'_'.join(ref)}", - body=code, + func_name = f"{op_prefix(ri, direction, deref=deref)}_set_{'_'.join(ref)}" + free = bool([x for x in code if 'free(' in x]) + alloc = bool([x for x in code if 'alloc(' in x]) + if free and not alloc: + func_name = '__' + func_name + ri.cw.write_func('static inline void', func_name, body=code, args=[f'{type_name(ri, direction, deref=deref)} *{var}'] + self.arg_member(ri)) @@ -197,6 +204,12 @@ class TypeUnused(Type): def presence_type(self): return '' + def arg_member(self, ri): + return [] + + def _attr_get(self, ri, var): + return ['return MNL_CB_ERROR;'], None, None + def _attr_typol(self): return '.type = YNL_PT_REJECT, ' @@ -208,8 +221,14 @@ class TypePad(Type): def presence_type(self): return '' + def arg_member(self, ri): + return [] + def _attr_typol(self): - return '.type = YNL_PT_REJECT, ' + return '.type = YNL_PT_IGNORE, ' + + def attr_get(self, ri, var, first): + pass def attr_policy(self, cw): pass @@ -411,7 +430,8 @@ class TypeNest(Type): f"{self.enum_name}, &{var}->{self.c_name})") def _attr_get(self, ri, var): - get_lines = [f"{self.nested_render_name}_parse(&parg, attr);"] + get_lines = [f"if ({self.nested_render_name}_parse(&parg, attr))", + "return MNL_CB_ERROR;"] init_lines = [f"parg.rsp_policy = &{self.nested_render_name}_nest;", f"parg.data = &{var}->{self.c_name};"] return get_lines, init_lines, None @@ -430,6 +450,13 @@ class TypeMultiAttr(Type): def presence_type(self): return 'count' + def _mnl_type(self): + t = self.type + # mnl does not have a helper for signed types + if t[0] == 's': + t = 'u' + t[1:] + return t + def _complex_member_type(self, ri): if 'type' not in self.attr or self.attr['type'] == 'nest': return f"struct {self.nested_render_name}" @@ -443,9 +470,14 @@ class TypeMultiAttr(Type): return 'type' not in self.attr or self.attr['type'] == 'nest' def free(self, ri, var, ref): - if 'type' not in self.attr or self.attr['type'] == 'nest': + if self.attr['type'] in scalars: + ri.cw.p(f"free({var}->{ref}{self.c_name});") + elif 'type' not in self.attr or self.attr['type'] == 'nest': ri.cw.p(f"for (i = 0; i < {var}->{ref}n_{self.c_name}; i++)") ri.cw.p(f'{self.nested_render_name}_free(&{var}->{ref}{self.c_name}[i]);') + ri.cw.p(f"free({var}->{ref}{self.c_name});") + else: + raise Exception(f"Free of MultiAttr sub-type {self.attr['type']} not supported yet") def _attr_typol(self): if 'type' not in self.attr or self.attr['type'] == 'nest': @@ -456,7 +488,26 @@ class TypeMultiAttr(Type): raise Exception(f"Sub-type {self.attr['type']} not supported yet") def _attr_get(self, ri, var): - return f'{var}->n_{self.c_name}++;', None, None + return f'n_{self.c_name}++;', None, None + + def attr_put(self, ri, var): + if self.attr['type'] in scalars: + put_type = self._mnl_type() + ri.cw.p(f"for (unsigned int i = 0; i < {var}->n_{self.c_name}; i++)") + ri.cw.p(f"mnl_attr_put_{put_type}(nlh, {self.enum_name}, {var}->{self.c_name}[i]);") + elif 'type' not in self.attr or self.attr['type'] == 'nest': + ri.cw.p(f"for (unsigned int i = 0; i < {var}->n_{self.c_name}; i++)") + self._attr_put_line(ri, var, f"{self.nested_render_name}_put(nlh, " + + f"{self.enum_name}, &{var}->{self.c_name}[i])") + else: + raise Exception(f"Put of MultiAttr sub-type {self.attr['type']} not supported yet") + + def _setter_lines(self, ri, member, presence): + # For multi-attr we have a count, not presence, hack up the presence + presence = presence[:-(len('_present.') + len(self.c_name))] + "n_" + self.c_name + return [f"free({member});", + f"{member} = {self.c_name};", + f"{presence} = n_{self.c_name};"] class TypeArrayNest(Type): @@ -812,7 +863,8 @@ class Family(SpecFamily): inherit = set() nested = spec['nested-attributes'] if nested not in self.root_sets: - self.pure_nested_structs[nested] = Struct(self, nested, inherited=inherit) + if nested not in self.pure_nested_structs: + self.pure_nested_structs[nested] = Struct(self, nested, inherited=inherit) if attr in rs_members['request']: self.pure_nested_structs[nested].request = True if attr in rs_members['reply']: @@ -872,6 +924,12 @@ class Family(SpecFamily): self.hooks[when][op_mode]['set'].add(name) self.hooks[when][op_mode]['list'].append(name) + def has_notifications(self): + for op in self.ops.values(): + if 'notify' in op or 'event' in op: + return True + return False + class RenderInfo: def __init__(self, cw, family, ku_space, op, op_name, op_mode, attr_set=None): @@ -883,11 +941,12 @@ class RenderInfo: self.op_mode = op_mode # 'do' and 'dump' response parsing is identical - if op_mode != 'do' and 'dump' in op and 'do' in op and 'reply' in op['do'] and \ - op["do"]["reply"] == op["dump"]["reply"]: - self.type_consistent = True - else: - self.type_consistent = op_mode == 'event' + self.type_consistent = True + if op_mode != 'do' and 'dump' in op and 'do' in op: + if ('reply' in op['do']) != ('reply' in op["dump"]): + self.type_consistent = False + elif 'reply' in op['do'] and op["do"]["reply"] != op["dump"]["reply"]: + self.type_consistent = False self.attr_set = attr_set if not self.attr_set: @@ -922,9 +981,10 @@ class CodeWriter: def _is_cond(cls, line): return line.startswith('if') or line.startswith('while') or line.startswith('for') - def p(self, line, add_ind=0): + def p(self, line, add_ind=0, eat_nl=False): if self._nl: - self._out.write('\n') + if not eat_nl: + self._out.write('\n') self._nl = False ind = self._ind if line[-1] == ':': @@ -949,7 +1009,7 @@ class CodeWriter: if line and line[0] not in {';', ','}: line = ' ' + line self._ind -= 1 - self.p('}' + line) + self.p('}' + line, eat_nl=True) def write_doc_line(self, doc, indent=True): words = doc.split() @@ -1152,6 +1212,56 @@ def put_typol(cw, struct): cw.nl() +def put_op_name_fwd(family, cw): + cw.write_func_prot('const char *', f'{family.name}_op_str', ['int op'], suffix=';') + + +def put_op_name(family, cw): + map_name = f'{family.name}_op_strmap' + cw.block_start(line=f"static const char * const {map_name}[] =") + for op_name, op in family.msgs.items(): + cw.p(f'[{op.enum_name}] = "{op_name}",') + cw.block_end(line=';') + cw.nl() + + cw.write_func_prot('const char *', f'{family.name}_op_str', ['int op']) + cw.block_start() + cw.p(f'if (op < 0 || op >= (int)MNL_ARRAY_SIZE({map_name}))') + cw.p('return NULL;') + cw.p(f'return {map_name}[op];') + cw.block_end() + cw.nl() + + +def put_enum_to_str_fwd(family, cw, enum): + args = [f'enum {enum.render_name} value'] + if 'enum-name' in enum and not enum['enum-name']: + args = ['int value'] + cw.write_func_prot('const char *', f'{enum.render_name}_str', args, suffix=';') + + +def put_enum_to_str(family, cw, enum): + map_name = f'{enum.render_name}_strmap' + cw.block_start(line=f"static const char * const {map_name}[] =") + for entry in enum.entries.values(): + cw.p(f'[{entry.value}] = "{entry.name}",') + cw.block_end(line=';') + cw.nl() + + args = [f'enum {enum.render_name} value'] + if 'enum-name' in enum and not enum['enum-name']: + args = ['int value'] + cw.write_func_prot('const char *', f'{enum.render_name}_str', args) + cw.block_start() + if enum.type == 'flags': + cw.p('value = ffs(value) - 1;') + cw.p(f'if (value < 0 || value >= (int)MNL_ARRAY_SIZE({map_name}))') + cw.p('return NULL;') + cw.p(f'return {map_name}[value];') + cw.block_end() + cw.nl() + + def put_req_nested(ri, struct): func_args = ['struct nlmsghdr *nlh', 'unsigned int attr_type', @@ -1196,6 +1306,11 @@ def _multi_parse(ri, struct, init_lines, local_vars): local_vars.append('struct ynl_parse_arg parg;') init_lines.append('parg.ys = yarg->ys;') + all_multi = array_nests | multi_attrs + + for anest in sorted(all_multi): + local_vars.append(f"unsigned int n_{struct[anest].c_name} = 0;") + ri.cw.block_start() ri.cw.write_func_lvar(local_vars) @@ -1206,13 +1321,19 @@ def _multi_parse(ri, struct, init_lines, local_vars): for arg in struct.inherited: ri.cw.p(f'dst->{arg} = {arg};') + for anest in sorted(all_multi): + aspec = struct[anest] + ri.cw.p(f"if (dst->{aspec.c_name})") + ri.cw.p(f'return ynl_error_parse(yarg, "attribute already present ({struct.attr_set.name}.{aspec.name})");') + ri.cw.nl() ri.cw.block_start(line=iter_line) first = True for _, arg in struct.member_list(): - arg.attr_get(ri, 'dst', first=first) - first = False + good = arg.attr_get(ri, 'dst', first=first) + # First may be 'unused' or 'pad', ignore those + first &= not good ri.cw.block_end() ri.cw.nl() @@ -1220,8 +1341,9 @@ def _multi_parse(ri, struct, init_lines, local_vars): for anest in sorted(array_nests): aspec = struct[anest] - ri.cw.block_start(line=f"if (dst->n_{aspec.c_name})") - ri.cw.p(f"dst->{aspec.c_name} = calloc(dst->n_{aspec.c_name}, sizeof(*dst->{aspec.c_name}));") + ri.cw.block_start(line=f"if (n_{aspec.c_name})") + ri.cw.p(f"dst->{aspec.c_name} = calloc({aspec.c_name}, sizeof(*dst->{aspec.c_name}));") + ri.cw.p(f"dst->n_{aspec.c_name} = n_{aspec.c_name};") ri.cw.p('i = 0;') ri.cw.p(f"parg.rsp_policy = &{aspec.nested_render_name}_nest;") ri.cw.block_start(line=f"mnl_attr_for_each_nested(attr, attr_{aspec.c_name})") @@ -1235,8 +1357,9 @@ def _multi_parse(ri, struct, init_lines, local_vars): for anest in sorted(multi_attrs): aspec = struct[anest] - ri.cw.block_start(line=f"if (dst->n_{aspec.c_name})") - ri.cw.p(f"dst->{aspec.c_name} = calloc(dst->n_{aspec.c_name}, sizeof(*dst->{aspec.c_name}));") + ri.cw.block_start(line=f"if (n_{aspec.c_name})") + ri.cw.p(f"dst->{aspec.c_name} = calloc(n_{aspec.c_name}, sizeof(*dst->{aspec.c_name}));") + ri.cw.p(f"dst->n_{aspec.c_name} = n_{aspec.c_name};") ri.cw.p('i = 0;') if 'nested-attributes' in aspec: ri.cw.p(f"parg.rsp_policy = &{aspec.nested_render_name}_nest;") @@ -1304,13 +1427,13 @@ def print_req(ri): ret_err = '-1' direction = "request" local_vars = ['struct nlmsghdr *nlh;', - 'int len, err;'] + 'int err;'] if 'reply' in ri.op[ri.op_mode]: ret_ok = 'rsp' ret_err = 'NULL' local_vars += [f'{type_name(ri, rdir(direction))} *rsp;', - 'struct ynl_parse_arg yarg = { .ys = ys, };'] + 'struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };'] print_prototype(ri, direction, terminate=False) ri.cw.block_start() @@ -1320,41 +1443,39 @@ def print_req(ri): ri.cw.p(f"ys->req_policy = &{ri.struct['request'].render_name}_nest;") if 'reply' in ri.op[ri.op_mode]: - ri.cw.p(f"yarg.rsp_policy = &{ri.struct['reply'].render_name}_nest;") + ri.cw.p(f"yrs.yarg.rsp_policy = &{ri.struct['reply'].render_name}_nest;") ri.cw.nl() for _, attr in ri.struct["request"].member_list(): attr.attr_put(ri, "req") ri.cw.nl() - ri.cw.p('err = mnl_socket_sendto(ys->sock, nlh, nlh->nlmsg_len);') - ri.cw.p('if (err < 0)') - ri.cw.p(f"return {ret_err};") - ri.cw.nl() - ri.cw.p('len = mnl_socket_recvfrom(ys->sock, ys->rx_buf, MNL_SOCKET_BUFFER_SIZE);') - ri.cw.p('if (len < 0)') - ri.cw.p(f"return {ret_err};") - ri.cw.nl() - + parse_arg = "NULL" if 'reply' in ri.op[ri.op_mode]: ri.cw.p('rsp = calloc(1, sizeof(*rsp));') - ri.cw.p('yarg.data = rsp;') + ri.cw.p('yrs.yarg.data = rsp;') + ri.cw.p(f"yrs.cb = {op_prefix(ri, 'reply')}_parse;") + if ri.op.value is not None: + ri.cw.p(f'yrs.rsp_cmd = {ri.op.enum_name};') + else: + ri.cw.p(f'yrs.rsp_cmd = {ri.op.rsp_value};') ri.cw.nl() - ri.cw.p(f"err = {ri.nl.parse_cb_run(op_prefix(ri, 'reply') + '_parse', '&yarg', False)};") - ri.cw.p('if (err < 0)') + parse_arg = '&yrs' + ri.cw.p(f"err = ynl_exec(ys, nlh, {parse_arg});") + ri.cw.p('if (err < 0)') + if 'reply' in ri.op[ri.op_mode]: ri.cw.p('goto err_free;') - ri.cw.nl() - - ri.cw.p('err = ynl_recv_ack(ys, err);') - ri.cw.p('if (err)') - ri.cw.p('goto err_free;') + else: + ri.cw.p('return -1;') ri.cw.nl() + ri.cw.p(f"return {ret_ok};") ri.cw.nl() - ri.cw.p('err_free:') if 'reply' in ri.op[ri.op_mode]: + ri.cw.p('err_free:') ri.cw.p(f"{call_free(ri, rdir(direction), 'rsp')}") - ri.cw.p(f"return {ret_err};") + ri.cw.p(f"return {ret_err};") + ri.cw.block_end() @@ -1364,7 +1485,7 @@ def print_dump(ri): ri.cw.block_start() local_vars = ['struct ynl_dump_state yds = {};', 'struct nlmsghdr *nlh;', - 'int len, err;'] + 'int err;'] for var in local_vars: ri.cw.p(f'{var}') @@ -1373,6 +1494,10 @@ def print_dump(ri): ri.cw.p('yds.ys = ys;') ri.cw.p(f"yds.alloc_sz = sizeof({type_name(ri, rdir(direction))});") ri.cw.p(f"yds.cb = {op_prefix(ri, 'reply', deref=True)}_parse;") + if ri.op.value is not None: + ri.cw.p(f'yds.rsp_cmd = {ri.op.enum_name};') + else: + ri.cw.p(f'yds.rsp_cmd = {ri.op.rsp_value};') ri.cw.p(f"yds.rsp_policy = &{ri.struct['reply'].render_name}_nest;") ri.cw.nl() ri.cw.p(f"nlh = ynl_gemsg_start_dump(ys, {ri.nl.get_family_id()}, {ri.op.enum_name}, 1);") @@ -1384,21 +1509,10 @@ def print_dump(ri): attr.attr_put(ri, "req") ri.cw.nl() - ri.cw.p('err = mnl_socket_sendto(ys->sock, nlh, nlh->nlmsg_len);') + ri.cw.p('err = ynl_exec_dump(ys, nlh, &yds);') ri.cw.p('if (err < 0)') - ri.cw.p('return NULL;') - ri.cw.nl() - - ri.cw.block_start(line='do') - ri.cw.p('len = mnl_socket_recvfrom(ys->sock, ys->rx_buf, MNL_SOCKET_BUFFER_SIZE);') - ri.cw.p('if (len < 0)') ri.cw.p('goto free_list;') ri.cw.nl() - ri.cw.p(f"err = {ri.nl.parse_cb_run('ynl_dump_trampoline', '&yds', False, indent=2)};") - ri.cw.p('if (err < 0)') - ri.cw.p('goto free_list;') - ri.cw.block_end(line='while (err > 0);') - ri.cw.nl() ri.cw.p('return yds.first;') ri.cw.nl() @@ -1418,6 +1532,14 @@ def free_arg_name(direction): return 'obj' +def print_alloc_wrapper(ri, direction): + name = op_prefix(ri, direction) + ri.cw.write_func_prot(f'static inline struct {name} *', f"{name}_alloc", [f"void"]) + ri.cw.block_start() + ri.cw.p(f'return calloc(1, sizeof(struct {name}));') + ri.cw.block_end() + + def print_free_prototype(ri, direction, suffix=';'): name = op_prefix(ri, direction) arg = free_arg_name(direction) @@ -1465,6 +1587,7 @@ def print_type_full(ri, struct): def print_type_helpers(ri, direction, deref=False): print_free_prototype(ri, direction) + ri.cw.nl() if ri.ku_space == 'user' and direction == 'request': for _, attr in ri.struct[direction].member_list(): @@ -1473,6 +1596,7 @@ def print_type_helpers(ri, direction, deref=False): def print_req_type_helpers(ri): + print_alloc_wrapper(ri, "request") print_type_helpers(ri, "request") @@ -1496,6 +1620,12 @@ def print_req_type(ri): print_type(ri, "request") +def print_req_free(ri): + if 'request' not in ri.op[ri.op_mode]: + return + _free_type(ri, 'request', ri.struct['request']) + + def print_rsp_type(ri): if (ri.op_mode == 'do' or ri.op_mode == 'dump') and 'reply' in ri.op[ri.op_mode]: direction = 'reply' @@ -1513,6 +1643,7 @@ def print_wrapped_type(ri): elif ri.op_mode == 'notify' or ri.op_mode == 'event': ri.cw.p('__u16 family;') ri.cw.p('__u8 cmd;') + ri.cw.p('struct ynl_ntf_base_type *next;') ri.cw.p(f"void (*free)({type_name(ri, 'reply')} *ntf);") ri.cw.p(f"{type_name(ri, 'reply', deref=True)} obj __attribute__ ((aligned (8)));") ri.cw.block_end(line=';') @@ -1564,7 +1695,7 @@ def print_dump_type_free(ri): ri.cw.block_start() ri.cw.p(f"{sub_type} *next = rsp;") ri.cw.nl() - ri.cw.block_start(line='while (next)') + ri.cw.block_start(line='while ((void *)next != YNL_LIST_END)') _free_type_members_iter(ri, ri.struct['reply']) ri.cw.p('rsp = next;') ri.cw.p('next = rsp->next;') @@ -2035,6 +2166,45 @@ def render_uapi(family, cw): cw.p(f'#endif /* {hdr_prot} */') +def _render_user_ntf_entry(ri, op): + ri.cw.block_start(line=f"[{op.enum_name}] = ") + ri.cw.p(f".alloc_sz\t= sizeof({type_name(ri, 'event')}),") + ri.cw.p(f".cb\t\t= {op_prefix(ri, 'reply', deref=True)}_parse,") + ri.cw.p(f".policy\t\t= &{ri.struct['reply'].render_name}_nest,") + ri.cw.p(f".free\t\t= (void *){op_prefix(ri, 'notify')}_free,") + ri.cw.block_end(line=',') + + +def render_user_family(family, cw, prototype): + symbol = f'const struct ynl_family ynl_{family.c_name}_family' + if prototype: + cw.p(f'extern {symbol};') + return + + ntf = family.has_notifications() + if ntf: + cw.block_start(line=f"static const struct ynl_ntf_info {family['name']}_ntf_info[] = ") + for ntf_op in sorted(family.all_notify.keys()): + op = family.ops[ntf_op] + ri = RenderInfo(cw, family, "user", op, ntf_op, "notify") + for ntf in op['notify']['cmds']: + _render_user_ntf_entry(ri, ntf) + for op_name, op in family.ops.items(): + if 'event' not in op: + continue + ri = RenderInfo(cw, family, "user", op, op_name, "event") + _render_user_ntf_entry(ri, op) + cw.block_end(line=";") + cw.nl() + + cw.block_start(f'{symbol} = ') + cw.p(f'.name\t\t= "{family.name}",') + if ntf: + cw.p(f".ntf_info\t= {family['name']}_ntf_info,") + cw.p(f".ntf_info_size\t= MNL_ARRAY_SIZE({family['name']}_ntf_info),") + cw.block_end(line=';') + + def find_kernel_root(full_path): sub_path = '' while True: @@ -2101,7 +2271,16 @@ def main(): if args.out_file: cw.p(f'#include "{os.path.basename(args.out_file[:-2])}.h"') cw.nl() - headers = [parsed.uapi_header] + headers = ['uapi/' + parsed.uapi_header] + else: + cw.p('#include <stdlib.h>') + if args.header: + cw.p('#include <string.h>') + cw.p('#include <linux/types.h>') + else: + cw.p(f'#include "{parsed.name}-user.h"') + cw.p('#include "ynl.h"') + headers = [parsed.uapi_header] for definition in parsed['definitions']: if 'header' in definition: headers.append(definition['header']) @@ -2121,6 +2300,8 @@ def main(): cw.p(f'#include "{one}"') else: cw.p('struct ynl_sock;') + cw.nl() + render_user_family(parsed, cw, True) cw.nl() if args.mode == "kernel": @@ -2182,8 +2363,15 @@ def main(): print_kernel_family_struct_src(parsed, cw) if args.mode == "user": - has_ntf = False if args.header: + cw.p('/* Enums */') + put_op_name_fwd(parsed, cw) + + for name, const in parsed.consts.items(): + if isinstance(const, EnumSet): + put_enum_to_str_fwd(parsed, cw, const) + cw.nl() + cw.p('/* Common nested types */') for attr_set, struct in sorted(parsed.pure_nested_structs.items()): ri = RenderInfo(cw, parsed, args.mode, "", "", "", attr_set) @@ -2219,9 +2407,8 @@ def main(): if 'notify' in op: cw.p(f"/* {op.enum_name} - notify */") ri = RenderInfo(cw, parsed, args.mode, op, op_name, 'notify') - has_ntf = True if not ri.type_consistent: - raise Exception('Only notifications with consistent types supported') + raise Exception(f'Only notifications with consistent types supported ({op.name})') print_wrapped_type(ri) if 'event' in op: @@ -2231,11 +2418,19 @@ def main(): cw.nl() print_wrapped_type(ri) - if has_ntf: + if parsed.has_notifications(): cw.p('/* --------------- Common notification parsing --------------- */') print_ntf_parse_prototype(parsed, cw) cw.nl() else: + cw.p('/* Enums */') + put_op_name(parsed, cw) + + for name, const in parsed.consts.items(): + if isinstance(const, EnumSet): + put_enum_to_str(parsed, cw, const) + cw.nl() + cw.p('/* Policies */') for name, _ in parsed.attr_sets.items(): struct = Struct(parsed, name) @@ -2261,6 +2456,7 @@ def main(): if 'do' in op and 'event' not in op: cw.p(f"/* {op.enum_name} - do */") ri = RenderInfo(cw, parsed, args.mode, op, op_name, "do") + print_req_free(ri) print_rsp_free(ri) parse_rsp_msg(ri) print_req(ri) @@ -2278,14 +2474,12 @@ def main(): if 'notify' in op: cw.p(f"/* {op.enum_name} - notify */") ri = RenderInfo(cw, parsed, args.mode, op, op_name, 'notify') - has_ntf = True if not ri.type_consistent: - raise Exception('Only notifications with consistent types supported') + raise Exception(f'Only notifications with consistent types supported ({op.name})') print_ntf_type_free(ri) if 'event' in op: cw.p(f"/* {op.enum_name} - event */") - has_ntf = True ri = RenderInfo(cw, parsed, args.mode, op, op_name, "do") parse_rsp_msg(ri) @@ -2293,10 +2487,13 @@ def main(): ri = RenderInfo(cw, parsed, args.mode, op, op_name, "event") print_ntf_type_free(ri) - if has_ntf: + if parsed.has_notifications(): cw.p('/* --------------- Common notification parsing --------------- */') print_ntf_type_parse(parsed, cw, args.mode) + cw.nl() + render_user_family(parsed, cw, False) + if args.header: cw.p(f'#endif /* {hdr_prot} */') diff --git a/tools/net/ynl/ynl-regen.sh b/tools/net/ynl/ynl-regen.sh index 74f5de1c2399..2a4525e2aa17 100755 --- a/tools/net/ynl/ynl-regen.sh +++ b/tools/net/ynl/ynl-regen.sh @@ -14,7 +14,7 @@ done KDIR=$(dirname $(dirname $(dirname $(dirname $(realpath $0))))) -files=$(git grep --files-with-matches '^/\* YNL-GEN \(kernel\|uapi\)') +files=$(git grep --files-with-matches '^/\* YNL-GEN \(kernel\|uapi\|user\)') for f in $files; do # params: 0 1 2 3 # $YAML YNL-GEN kernel $mode diff --git a/tools/testing/selftests/bpf/DENYLIST.aarch64 b/tools/testing/selftests/bpf/DENYLIST.aarch64 index 0a6837f97c32..08adc805878b 100644 --- a/tools/testing/selftests/bpf/DENYLIST.aarch64 +++ b/tools/testing/selftests/bpf/DENYLIST.aarch64 @@ -1,33 +1,6 @@ -bloom_filter_map # libbpf: prog 'check_bloom': failed to attach: ERROR: strerror_r(-524)=22 -bpf_cookie/lsm -bpf_cookie/multi_kprobe_attach_api -bpf_cookie/multi_kprobe_link_api -bpf_cookie/trampoline -bpf_loop/check_callback_fn_stop # link unexpected error: -524 -bpf_loop/check_invalid_flags -bpf_loop/check_nested_calls -bpf_loop/check_non_constant_callback -bpf_loop/check_nr_loops -bpf_loop/check_null_callback_ctx -bpf_loop/check_stack -bpf_mod_race # bpf_mod_kfunc_race__attach unexpected error: -524 (errno 524) -bpf_tcp_ca/dctcp_fallback -btf_dump/btf_dump: var_data # find type id unexpected find type id: actual -2 < expected 0 -cgroup_hierarchical_stats # attach unexpected error: -524 (errno 524) -d_path/basic # setup attach failed: -524 -deny_namespace # attach unexpected error: -524 (errno 524) -fentry_fexit # fentry_attach unexpected error: -1 (errno 524) -fentry_test # fentry_attach unexpected error: -1 (errno 524) -fexit_sleep # fexit_attach fexit attach failed: -1 -fexit_stress # fexit attach unexpected fexit attach: actual -524 < expected 0 -fexit_test # fexit_attach unexpected error: -1 (errno 524) -get_func_args_test # get_func_args_test__attach unexpected error: -524 (errno 524) (trampoline) -get_func_ip_test # get_func_ip_test__attach unexpected error: -524 (errno 524) (trampoline) -htab_update/reenter_update -kfree_skb # attach fentry unexpected error: -524 (trampoline) -kfunc_call/subprog # extern (var ksym) 'bpf_prog_active': not found in kernel BTF -kfunc_call/subprog_lskel # skel unexpected error: -2 -kfunc_dynptr_param/dynptr_data_null # libbpf: prog 'dynptr_data_null': failed to attach: ERROR: strerror_r(-524)=22 +bpf_cookie/multi_kprobe_attach_api # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3 +bpf_cookie/multi_kprobe_link_api # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3 +fexit_sleep # The test never returns. The remaining tests cannot start. kprobe_multi_bench_attach # bpf_program__attach_kprobe_multi_opts unexpected error: -95 kprobe_multi_test/attach_api_addrs # bpf_program__attach_kprobe_multi_opts unexpected error: -95 kprobe_multi_test/attach_api_pattern # bpf_program__attach_kprobe_multi_opts unexpected error: -95 @@ -35,51 +8,5 @@ kprobe_multi_test/attach_api_syms # bpf_program__attach_kprobe_mu kprobe_multi_test/bench_attach # bpf_program__attach_kprobe_multi_opts unexpected error: -95 kprobe_multi_test/link_api_addrs # link_fd unexpected link_fd: actual -95 < expected 0 kprobe_multi_test/link_api_syms # link_fd unexpected link_fd: actual -95 < expected 0 -kprobe_multi_test/skel_api # kprobe_multi__attach unexpected error: -524 (errno 524) -ksyms_module/libbpf # 'bpf_testmod_ksym_percpu': not found in kernel BTF -ksyms_module/lskel # test_ksyms_module_lskel__open_and_load unexpected error: -2 -libbpf_get_fd_by_id_opts # test_libbpf_get_fd_by_id_opts__attach unexpected error: -524 (errno 524) -linked_list -lookup_key # test_lookup_key__attach unexpected error: -524 (errno 524) -lru_bug # lru_bug__attach unexpected error: -524 (errno 524) -modify_return # modify_return__attach failed unexpected error: -524 (errno 524) -module_attach # skel_attach skeleton attach failed: -524 -module_fentry_shadow # bpf_link_create unexpected bpf_link_create: actual -524 < expected 0 -mptcp/base # run_test mptcp unexpected error: -524 (errno 524) -netcnt # packets unexpected packets: actual 10001 != expected 10000 -rcu_read_lock # failed to attach: ERROR: strerror_r(-524)=22 -recursion # skel_attach unexpected error: -524 (errno 524) -ringbuf # skel_attach skeleton attachment failed: -1 -setget_sockopt # attach_cgroup unexpected error: -524 -sk_storage_tracing # test_sk_storage_tracing__attach unexpected error: -524 (errno 524) -skc_to_unix_sock # could not attach BPF object unexpected error: -524 (errno 524) -socket_cookie # prog_attach unexpected error: -524 -stacktrace_build_id # compare_stack_ips stackmap vs. stack_amap err -1 errno 2 -task_local_storage/exit_creds # skel_attach unexpected error: -524 (errno 524) -task_local_storage/recursion # skel_attach unexpected error: -524 (errno 524) -test_bprm_opts # attach attach failed: -524 -test_ima # attach attach failed: -524 -test_local_storage # attach lsm attach failed: -524 -test_lsm # test_lsm_first_attach unexpected error: -524 (errno 524) -test_overhead # attach_fentry unexpected error: -524 -timer # timer unexpected error: -524 (errno 524) -timer_crash # timer_crash__attach unexpected error: -524 (errno 524) -timer_mim # timer_mim unexpected error: -524 (errno 524) -trace_printk # trace_printk__attach unexpected error: -1 (errno 524) -trace_vprintk # trace_vprintk__attach unexpected error: -1 (errno 524) -tracing_struct # tracing_struct__attach unexpected error: -524 (errno 524) -trampoline_count # attach_prog unexpected error: -524 -unpriv_bpf_disabled # skel_attach unexpected error: -524 (errno 524) -user_ringbuf/test_user_ringbuf_post_misaligned # misaligned_skel unexpected error: -524 (errno 524) -user_ringbuf/test_user_ringbuf_post_producer_wrong_offset -user_ringbuf/test_user_ringbuf_post_larger_than_ringbuf_sz -user_ringbuf/test_user_ringbuf_basic # ringbuf_basic_skel unexpected error: -524 (errno 524) -user_ringbuf/test_user_ringbuf_sample_full_ring_buffer -user_ringbuf/test_user_ringbuf_post_alignment_autoadjust -user_ringbuf/test_user_ringbuf_overfill -user_ringbuf/test_user_ringbuf_discards_properly_ignored -user_ringbuf/test_user_ringbuf_loop -user_ringbuf/test_user_ringbuf_msg_protocol -user_ringbuf/test_user_ringbuf_blocking_reserve -verify_pkcs7_sig # test_verify_pkcs7_sig__attach unexpected error: -524 (errno 524) -vmlinux # skel_attach skeleton attach failed: -524 +kprobe_multi_test/skel_api # libbpf: failed to load BPF skeleton 'kprobe_multi': -3 +module_attach # prog 'kprobe_multi': failed to auto-attach: -95 diff --git a/tools/testing/selftests/bpf/DENYLIST.s390x b/tools/testing/selftests/bpf/DENYLIST.s390x index c7463f3ec3c0..5061d9e24c16 100644 --- a/tools/testing/selftests/bpf/DENYLIST.s390x +++ b/tools/testing/selftests/bpf/DENYLIST.s390x @@ -26,3 +26,4 @@ user_ringbuf # failed to find kernel BTF type ID of verif_stats # trace_vprintk__open_and_load unexpected error: -9 (?) xdp_bonding # failed to auto-attach program 'trace_on_entry': -524 (trampoline) xdp_metadata # JIT does not support calling kernel function (kfunc) +test_task_under_cgroup # JIT does not support calling kernel function (kfunc) diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 28d2c77262be..538df8fb8c42 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -88,8 +88,7 @@ TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \ xskxceiver xdp_redirect_multi xdp_synproxy veristat xdp_hw_metadata \ xdp_features -TEST_CUSTOM_PROGS = $(OUTPUT)/urandom_read $(OUTPUT)/sign-file -TEST_GEN_FILES += liburandom_read.so +TEST_GEN_FILES += liburandom_read.so urandom_read sign-file # Emit succinct information message describing current building step # $1 - generic step name (e.g., CC, LINK, etc); diff --git a/tools/testing/selftests/bpf/bpf_kfuncs.h b/tools/testing/selftests/bpf/bpf_kfuncs.h index 8c993ec8ceea..642dda0e758a 100644 --- a/tools/testing/selftests/bpf/bpf_kfuncs.h +++ b/tools/testing/selftests/bpf/bpf_kfuncs.h @@ -35,4 +35,10 @@ extern void *bpf_dynptr_slice(const struct bpf_dynptr *ptr, __u32 offset, extern void *bpf_dynptr_slice_rdwr(const struct bpf_dynptr *ptr, __u32 offset, void *buffer, __u32 buffer__szk) __ksym; +extern int bpf_dynptr_adjust(const struct bpf_dynptr *ptr, __u32 start, __u32 end) __ksym; +extern bool bpf_dynptr_is_null(const struct bpf_dynptr *ptr) __ksym; +extern bool bpf_dynptr_is_rdonly(const struct bpf_dynptr *ptr) __ksym; +extern __u32 bpf_dynptr_size(const struct bpf_dynptr *ptr) __ksym; +extern int bpf_dynptr_clone(const struct bpf_dynptr *ptr, struct bpf_dynptr *clone__init) __ksym; + #endif diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index 52785ba671e6..cf216041876c 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -9,6 +9,7 @@ #include <linux/sysfs.h> #include <linux/tracepoint.h> #include "bpf_testmod.h" +#include "bpf_testmod_kfunc.h" #define CREATE_TRACE_POINTS #include "bpf_testmod-events.h" @@ -289,8 +290,171 @@ static const struct btf_kfunc_id_set bpf_testmod_common_kfunc_set = { .set = &bpf_testmod_common_kfunc_ids, }; +__bpf_kfunc u64 bpf_kfunc_call_test1(struct sock *sk, u32 a, u64 b, u32 c, u64 d) +{ + return a + b + c + d; +} + +__bpf_kfunc int bpf_kfunc_call_test2(struct sock *sk, u32 a, u32 b) +{ + return a + b; +} + +__bpf_kfunc struct sock *bpf_kfunc_call_test3(struct sock *sk) +{ + return sk; +} + +__bpf_kfunc long noinline bpf_kfunc_call_test4(signed char a, short b, int c, long d) +{ + /* Provoke the compiler to assume that the caller has sign-extended a, + * b and c on platforms where this is required (e.g. s390x). + */ + return (long)a + (long)b + (long)c + d; +} + +static struct prog_test_ref_kfunc prog_test_struct = { + .a = 42, + .b = 108, + .next = &prog_test_struct, + .cnt = REFCOUNT_INIT(1), +}; + +__bpf_kfunc struct prog_test_ref_kfunc * +bpf_kfunc_call_test_acquire(unsigned long *scalar_ptr) +{ + refcount_inc(&prog_test_struct.cnt); + return &prog_test_struct; +} + +__bpf_kfunc void bpf_kfunc_call_test_offset(struct prog_test_ref_kfunc *p) +{ + WARN_ON_ONCE(1); +} + +__bpf_kfunc struct prog_test_member * +bpf_kfunc_call_memb_acquire(void) +{ + WARN_ON_ONCE(1); + return NULL; +} + +__bpf_kfunc void bpf_kfunc_call_memb1_release(struct prog_test_member1 *p) +{ + WARN_ON_ONCE(1); +} + +static int *__bpf_kfunc_call_test_get_mem(struct prog_test_ref_kfunc *p, const int size) +{ + if (size > 2 * sizeof(int)) + return NULL; + + return (int *)p; +} + +__bpf_kfunc int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p, + const int rdwr_buf_size) +{ + return __bpf_kfunc_call_test_get_mem(p, rdwr_buf_size); +} + +__bpf_kfunc int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p, + const int rdonly_buf_size) +{ + return __bpf_kfunc_call_test_get_mem(p, rdonly_buf_size); +} + +/* the next 2 ones can't be really used for testing expect to ensure + * that the verifier rejects the call. + * Acquire functions must return struct pointers, so these ones are + * failing. + */ +__bpf_kfunc int *bpf_kfunc_call_test_acq_rdonly_mem(struct prog_test_ref_kfunc *p, + const int rdonly_buf_size) +{ + return __bpf_kfunc_call_test_get_mem(p, rdonly_buf_size); +} + +__bpf_kfunc void bpf_kfunc_call_int_mem_release(int *p) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_pass1(struct prog_test_pass1 *p) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_pass2(struct prog_test_pass2 *p) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_fail1(struct prog_test_fail1 *p) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_fail2(struct prog_test_fail2 *p) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_fail3(struct prog_test_fail3 *p) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_mem_len_pass1(void *mem, int mem__sz) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_mem_len_fail1(void *mem, int len) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_mem_len_fail2(u64 *mem, int len) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_ref(struct prog_test_ref_kfunc *p) +{ + /* p != NULL, but p->cnt could be 0 */ +} + +__bpf_kfunc void bpf_kfunc_call_test_destructive(void) +{ +} + +__bpf_kfunc static u32 bpf_kfunc_call_test_static_unused_arg(u32 arg, u32 unused) +{ + return arg; +} + BTF_SET8_START(bpf_testmod_check_kfunc_ids) BTF_ID_FLAGS(func, bpf_testmod_test_mod_kfunc) +BTF_ID_FLAGS(func, bpf_kfunc_call_test1) +BTF_ID_FLAGS(func, bpf_kfunc_call_test2) +BTF_ID_FLAGS(func, bpf_kfunc_call_test3) +BTF_ID_FLAGS(func, bpf_kfunc_call_test4) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_pass1) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_fail1) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_fail2) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_acquire, KF_ACQUIRE | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_kfunc_call_memb_acquire, KF_ACQUIRE | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_kfunc_call_memb1_release, KF_RELEASE) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_get_rdwr_mem, KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_get_rdonly_mem, KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_acq_rdonly_mem, KF_ACQUIRE | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_kfunc_call_int_mem_release, KF_RELEASE) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_pass_ctx) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_pass1) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_pass2) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_fail1) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_fail2) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_fail3) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_ref, KF_TRUSTED_ARGS | KF_RCU) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_destructive, KF_DESTRUCTIVE) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_static_unused_arg) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_offset) BTF_SET8_END(bpf_testmod_check_kfunc_ids) static const struct btf_kfunc_id_set bpf_testmod_kfunc_set = { @@ -312,6 +476,8 @@ static int bpf_testmod_init(void) ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_UNSPEC, &bpf_testmod_common_kfunc_set); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_testmod_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_testmod_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, &bpf_testmod_kfunc_set); if (ret < 0) return ret; if (bpf_fentry_test1(0) < 0) diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h new file mode 100644 index 000000000000..9693c626646b --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h @@ -0,0 +1,100 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _BPF_TESTMOD_KFUNC_H +#define _BPF_TESTMOD_KFUNC_H + +#ifndef __KERNEL__ +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#else +#define __ksym +struct prog_test_member1 { + int a; +}; + +struct prog_test_member { + struct prog_test_member1 m; + int c; +}; + +struct prog_test_ref_kfunc { + int a; + int b; + struct prog_test_member memb; + struct prog_test_ref_kfunc *next; + refcount_t cnt; +}; +#endif + +struct prog_test_pass1 { + int x0; + struct { + int x1; + struct { + int x2; + struct { + int x3; + }; + }; + }; +}; + +struct prog_test_pass2 { + int len; + short arr1[4]; + struct { + char arr2[4]; + unsigned long arr3[8]; + } x; +}; + +struct prog_test_fail1 { + void *p; + int x; +}; + +struct prog_test_fail2 { + int x8; + struct prog_test_pass1 x; +}; + +struct prog_test_fail3 { + int len; + char arr1[2]; + char arr2[]; +}; + +struct prog_test_ref_kfunc * +bpf_kfunc_call_test_acquire(unsigned long *scalar_ptr) __ksym; +void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; +void bpf_kfunc_call_test_ref(struct prog_test_ref_kfunc *p) __ksym; + +void bpf_kfunc_call_test_mem_len_pass1(void *mem, int len) __ksym; +int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p, const int rdwr_buf_size) __ksym; +int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) __ksym; +int *bpf_kfunc_call_test_acq_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) __ksym; +void bpf_kfunc_call_int_mem_release(int *p) __ksym; + +/* The bpf_kfunc_call_test_static_unused_arg is defined as static, + * but bpf program compilation needs to see it as global symbol. + */ +#ifndef __KERNEL__ +u32 bpf_kfunc_call_test_static_unused_arg(u32 arg, u32 unused) __ksym; +#endif + +void bpf_testmod_test_mod_kfunc(int i) __ksym; + +__u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b, + __u32 c, __u64 d) __ksym; +int bpf_kfunc_call_test2(struct sock *sk, __u32 a, __u32 b) __ksym; +struct sock *bpf_kfunc_call_test3(struct sock *sk) __ksym; +long bpf_kfunc_call_test4(signed char a, short b, int c, long d) __ksym; + +void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb) __ksym; +void bpf_kfunc_call_test_pass1(struct prog_test_pass1 *p) __ksym; +void bpf_kfunc_call_test_pass2(struct prog_test_pass2 *p) __ksym; +void bpf_kfunc_call_test_mem_len_fail2(__u64 *mem, int len) __ksym; + +void bpf_kfunc_call_test_destructive(void) __ksym; + +#endif /* _BPF_TESTMOD_KFUNC_H */ diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index 596caa176582..a105c0cd008a 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -427,3 +427,26 @@ void close_netns(struct nstoken *token) close(token->orig_netns_fd); free(token); } + +int get_socket_local_port(int sock_fd) +{ + struct sockaddr_storage addr; + socklen_t addrlen = sizeof(addr); + int err; + + err = getsockname(sock_fd, (struct sockaddr *)&addr, &addrlen); + if (err < 0) + return err; + + if (addr.ss_family == AF_INET) { + struct sockaddr_in *sin = (struct sockaddr_in *)&addr; + + return sin->sin_port; + } else if (addr.ss_family == AF_INET6) { + struct sockaddr_in6 *sin = (struct sockaddr_in6 *)&addr; + + return sin->sin6_port; + } + + return -1; +} diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h index f882c691b790..694185644da6 100644 --- a/tools/testing/selftests/bpf/network_helpers.h +++ b/tools/testing/selftests/bpf/network_helpers.h @@ -56,6 +56,7 @@ int fastopen_connect(int server_fd, const char *data, unsigned int data_len, int make_sockaddr(int family, const char *addr_str, __u16 port, struct sockaddr_storage *addr, socklen_t *len); char *ping_command(int family); +int get_socket_local_port(int sock_fd); struct nstoken; /** diff --git a/tools/testing/selftests/bpf/prog_tests/arg_parsing.c b/tools/testing/selftests/bpf/prog_tests/arg_parsing.c index b17bfa0e0aac..bb143de68875 100644 --- a/tools/testing/selftests/bpf/prog_tests/arg_parsing.c +++ b/tools/testing/selftests/bpf/prog_tests/arg_parsing.c @@ -96,12 +96,80 @@ static void test_parse_test_list(void) goto error; ASSERT_OK(strcmp("*bpf_cookie*", set.tests[0].name), "test name"); ASSERT_OK(strcmp("*trace*", set.tests[0].subtests[0]), "subtest name"); + free_test_filter_set(&set); + + ASSERT_OK(parse_test_list("t/subtest1,t/subtest2", &set, true), + "parsing"); + if (!ASSERT_EQ(set.cnt, 1, "count of test filters")) + goto error; + if (!ASSERT_OK_PTR(set.tests, "test filters initialized")) + goto error; + if (!ASSERT_EQ(set.tests[0].subtest_cnt, 2, "subtest filters count")) + goto error; + ASSERT_OK(strcmp("t", set.tests[0].name), "test name"); + ASSERT_OK(strcmp("subtest1", set.tests[0].subtests[0]), "subtest name"); + ASSERT_OK(strcmp("subtest2", set.tests[0].subtests[1]), "subtest name"); error: free_test_filter_set(&set); } +static void test_parse_test_list_file(void) +{ + struct test_filter_set set; + char tmpfile[80]; + FILE *fp; + int fd; + + snprintf(tmpfile, sizeof(tmpfile), "/tmp/bpf_arg_parsing_test.XXXXXX"); + fd = mkstemp(tmpfile); + if (!ASSERT_GE(fd, 0, "create tmp")) + return; + + fp = fdopen(fd, "w"); + if (!ASSERT_NEQ(fp, NULL, "fdopen tmp")) { + close(fd); + goto out_remove; + } + + fprintf(fp, "# comment\n"); + fprintf(fp, " test_with_spaces \n"); + fprintf(fp, "testA/subtest # comment\n"); + fprintf(fp, "testB#comment with no space\n"); + fprintf(fp, "testB # duplicate\n"); + fprintf(fp, "testA/subtest # subtest duplicate\n"); + fprintf(fp, "testA/subtest2\n"); + fprintf(fp, "testC_no_eof_newline"); + fflush(fp); + + if (!ASSERT_OK(ferror(fp), "prepare tmp")) + goto out_fclose; + + init_test_filter_set(&set); + + ASSERT_OK(parse_test_list_file(tmpfile, &set, true), "parse file"); + + ASSERT_EQ(set.cnt, 4, "test count"); + ASSERT_OK(strcmp("test_with_spaces", set.tests[0].name), "test 0 name"); + ASSERT_EQ(set.tests[0].subtest_cnt, 0, "test 0 subtest count"); + ASSERT_OK(strcmp("testA", set.tests[1].name), "test 1 name"); + ASSERT_EQ(set.tests[1].subtest_cnt, 2, "test 1 subtest count"); + ASSERT_OK(strcmp("subtest", set.tests[1].subtests[0]), "test 1 subtest 0"); + ASSERT_OK(strcmp("subtest2", set.tests[1].subtests[1]), "test 1 subtest 1"); + ASSERT_OK(strcmp("testB", set.tests[2].name), "test 2 name"); + ASSERT_OK(strcmp("testC_no_eof_newline", set.tests[3].name), "test 3 name"); + + free_test_filter_set(&set); + +out_fclose: + fclose(fp); +out_remove: + remove(tmpfile); +} + void test_arg_parsing(void) { if (test__start_subtest("test_parse_test_list")) test_parse_test_list(); + if (test__start_subtest("test_parse_test_list_file")) + test_parse_test_list_file(); } diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c b/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c index a4d0cc9d3367..fe2c502e5089 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c @@ -11,6 +11,7 @@ #include "ksym_race.skel.h" #include "bpf_mod_race.skel.h" #include "kfunc_call_race.skel.h" +#include "testing_helpers.h" /* This test crafts a race between btf_try_get_module and do_init_module, and * checks whether btf_try_get_module handles the invocation for a well-formed @@ -44,35 +45,10 @@ enum bpf_test_state { static _Atomic enum bpf_test_state state = _TS_INVALID; -static int sys_finit_module(int fd, const char *param_values, int flags) -{ - return syscall(__NR_finit_module, fd, param_values, flags); -} - -static int sys_delete_module(const char *name, unsigned int flags) -{ - return syscall(__NR_delete_module, name, flags); -} - -static int load_module(const char *mod) -{ - int ret, fd; - - fd = open("bpf_testmod.ko", O_RDONLY); - if (fd < 0) - return fd; - - ret = sys_finit_module(fd, "", 0); - close(fd); - if (ret < 0) - return ret; - return 0; -} - static void *load_module_thread(void *p) { - if (!ASSERT_NEQ(load_module("bpf_testmod.ko"), 0, "load_module_thread must fail")) + if (!ASSERT_NEQ(load_bpf_testmod(false), 0, "load_module_thread must fail")) atomic_store(&state, TS_MODULE_LOAD); else atomic_store(&state, TS_MODULE_LOAD_FAIL); @@ -124,7 +100,7 @@ static void test_bpf_mod_race_config(const struct test_config *config) if (!ASSERT_NEQ(fault_addr, MAP_FAILED, "mmap for uffd registration")) return; - if (!ASSERT_OK(sys_delete_module("bpf_testmod", 0), "unload bpf_testmod")) + if (!ASSERT_OK(unload_bpf_testmod(false), "unload bpf_testmod")) goto end_mmap; skel = bpf_mod_race__open(); @@ -202,8 +178,8 @@ end_destroy: bpf_mod_race__destroy(skel); ASSERT_OK(kern_sync_rcu(), "kern_sync_rcu"); end_module: - sys_delete_module("bpf_testmod", 0); - ASSERT_OK(load_module("bpf_testmod.ko"), "restore bpf_testmod"); + unload_bpf_testmod(false); + ASSERT_OK(load_bpf_testmod(false), "restore bpf_testmod"); end_mmap: munmap(fault_addr, 4096); atomic_store(&state, _TS_INVALID); diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_obj_pinning.c b/tools/testing/selftests/bpf/prog_tests/bpf_obj_pinning.c new file mode 100644 index 000000000000..31f1e815f671 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_pinning.c @@ -0,0 +1,268 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ +#define _GNU_SOURCE +#include <test_progs.h> +#include <bpf/btf.h> +#include <fcntl.h> +#include <unistd.h> +#include <linux/unistd.h> +#include <linux/mount.h> +#include <sys/syscall.h> + +static inline int sys_fsopen(const char *fsname, unsigned flags) +{ + return syscall(__NR_fsopen, fsname, flags); +} + +static inline int sys_fsconfig(int fs_fd, unsigned cmd, const char *key, const void *val, int aux) +{ + return syscall(__NR_fsconfig, fs_fd, cmd, key, val, aux); +} + +static inline int sys_fsmount(int fs_fd, unsigned flags, unsigned ms_flags) +{ + return syscall(__NR_fsmount, fs_fd, flags, ms_flags); +} + +__attribute__((unused)) +static inline int sys_move_mount(int from_dfd, const char *from_path, + int to_dfd, const char *to_path, + unsigned int ms_flags) +{ + return syscall(__NR_move_mount, from_dfd, from_path, to_dfd, to_path, ms_flags); +} + +static void bpf_obj_pinning_detached(void) +{ + LIBBPF_OPTS(bpf_obj_pin_opts, pin_opts); + LIBBPF_OPTS(bpf_obj_get_opts, get_opts); + int fs_fd = -1, mnt_fd = -1; + int map_fd = -1, map_fd2 = -1; + int zero = 0, src_value, dst_value, err; + const char *map_name = "fsmount_map"; + + /* A bunch of below UAPI calls are constructed based on reading: + * https://brauner.io/2023/02/28/mounting-into-mount-namespaces.html + */ + + /* create VFS context */ + fs_fd = sys_fsopen("bpf", 0); + if (!ASSERT_GE(fs_fd, 0, "fs_fd")) + goto cleanup; + + /* instantiate FS object */ + err = sys_fsconfig(fs_fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0); + if (!ASSERT_OK(err, "fs_create")) + goto cleanup; + + /* create O_PATH fd for detached mount */ + mnt_fd = sys_fsmount(fs_fd, 0, 0); + if (!ASSERT_GE(mnt_fd, 0, "mnt_fd")) + goto cleanup; + + /* If we wanted to expose detached mount in the file system, we'd do + * something like below. But the whole point is that we actually don't + * even have to expose BPF FS in the file system to be able to work + * (pin/get objects) with it. + * + * err = sys_move_mount(mnt_fd, "", -EBADF, mnt_path, MOVE_MOUNT_F_EMPTY_PATH); + * if (!ASSERT_OK(err, "move_mount")) + * goto cleanup; + */ + + /* create BPF map to pin */ + map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, map_name, 4, 4, 1, NULL); + if (!ASSERT_GE(map_fd, 0, "map_fd")) + goto cleanup; + + /* pin BPF map into detached BPF FS through mnt_fd */ + pin_opts.file_flags = BPF_F_PATH_FD; + pin_opts.path_fd = mnt_fd; + err = bpf_obj_pin_opts(map_fd, map_name, &pin_opts); + if (!ASSERT_OK(err, "map_pin")) + goto cleanup; + + /* get BPF map from detached BPF FS through mnt_fd */ + get_opts.file_flags = BPF_F_PATH_FD; + get_opts.path_fd = mnt_fd; + map_fd2 = bpf_obj_get_opts(map_name, &get_opts); + if (!ASSERT_GE(map_fd2, 0, "map_get")) + goto cleanup; + + /* update map through one FD */ + src_value = 0xcafebeef; + err = bpf_map_update_elem(map_fd, &zero, &src_value, 0); + ASSERT_OK(err, "map_update"); + + /* check values written/read through different FDs do match */ + dst_value = 0; + err = bpf_map_lookup_elem(map_fd2, &zero, &dst_value); + ASSERT_OK(err, "map_lookup"); + ASSERT_EQ(dst_value, src_value, "map_value_eq1"); + ASSERT_EQ(dst_value, 0xcafebeef, "map_value_eq2"); + +cleanup: + if (map_fd >= 0) + ASSERT_OK(close(map_fd), "close_map_fd"); + if (map_fd2 >= 0) + ASSERT_OK(close(map_fd2), "close_map_fd2"); + if (fs_fd >= 0) + ASSERT_OK(close(fs_fd), "close_fs_fd"); + if (mnt_fd >= 0) + ASSERT_OK(close(mnt_fd), "close_mnt_fd"); +} + +enum path_kind +{ + PATH_STR_ABS, + PATH_STR_REL, + PATH_FD_REL, +}; + +static void validate_pin(int map_fd, const char *map_name, int src_value, + enum path_kind path_kind) +{ + LIBBPF_OPTS(bpf_obj_pin_opts, pin_opts); + char abs_path[PATH_MAX], old_cwd[PATH_MAX]; + const char *pin_path = NULL; + int zero = 0, dst_value, map_fd2, err; + + snprintf(abs_path, sizeof(abs_path), "/sys/fs/bpf/%s", map_name); + old_cwd[0] = '\0'; + + switch (path_kind) { + case PATH_STR_ABS: + /* absolute path */ + pin_path = abs_path; + break; + case PATH_STR_REL: + /* cwd + relative path */ + ASSERT_OK_PTR(getcwd(old_cwd, sizeof(old_cwd)), "getcwd"); + ASSERT_OK(chdir("/sys/fs/bpf"), "chdir"); + pin_path = map_name; + break; + case PATH_FD_REL: + /* dir fd + relative path */ + pin_opts.file_flags = BPF_F_PATH_FD; + pin_opts.path_fd = open("/sys/fs/bpf", O_PATH); + ASSERT_GE(pin_opts.path_fd, 0, "path_fd"); + pin_path = map_name; + break; + } + + /* pin BPF map using specified path definition */ + err = bpf_obj_pin_opts(map_fd, pin_path, &pin_opts); + ASSERT_OK(err, "obj_pin"); + + /* cleanup */ + if (pin_opts.path_fd >= 0) + close(pin_opts.path_fd); + if (old_cwd[0]) + ASSERT_OK(chdir(old_cwd), "restore_cwd"); + + map_fd2 = bpf_obj_get(abs_path); + if (!ASSERT_GE(map_fd2, 0, "map_get")) + goto cleanup; + + /* update map through one FD */ + err = bpf_map_update_elem(map_fd, &zero, &src_value, 0); + ASSERT_OK(err, "map_update"); + + /* check values written/read through different FDs do match */ + dst_value = 0; + err = bpf_map_lookup_elem(map_fd2, &zero, &dst_value); + ASSERT_OK(err, "map_lookup"); + ASSERT_EQ(dst_value, src_value, "map_value_eq"); +cleanup: + if (map_fd2 >= 0) + ASSERT_OK(close(map_fd2), "close_map_fd2"); + unlink(abs_path); +} + +static void validate_get(int map_fd, const char *map_name, int src_value, + enum path_kind path_kind) +{ + LIBBPF_OPTS(bpf_obj_get_opts, get_opts); + char abs_path[PATH_MAX], old_cwd[PATH_MAX]; + const char *pin_path = NULL; + int zero = 0, dst_value, map_fd2, err; + + snprintf(abs_path, sizeof(abs_path), "/sys/fs/bpf/%s", map_name); + /* pin BPF map using specified path definition */ + err = bpf_obj_pin(map_fd, abs_path); + if (!ASSERT_OK(err, "pin_map")) + return; + + old_cwd[0] = '\0'; + + switch (path_kind) { + case PATH_STR_ABS: + /* absolute path */ + pin_path = abs_path; + break; + case PATH_STR_REL: + /* cwd + relative path */ + ASSERT_OK_PTR(getcwd(old_cwd, sizeof(old_cwd)), "getcwd"); + ASSERT_OK(chdir("/sys/fs/bpf"), "chdir"); + pin_path = map_name; + break; + case PATH_FD_REL: + /* dir fd + relative path */ + get_opts.file_flags = BPF_F_PATH_FD; + get_opts.path_fd = open("/sys/fs/bpf", O_PATH); + ASSERT_GE(get_opts.path_fd, 0, "path_fd"); + pin_path = map_name; + break; + } + + map_fd2 = bpf_obj_get_opts(pin_path, &get_opts); + if (!ASSERT_GE(map_fd2, 0, "map_get")) + goto cleanup; + + /* cleanup */ + if (get_opts.path_fd >= 0) + close(get_opts.path_fd); + if (old_cwd[0]) + ASSERT_OK(chdir(old_cwd), "restore_cwd"); + + /* update map through one FD */ + err = bpf_map_update_elem(map_fd, &zero, &src_value, 0); + ASSERT_OK(err, "map_update"); + + /* check values written/read through different FDs do match */ + dst_value = 0; + err = bpf_map_lookup_elem(map_fd2, &zero, &dst_value); + ASSERT_OK(err, "map_lookup"); + ASSERT_EQ(dst_value, src_value, "map_value_eq"); +cleanup: + if (map_fd2 >= 0) + ASSERT_OK(close(map_fd2), "close_map_fd2"); + unlink(abs_path); +} + +static void bpf_obj_pinning_mounted(enum path_kind path_kind) +{ + const char *map_name = "mounted_map"; + int map_fd; + + /* create BPF map to pin */ + map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, map_name, 4, 4, 1, NULL); + if (!ASSERT_GE(map_fd, 0, "map_fd")) + return; + + validate_pin(map_fd, map_name, 100 + (int)path_kind, path_kind); + validate_get(map_fd, map_name, 200 + (int)path_kind, path_kind); + ASSERT_OK(close(map_fd), "close_map_fd"); +} + +void test_bpf_obj_pinning() +{ + if (test__start_subtest("detached")) + bpf_obj_pinning_detached(); + if (test__start_subtest("mounted-str-abs")) + bpf_obj_pinning_mounted(PATH_STR_ABS); + if (test__start_subtest("mounted-str-rel")) + bpf_obj_pinning_mounted(PATH_STR_REL); + if (test__start_subtest("mounted-fd-rel")) + bpf_obj_pinning_mounted(PATH_FD_REL); +} diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c b/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c index 4d2fa99273d8..2bb5773d6f99 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c @@ -25,6 +25,8 @@ static void test_setsockopt_set(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach setsockopt that sets EUNATCH, assert that * we actually get that error when we run setsockopt() */ @@ -59,6 +61,8 @@ static void test_setsockopt_set_and_get(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach setsockopt that sets EUNATCH, and one that gets the * previously set errno. Assert that we get the same errno back. */ @@ -100,6 +104,8 @@ static void test_setsockopt_default_zero(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach setsockopt that gets the previously set errno. * Assert that, without anything setting one, we get 0. */ @@ -134,6 +140,8 @@ static void test_setsockopt_default_zero_and_set(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach setsockopt that gets the previously set errno, and then * one that sets the errno to EUNATCH. Assert that the get does not * see EUNATCH set later, and does not prevent EUNATCH from being set. @@ -177,6 +185,8 @@ static void test_setsockopt_override(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach setsockopt that sets EUNATCH, then one that sets EISCONN, * and then one that gets the exported errno. Assert both the syscall * and the helper sees the last set errno. @@ -224,6 +234,8 @@ static void test_setsockopt_legacy_eperm(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach setsockopt that return a reject without setting errno * (legacy reject), and one that gets the errno. Assert that for * backward compatibility the syscall result in EPERM, and this @@ -268,6 +280,8 @@ static void test_setsockopt_legacy_no_override(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach setsockopt that sets EUNATCH, then one that return a reject * without setting errno, and then one that gets the exported errno. * Assert both the syscall and the helper's errno are unaffected by @@ -319,6 +333,8 @@ static void test_getsockopt_get(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach getsockopt that gets previously set errno. Assert that the * error from kernel is in both ctx_retval_value and retval_value. */ @@ -359,6 +375,8 @@ static void test_getsockopt_override(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach getsockopt that sets retval to -EISCONN. Assert that this * overrides the value from kernel. */ @@ -396,6 +414,8 @@ static void test_getsockopt_retval_sync(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach getsockopt that sets retval to -EISCONN, and one that clears * ctx retval. Assert that the clearing ctx retval is synced to helper * and clears any errors both from kernel and BPF.. diff --git a/tools/testing/selftests/bpf/prog_tests/dynptr.c b/tools/testing/selftests/bpf/prog_tests/dynptr.c index d176c34a7d2e..7cfac53c0d58 100644 --- a/tools/testing/selftests/bpf/prog_tests/dynptr.c +++ b/tools/testing/selftests/bpf/prog_tests/dynptr.c @@ -20,6 +20,14 @@ static struct { {"test_ringbuf", SETUP_SYSCALL_SLEEP}, {"test_skb_readonly", SETUP_SKB_PROG}, {"test_dynptr_skb_data", SETUP_SKB_PROG}, + {"test_adjust", SETUP_SYSCALL_SLEEP}, + {"test_adjust_err", SETUP_SYSCALL_SLEEP}, + {"test_zero_size_dynptr", SETUP_SYSCALL_SLEEP}, + {"test_dynptr_is_null", SETUP_SYSCALL_SLEEP}, + {"test_dynptr_is_rdonly", SETUP_SKB_PROG}, + {"test_dynptr_clone", SETUP_SKB_PROG}, + {"test_dynptr_skb_no_buff", SETUP_SKB_PROG}, + {"test_dynptr_skb_strcmp", SETUP_SKB_PROG}, }; static void verify_success(const char *prog_name, enum test_setup_type setup_type) diff --git a/tools/testing/selftests/bpf/prog_tests/global_map_resize.c b/tools/testing/selftests/bpf/prog_tests/global_map_resize.c new file mode 100644 index 000000000000..fd41425d2e5c --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/global_map_resize.c @@ -0,0 +1,227 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ +#include <errno.h> +#include <sys/syscall.h> +#include <unistd.h> +#include "test_global_map_resize.skel.h" +#include "test_progs.h" + +static void run_prog_bss_array_sum(void) +{ + (void)syscall(__NR_getpid); +} + +static void run_prog_data_array_sum(void) +{ + (void)syscall(__NR_getuid); +} + +static void global_map_resize_bss_subtest(void) +{ + int err; + struct test_global_map_resize *skel; + struct bpf_map *map; + const __u32 desired_sz = sizeof(skel->bss->sum) + sysconf(_SC_PAGE_SIZE) * 2; + size_t array_len, actual_sz; + + skel = test_global_map_resize__open(); + if (!ASSERT_OK_PTR(skel, "test_global_map_resize__open")) + goto teardown; + + /* set some initial value before resizing. + * it is expected this non-zero value will be preserved + * while resizing. + */ + skel->bss->array[0] = 1; + + /* resize map value and verify the new size */ + map = skel->maps.bss; + err = bpf_map__set_value_size(map, desired_sz); + if (!ASSERT_OK(err, "bpf_map__set_value_size")) + goto teardown; + if (!ASSERT_EQ(bpf_map__value_size(map), desired_sz, "resize")) + goto teardown; + + /* set the expected number of elements based on the resized array */ + array_len = (desired_sz - sizeof(skel->bss->sum)) / sizeof(skel->bss->array[0]); + if (!ASSERT_GT(array_len, 1, "array_len")) + goto teardown; + + skel->bss = bpf_map__initial_value(skel->maps.bss, &actual_sz); + if (!ASSERT_OK_PTR(skel->bss, "bpf_map__initial_value (ptr)")) + goto teardown; + if (!ASSERT_EQ(actual_sz, desired_sz, "bpf_map__initial_value (size)")) + goto teardown; + + /* fill the newly resized array with ones, + * skipping the first element which was previously set + */ + for (int i = 1; i < array_len; i++) + skel->bss->array[i] = 1; + + /* set global const values before loading */ + skel->rodata->pid = getpid(); + skel->rodata->bss_array_len = array_len; + skel->rodata->data_array_len = 1; + + err = test_global_map_resize__load(skel); + if (!ASSERT_OK(err, "test_global_map_resize__load")) + goto teardown; + err = test_global_map_resize__attach(skel); + if (!ASSERT_OK(err, "test_global_map_resize__attach")) + goto teardown; + + /* run the bpf program which will sum the contents of the array. + * since the array was filled with ones,verify the sum equals array_len + */ + run_prog_bss_array_sum(); + if (!ASSERT_EQ(skel->bss->sum, array_len, "sum")) + goto teardown; + +teardown: + test_global_map_resize__destroy(skel); +} + +static void global_map_resize_data_subtest(void) +{ + int err; + struct test_global_map_resize *skel; + struct bpf_map *map; + const __u32 desired_sz = sysconf(_SC_PAGE_SIZE) * 2; + size_t array_len, actual_sz; + + skel = test_global_map_resize__open(); + if (!ASSERT_OK_PTR(skel, "test_global_map_resize__open")) + goto teardown; + + /* set some initial value before resizing. + * it is expected this non-zero value will be preserved + * while resizing. + */ + skel->data_custom->my_array[0] = 1; + + /* resize map value and verify the new size */ + map = skel->maps.data_custom; + err = bpf_map__set_value_size(map, desired_sz); + if (!ASSERT_OK(err, "bpf_map__set_value_size")) + goto teardown; + if (!ASSERT_EQ(bpf_map__value_size(map), desired_sz, "resize")) + goto teardown; + + /* set the expected number of elements based on the resized array */ + array_len = (desired_sz - sizeof(skel->bss->sum)) / sizeof(skel->data_custom->my_array[0]); + if (!ASSERT_GT(array_len, 1, "array_len")) + goto teardown; + + skel->data_custom = bpf_map__initial_value(skel->maps.data_custom, &actual_sz); + if (!ASSERT_OK_PTR(skel->data_custom, "bpf_map__initial_value (ptr)")) + goto teardown; + if (!ASSERT_EQ(actual_sz, desired_sz, "bpf_map__initial_value (size)")) + goto teardown; + + /* fill the newly resized array with ones, + * skipping the first element which was previously set + */ + for (int i = 1; i < array_len; i++) + skel->data_custom->my_array[i] = 1; + + /* set global const values before loading */ + skel->rodata->pid = getpid(); + skel->rodata->bss_array_len = 1; + skel->rodata->data_array_len = array_len; + + err = test_global_map_resize__load(skel); + if (!ASSERT_OK(err, "test_global_map_resize__load")) + goto teardown; + err = test_global_map_resize__attach(skel); + if (!ASSERT_OK(err, "test_global_map_resize__attach")) + goto teardown; + + /* run the bpf program which will sum the contents of the array. + * since the array was filled with ones,verify the sum equals array_len + */ + run_prog_data_array_sum(); + if (!ASSERT_EQ(skel->bss->sum, array_len, "sum")) + goto teardown; + +teardown: + test_global_map_resize__destroy(skel); +} + +static void global_map_resize_invalid_subtest(void) +{ + int err; + struct test_global_map_resize *skel; + struct bpf_map *map; + __u32 element_sz, desired_sz; + + skel = test_global_map_resize__open(); + if (!ASSERT_OK_PTR(skel, "test_global_map_resize__open")) + return; + + /* attempt to resize a global datasec map to size + * which does NOT align with array + */ + map = skel->maps.data_custom; + if (!ASSERT_NEQ(bpf_map__btf_value_type_id(map), 0, ".data.custom initial btf")) + goto teardown; + /* set desired size a fraction of element size beyond an aligned size */ + element_sz = sizeof(skel->data_custom->my_array[0]); + desired_sz = element_sz + element_sz / 2; + /* confirm desired size does NOT align with array */ + if (!ASSERT_NEQ(desired_sz % element_sz, 0, "my_array alignment")) + goto teardown; + err = bpf_map__set_value_size(map, desired_sz); + /* confirm resize is OK but BTF info is cleared */ + if (!ASSERT_OK(err, ".data.custom bpf_map__set_value_size") || + !ASSERT_EQ(bpf_map__btf_key_type_id(map), 0, ".data.custom clear btf key") || + !ASSERT_EQ(bpf_map__btf_value_type_id(map), 0, ".data.custom clear btf val")) + goto teardown; + + /* attempt to resize a global datasec map whose only var is NOT an array */ + map = skel->maps.data_non_array; + if (!ASSERT_NEQ(bpf_map__btf_value_type_id(map), 0, ".data.non_array initial btf")) + goto teardown; + /* set desired size to arbitrary value */ + desired_sz = 1024; + err = bpf_map__set_value_size(map, desired_sz); + /* confirm resize is OK but BTF info is cleared */ + if (!ASSERT_OK(err, ".data.non_array bpf_map__set_value_size") || + !ASSERT_EQ(bpf_map__btf_key_type_id(map), 0, ".data.non_array clear btf key") || + !ASSERT_EQ(bpf_map__btf_value_type_id(map), 0, ".data.non_array clear btf val")) + goto teardown; + + /* attempt to resize a global datasec map + * whose last var is NOT an array + */ + map = skel->maps.data_array_not_last; + if (!ASSERT_NEQ(bpf_map__btf_value_type_id(map), 0, ".data.array_not_last initial btf")) + goto teardown; + /* set desired size to a multiple of element size */ + element_sz = sizeof(skel->data_array_not_last->my_array_first[0]); + desired_sz = element_sz * 8; + /* confirm desired size aligns with array */ + if (!ASSERT_EQ(desired_sz % element_sz, 0, "my_array_first alignment")) + goto teardown; + err = bpf_map__set_value_size(map, desired_sz); + /* confirm resize is OK but BTF info is cleared */ + if (!ASSERT_OK(err, ".data.array_not_last bpf_map__set_value_size") || + !ASSERT_EQ(bpf_map__btf_key_type_id(map), 0, ".data.array_not_last clear btf key") || + !ASSERT_EQ(bpf_map__btf_value_type_id(map), 0, ".data.array_not_last clear btf val")) + goto teardown; + +teardown: + test_global_map_resize__destroy(skel); +} + +void test_global_map_resize(void) +{ + if (test__start_subtest("global_map_resize_bss")) + global_map_resize_bss_subtest(); + + if (test__start_subtest("global_map_resize_data")) + global_map_resize_data_subtest(); + + if (test__start_subtest("global_map_resize_invalid")) + global_map_resize_invalid_subtest(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/module_attach.c b/tools/testing/selftests/bpf/prog_tests/module_attach.c index 7fc01ff490db..f53d658ed080 100644 --- a/tools/testing/selftests/bpf/prog_tests/module_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/module_attach.c @@ -4,6 +4,7 @@ #include <test_progs.h> #include <stdbool.h> #include "test_module_attach.skel.h" +#include "testing_helpers.h" static int duration; @@ -32,11 +33,6 @@ static int trigger_module_test_writable(int *val) return 0; } -static int delete_module(const char *name, int flags) -{ - return syscall(__NR_delete_module, name, flags); -} - void test_module_attach(void) { const int READ_SZ = 456; @@ -93,21 +89,21 @@ void test_module_attach(void) if (!ASSERT_OK_PTR(link, "attach_fentry")) goto cleanup; - ASSERT_ERR(delete_module("bpf_testmod", 0), "delete_module"); + ASSERT_ERR(unload_bpf_testmod(false), "unload_bpf_testmod"); bpf_link__destroy(link); link = bpf_program__attach(skel->progs.handle_fexit); if (!ASSERT_OK_PTR(link, "attach_fexit")) goto cleanup; - ASSERT_ERR(delete_module("bpf_testmod", 0), "delete_module"); + ASSERT_ERR(unload_bpf_testmod(false), "unload_bpf_testmod"); bpf_link__destroy(link); link = bpf_program__attach(skel->progs.kprobe_multi); if (!ASSERT_OK_PTR(link, "attach_kprobe_multi")) goto cleanup; - ASSERT_ERR(delete_module("bpf_testmod", 0), "delete_module"); + ASSERT_ERR(unload_bpf_testmod(false), "unload_bpf_testmod"); bpf_link__destroy(link); cleanup: diff --git a/tools/testing/selftests/bpf/prog_tests/netcnt.c b/tools/testing/selftests/bpf/prog_tests/netcnt.c index d3915c58d0e1..c3333edd029f 100644 --- a/tools/testing/selftests/bpf/prog_tests/netcnt.c +++ b/tools/testing/selftests/bpf/prog_tests/netcnt.c @@ -67,12 +67,12 @@ void serial_test_netcnt(void) } /* No packets should be lost */ - ASSERT_EQ(packets, 10000, "packets"); + ASSERT_GE(packets, 10000, "packets"); /* Let's check that bytes counter matches the number of packets * multiplied by the size of ipv6 ICMP packet. */ - ASSERT_EQ(bytes, packets * 104, "bytes"); + ASSERT_GE(bytes, packets * 104, "bytes"); err: if (cg_fd != -1) diff --git a/tools/testing/selftests/bpf/prog_tests/sock_destroy.c b/tools/testing/selftests/bpf/prog_tests/sock_destroy.c new file mode 100644 index 000000000000..b0583309a94e --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/sock_destroy.c @@ -0,0 +1,221 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include <bpf/bpf_endian.h> + +#include "sock_destroy_prog.skel.h" +#include "sock_destroy_prog_fail.skel.h" +#include "network_helpers.h" + +#define TEST_NS "sock_destroy_netns" + +static void start_iter_sockets(struct bpf_program *prog) +{ + struct bpf_link *link; + char buf[50] = {}; + int iter_fd, len; + + link = bpf_program__attach_iter(prog, NULL); + if (!ASSERT_OK_PTR(link, "attach_iter")) + return; + + iter_fd = bpf_iter_create(bpf_link__fd(link)); + if (!ASSERT_GE(iter_fd, 0, "create_iter")) + goto free_link; + + while ((len = read(iter_fd, buf, sizeof(buf))) > 0) + ; + ASSERT_GE(len, 0, "read"); + + close(iter_fd); + +free_link: + bpf_link__destroy(link); +} + +static void test_tcp_client(struct sock_destroy_prog *skel) +{ + int serv = -1, clien = -1, accept_serv = -1, n; + + serv = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0); + if (!ASSERT_GE(serv, 0, "start_server")) + goto cleanup; + + clien = connect_to_fd(serv, 0); + if (!ASSERT_GE(clien, 0, "connect_to_fd")) + goto cleanup; + + accept_serv = accept(serv, NULL, NULL); + if (!ASSERT_GE(accept_serv, 0, "serv accept")) + goto cleanup; + + n = send(clien, "t", 1, 0); + if (!ASSERT_EQ(n, 1, "client send")) + goto cleanup; + + /* Run iterator program that destroys connected client sockets. */ + start_iter_sockets(skel->progs.iter_tcp6_client); + + n = send(clien, "t", 1, 0); + if (!ASSERT_LT(n, 0, "client_send on destroyed socket")) + goto cleanup; + ASSERT_EQ(errno, ECONNABORTED, "error code on destroyed socket"); + +cleanup: + if (clien != -1) + close(clien); + if (accept_serv != -1) + close(accept_serv); + if (serv != -1) + close(serv); +} + +static void test_tcp_server(struct sock_destroy_prog *skel) +{ + int serv = -1, clien = -1, accept_serv = -1, n, serv_port; + + serv = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0); + if (!ASSERT_GE(serv, 0, "start_server")) + goto cleanup; + serv_port = get_socket_local_port(serv); + if (!ASSERT_GE(serv_port, 0, "get_sock_local_port")) + goto cleanup; + skel->bss->serv_port = (__be16) serv_port; + + clien = connect_to_fd(serv, 0); + if (!ASSERT_GE(clien, 0, "connect_to_fd")) + goto cleanup; + + accept_serv = accept(serv, NULL, NULL); + if (!ASSERT_GE(accept_serv, 0, "serv accept")) + goto cleanup; + + n = send(clien, "t", 1, 0); + if (!ASSERT_EQ(n, 1, "client send")) + goto cleanup; + + /* Run iterator program that destroys server sockets. */ + start_iter_sockets(skel->progs.iter_tcp6_server); + + n = send(clien, "t", 1, 0); + if (!ASSERT_LT(n, 0, "client_send on destroyed socket")) + goto cleanup; + ASSERT_EQ(errno, ECONNRESET, "error code on destroyed socket"); + +cleanup: + if (clien != -1) + close(clien); + if (accept_serv != -1) + close(accept_serv); + if (serv != -1) + close(serv); +} + +static void test_udp_client(struct sock_destroy_prog *skel) +{ + int serv = -1, clien = -1, n = 0; + + serv = start_server(AF_INET6, SOCK_DGRAM, NULL, 0, 0); + if (!ASSERT_GE(serv, 0, "start_server")) + goto cleanup; + + clien = connect_to_fd(serv, 0); + if (!ASSERT_GE(clien, 0, "connect_to_fd")) + goto cleanup; + + n = send(clien, "t", 1, 0); + if (!ASSERT_EQ(n, 1, "client send")) + goto cleanup; + + /* Run iterator program that destroys sockets. */ + start_iter_sockets(skel->progs.iter_udp6_client); + + n = send(clien, "t", 1, 0); + if (!ASSERT_LT(n, 0, "client_send on destroyed socket")) + goto cleanup; + /* UDP sockets have an overriding error code after they are disconnected, + * so we don't check for ECONNABORTED error code. + */ + +cleanup: + if (clien != -1) + close(clien); + if (serv != -1) + close(serv); +} + +static void test_udp_server(struct sock_destroy_prog *skel) +{ + int *listen_fds = NULL, n, i, serv_port; + unsigned int num_listens = 5; + char buf[1]; + + /* Start reuseport servers. */ + listen_fds = start_reuseport_server(AF_INET6, SOCK_DGRAM, + "::1", 0, 0, num_listens); + if (!ASSERT_OK_PTR(listen_fds, "start_reuseport_server")) + goto cleanup; + serv_port = get_socket_local_port(listen_fds[0]); + if (!ASSERT_GE(serv_port, 0, "get_sock_local_port")) + goto cleanup; + skel->bss->serv_port = (__be16) serv_port; + + /* Run iterator program that destroys server sockets. */ + start_iter_sockets(skel->progs.iter_udp6_server); + + for (i = 0; i < num_listens; ++i) { + n = read(listen_fds[i], buf, sizeof(buf)); + if (!ASSERT_EQ(n, -1, "read") || + !ASSERT_EQ(errno, ECONNABORTED, "error code on destroyed socket")) + break; + } + ASSERT_EQ(i, num_listens, "server socket"); + +cleanup: + free_fds(listen_fds, num_listens); +} + +void test_sock_destroy(void) +{ + struct sock_destroy_prog *skel; + struct nstoken *nstoken = NULL; + int cgroup_fd; + + skel = sock_destroy_prog__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return; + + cgroup_fd = test__join_cgroup("/sock_destroy"); + if (!ASSERT_GE(cgroup_fd, 0, "join_cgroup")) + goto cleanup; + + skel->links.sock_connect = bpf_program__attach_cgroup( + skel->progs.sock_connect, cgroup_fd); + if (!ASSERT_OK_PTR(skel->links.sock_connect, "prog_attach")) + goto cleanup; + + SYS(cleanup, "ip netns add %s", TEST_NS); + SYS(cleanup, "ip -net %s link set dev lo up", TEST_NS); + + nstoken = open_netns(TEST_NS); + if (!ASSERT_OK_PTR(nstoken, "open_netns")) + goto cleanup; + + if (test__start_subtest("tcp_client")) + test_tcp_client(skel); + if (test__start_subtest("tcp_server")) + test_tcp_server(skel); + if (test__start_subtest("udp_client")) + test_udp_client(skel); + if (test__start_subtest("udp_server")) + test_udp_server(skel); + + RUN_TESTS(sock_destroy_prog_fail); + +cleanup: + if (nstoken) + close_netns(nstoken); + SYS_NOFAIL("ip netns del " TEST_NS " &> /dev/null"); + if (cgroup_fd >= 0) + close(cgroup_fd); + sock_destroy_prog__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt.c b/tools/testing/selftests/bpf/prog_tests/sockopt.c index aa4debf62fc6..9e6a5e3ed4de 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt.c @@ -5,10 +5,15 @@ static char bpf_log_buf[4096]; static bool verbose; +#ifndef PAGE_SIZE +#define PAGE_SIZE 4096 +#endif + enum sockopt_test_error { OK = 0, DENY_LOAD, DENY_ATTACH, + EOPNOTSUPP_GETSOCKOPT, EPERM_GETSOCKOPT, EFAULT_GETSOCKOPT, EPERM_SETSOCKOPT, @@ -273,10 +278,31 @@ static struct sockopt_test { .error = EFAULT_GETSOCKOPT, }, { - .descr = "getsockopt: deny arbitrary ctx->retval", + .descr = "getsockopt: ignore >PAGE_SIZE optlen", .insns = { - /* ctx->retval = 123 */ - BPF_MOV64_IMM(BPF_REG_0, 123), + /* write 0xFF to the first optval byte */ + + /* r6 = ctx->optval */ + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, + offsetof(struct bpf_sockopt, optval)), + /* r2 = ctx->optval */ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_6), + /* r6 = ctx->optval + 1 */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1), + + /* r7 = ctx->optval_end */ + BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_1, + offsetof(struct bpf_sockopt, optval_end)), + + /* if (ctx->optval + 1 <= ctx->optval_end) { */ + BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_7, 1), + /* ctx->optval[0] = 0xF0 */ + BPF_ST_MEM(BPF_B, BPF_REG_2, 0, 0xFF), + /* } */ + + /* retval changes are ignored */ + /* ctx->retval = 5 */ + BPF_MOV64_IMM(BPF_REG_0, 5), BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, offsetof(struct bpf_sockopt, retval)), @@ -287,9 +313,11 @@ static struct sockopt_test { .attach_type = BPF_CGROUP_GETSOCKOPT, .expected_attach_type = BPF_CGROUP_GETSOCKOPT, - .get_optlen = 64, - - .error = EFAULT_GETSOCKOPT, + .get_level = 1234, + .get_optname = 5678, + .get_optval = {}, /* the changes are ignored */ + .get_optlen = PAGE_SIZE + 1, + .error = EOPNOTSUPP_GETSOCKOPT, }, { .descr = "getsockopt: support smaller ctx->optlen", @@ -649,6 +677,45 @@ static struct sockopt_test { .error = EFAULT_SETSOCKOPT, }, { + .descr = "setsockopt: ignore >PAGE_SIZE optlen", + .insns = { + /* write 0xFF to the first optval byte */ + + /* r6 = ctx->optval */ + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, + offsetof(struct bpf_sockopt, optval)), + /* r2 = ctx->optval */ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_6), + /* r6 = ctx->optval + 1 */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1), + + /* r7 = ctx->optval_end */ + BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_1, + offsetof(struct bpf_sockopt, optval_end)), + + /* if (ctx->optval + 1 <= ctx->optval_end) { */ + BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_7, 1), + /* ctx->optval[0] = 0xF0 */ + BPF_ST_MEM(BPF_B, BPF_REG_2, 0, 0xF0), + /* } */ + + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SETSOCKOPT, + .expected_attach_type = BPF_CGROUP_SETSOCKOPT, + + .set_level = SOL_IP, + .set_optname = IP_TOS, + .set_optval = {}, + .set_optlen = PAGE_SIZE + 1, + + .get_level = SOL_IP, + .get_optname = IP_TOS, + .get_optval = {}, /* the changes are ignored */ + .get_optlen = 4, + }, + { .descr = "setsockopt: allow changing ctx->optlen within bounds", .insns = { /* r6 = ctx->optval */ @@ -906,6 +973,13 @@ static int run_test(int cgroup_fd, struct sockopt_test *test) } if (test->set_optlen) { + if (test->set_optlen >= PAGE_SIZE) { + int num_pages = test->set_optlen / PAGE_SIZE; + int remainder = test->set_optlen % PAGE_SIZE; + + test->set_optlen = num_pages * sysconf(_SC_PAGESIZE) + remainder; + } + err = setsockopt(sock_fd, test->set_level, test->set_optname, test->set_optval, test->set_optlen); if (err) { @@ -921,7 +995,15 @@ static int run_test(int cgroup_fd, struct sockopt_test *test) } if (test->get_optlen) { + if (test->get_optlen >= PAGE_SIZE) { + int num_pages = test->get_optlen / PAGE_SIZE; + int remainder = test->get_optlen % PAGE_SIZE; + + test->get_optlen = num_pages * sysconf(_SC_PAGESIZE) + remainder; + } + optval = malloc(test->get_optlen); + memset(optval, 0, test->get_optlen); socklen_t optlen = test->get_optlen; socklen_t expected_get_optlen = test->get_optlen_ret ?: test->get_optlen; @@ -929,6 +1011,8 @@ static int run_test(int cgroup_fd, struct sockopt_test *test) err = getsockopt(sock_fd, test->get_level, test->get_optname, optval, &optlen); if (err) { + if (errno == EOPNOTSUPP && test->error == EOPNOTSUPP_GETSOCKOPT) + goto free_optval; if (errno == EPERM && test->error == EPERM_GETSOCKOPT) goto free_optval; if (errno == EFAULT && test->error == EFAULT_GETSOCKOPT) @@ -976,7 +1060,9 @@ void test_sockopt(void) return; for (i = 0; i < ARRAY_SIZE(tests); i++) { - test__start_subtest(tests[i].descr); + if (!test__start_subtest(tests[i].descr)) + continue; + ASSERT_OK(run_test(cgroup_fd, &tests[i]), tests[i].descr); } diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c index 60c17a8e2789..917f486db826 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c @@ -2,6 +2,8 @@ #include <test_progs.h> #include "cgroup_helpers.h" +#include "sockopt_inherit.skel.h" + #define SOL_CUSTOM 0xdeadbeef #define CUSTOM_INHERIT1 0 #define CUSTOM_INHERIT2 1 @@ -132,58 +134,30 @@ static int start_server(void) return fd; } -static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title, - const char *prog_name) -{ - enum bpf_attach_type attach_type; - enum bpf_prog_type prog_type; - struct bpf_program *prog; - int err; - - err = libbpf_prog_type_by_name(title, &prog_type, &attach_type); - if (err) { - log_err("Failed to deduct types for %s BPF program", prog_name); - return -1; - } - - prog = bpf_object__find_program_by_name(obj, prog_name); - if (!prog) { - log_err("Failed to find %s BPF program", prog_name); - return -1; - } - - err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd, - attach_type, 0); - if (err) { - log_err("Failed to attach %s BPF program", prog_name); - return -1; - } - - return 0; -} - static void run_test(int cgroup_fd) { + struct bpf_link *link_getsockopt = NULL; + struct bpf_link *link_setsockopt = NULL; int server_fd = -1, client_fd; - struct bpf_object *obj; + struct sockopt_inherit *obj; void *server_err; pthread_t tid; int err; - obj = bpf_object__open_file("sockopt_inherit.bpf.o", NULL); - if (!ASSERT_OK_PTR(obj, "obj_open")) + obj = sockopt_inherit__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) return; - err = bpf_object__load(obj); - if (!ASSERT_OK(err, "obj_load")) - goto close_bpf_object; + obj->bss->page_size = sysconf(_SC_PAGESIZE); - err = prog_attach(obj, cgroup_fd, "cgroup/getsockopt", "_getsockopt"); - if (!ASSERT_OK(err, "prog_attach _getsockopt")) + link_getsockopt = bpf_program__attach_cgroup(obj->progs._getsockopt, + cgroup_fd); + if (!ASSERT_OK_PTR(link_getsockopt, "cg-attach-getsockopt")) goto close_bpf_object; - err = prog_attach(obj, cgroup_fd, "cgroup/setsockopt", "_setsockopt"); - if (!ASSERT_OK(err, "prog_attach _setsockopt")) + link_setsockopt = bpf_program__attach_cgroup(obj->progs._setsockopt, + cgroup_fd); + if (!ASSERT_OK_PTR(link_setsockopt, "cg-attach-setsockopt")) goto close_bpf_object; server_fd = start_server(); @@ -217,7 +191,10 @@ static void run_test(int cgroup_fd) close_server_fd: close(server_fd); close_bpf_object: - bpf_object__close(obj); + bpf_link__destroy(link_getsockopt); + bpf_link__destroy(link_setsockopt); + + sockopt_inherit__destroy(obj); } void test_sockopt_inherit(void) diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c index 7f5659349011..759bbb6f8c5f 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c @@ -2,61 +2,13 @@ #include <test_progs.h> #include "cgroup_helpers.h" -static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title, const char *name) -{ - enum bpf_attach_type attach_type; - enum bpf_prog_type prog_type; - struct bpf_program *prog; - int err; - - err = libbpf_prog_type_by_name(title, &prog_type, &attach_type); - if (err) { - log_err("Failed to deduct types for %s BPF program", title); - return -1; - } - - prog = bpf_object__find_program_by_name(obj, name); - if (!prog) { - log_err("Failed to find %s BPF program", name); - return -1; - } - - err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd, - attach_type, BPF_F_ALLOW_MULTI); - if (err) { - log_err("Failed to attach %s BPF program", name); - return -1; - } - - return 0; -} +#include "sockopt_multi.skel.h" -static int prog_detach(struct bpf_object *obj, int cgroup_fd, const char *title, const char *name) -{ - enum bpf_attach_type attach_type; - enum bpf_prog_type prog_type; - struct bpf_program *prog; - int err; - - err = libbpf_prog_type_by_name(title, &prog_type, &attach_type); - if (err) - return -1; - - prog = bpf_object__find_program_by_name(obj, name); - if (!prog) - return -1; - - err = bpf_prog_detach2(bpf_program__fd(prog), cgroup_fd, - attach_type); - if (err) - return -1; - - return 0; -} - -static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, +static int run_getsockopt_test(struct sockopt_multi *obj, int cg_parent, int cg_child, int sock_fd) { + struct bpf_link *link_parent = NULL; + struct bpf_link *link_child = NULL; socklen_t optlen; __u8 buf; int err; @@ -89,8 +41,9 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, * - child: 0x80 -> 0x90 */ - err = prog_attach(obj, cg_child, "cgroup/getsockopt", "_getsockopt_child"); - if (err) + link_child = bpf_program__attach_cgroup(obj->progs._getsockopt_child, + cg_child); + if (!ASSERT_OK_PTR(link_child, "cg-attach-getsockopt_child")) goto detach; buf = 0x00; @@ -113,8 +66,9 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, * - parent: 0x90 -> 0xA0 */ - err = prog_attach(obj, cg_parent, "cgroup/getsockopt", "_getsockopt_parent"); - if (err) + link_parent = bpf_program__attach_cgroup(obj->progs._getsockopt_parent, + cg_parent); + if (!ASSERT_OK_PTR(link_parent, "cg-attach-getsockopt_parent")) goto detach; buf = 0x00; @@ -157,11 +111,8 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, * - parent: unexpected 0x40, EPERM */ - err = prog_detach(obj, cg_child, "cgroup/getsockopt", "_getsockopt_child"); - if (err) { - log_err("Failed to detach child program"); - goto detach; - } + bpf_link__destroy(link_child); + link_child = NULL; buf = 0x00; optlen = 1; @@ -198,15 +149,17 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, } detach: - prog_detach(obj, cg_child, "cgroup/getsockopt", "_getsockopt_child"); - prog_detach(obj, cg_parent, "cgroup/getsockopt", "_getsockopt_parent"); + bpf_link__destroy(link_child); + bpf_link__destroy(link_parent); return err; } -static int run_setsockopt_test(struct bpf_object *obj, int cg_parent, +static int run_setsockopt_test(struct sockopt_multi *obj, int cg_parent, int cg_child, int sock_fd) { + struct bpf_link *link_parent = NULL; + struct bpf_link *link_child = NULL; socklen_t optlen; __u8 buf; int err; @@ -236,8 +189,9 @@ static int run_setsockopt_test(struct bpf_object *obj, int cg_parent, /* Attach child program and make sure it adds 0x10. */ - err = prog_attach(obj, cg_child, "cgroup/setsockopt", "_setsockopt"); - if (err) + link_child = bpf_program__attach_cgroup(obj->progs._setsockopt, + cg_child); + if (!ASSERT_OK_PTR(link_child, "cg-attach-setsockopt_child")) goto detach; buf = 0x80; @@ -263,8 +217,9 @@ static int run_setsockopt_test(struct bpf_object *obj, int cg_parent, /* Attach parent program and make sure it adds another 0x10. */ - err = prog_attach(obj, cg_parent, "cgroup/setsockopt", "_setsockopt"); - if (err) + link_parent = bpf_program__attach_cgroup(obj->progs._setsockopt, + cg_parent); + if (!ASSERT_OK_PTR(link_parent, "cg-attach-setsockopt_parent")) goto detach; buf = 0x80; @@ -289,8 +244,8 @@ static int run_setsockopt_test(struct bpf_object *obj, int cg_parent, } detach: - prog_detach(obj, cg_child, "cgroup/setsockopt", "_setsockopt"); - prog_detach(obj, cg_parent, "cgroup/setsockopt", "_setsockopt"); + bpf_link__destroy(link_child); + bpf_link__destroy(link_parent); return err; } @@ -298,9 +253,8 @@ detach: void test_sockopt_multi(void) { int cg_parent = -1, cg_child = -1; - struct bpf_object *obj = NULL; + struct sockopt_multi *obj = NULL; int sock_fd = -1; - int err = -1; cg_parent = test__join_cgroup("/parent"); if (!ASSERT_GE(cg_parent, 0, "join_cgroup /parent")) @@ -310,13 +264,11 @@ void test_sockopt_multi(void) if (!ASSERT_GE(cg_child, 0, "join_cgroup /parent/child")) goto out; - obj = bpf_object__open_file("sockopt_multi.bpf.o", NULL); - if (!ASSERT_OK_PTR(obj, "obj_load")) + obj = sockopt_multi__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) goto out; - err = bpf_object__load(obj); - if (!ASSERT_OK(err, "obj_load")) - goto out; + obj->bss->page_size = sysconf(_SC_PAGESIZE); sock_fd = socket(AF_INET, SOCK_STREAM, 0); if (!ASSERT_GE(sock_fd, 0, "socket")) @@ -327,7 +279,7 @@ void test_sockopt_multi(void) out: close(sock_fd); - bpf_object__close(obj); + sockopt_multi__destroy(obj); close(cg_child); close(cg_parent); } diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_qos_to_cc.c b/tools/testing/selftests/bpf/prog_tests/sockopt_qos_to_cc.c index 6b53b3cb8dad..6b2d300e9fd4 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_qos_to_cc.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_qos_to_cc.c @@ -42,6 +42,8 @@ void test_sockopt_qos_to_cc(void) if (!ASSERT_OK_PTR(skel, "skel")) goto done; + skel->bss->page_size = sysconf(_SC_PAGESIZE); + sock_fd = socket(AF_INET6, SOCK_STREAM, 0); if (!ASSERT_GE(sock_fd, 0, "v6 socket open")) goto done; diff --git a/tools/testing/selftests/bpf/prog_tests/task_under_cgroup.c b/tools/testing/selftests/bpf/prog_tests/task_under_cgroup.c new file mode 100644 index 000000000000..4224727fb364 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/task_under_cgroup.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Bytedance */ + +#include <sys/syscall.h> +#include <test_progs.h> +#include <cgroup_helpers.h> +#include "test_task_under_cgroup.skel.h" + +#define FOO "/foo" + +void test_task_under_cgroup(void) +{ + struct test_task_under_cgroup *skel; + int ret, foo; + pid_t pid; + + foo = test__join_cgroup(FOO); + if (!ASSERT_OK(foo < 0, "cgroup_join_foo")) + return; + + skel = test_task_under_cgroup__open(); + if (!ASSERT_OK_PTR(skel, "test_task_under_cgroup__open")) + goto cleanup; + + skel->rodata->local_pid = getpid(); + skel->bss->remote_pid = getpid(); + skel->rodata->cgid = get_cgroup_id(FOO); + + ret = test_task_under_cgroup__load(skel); + if (!ASSERT_OK(ret, "test_task_under_cgroup__load")) + goto cleanup; + + ret = test_task_under_cgroup__attach(skel); + if (!ASSERT_OK(ret, "test_task_under_cgroup__attach")) + goto cleanup; + + pid = fork(); + if (pid == 0) + exit(0); + + ret = (pid == -1); + if (ASSERT_OK(ret, "fork process")) + wait(NULL); + + test_task_under_cgroup__detach(skel); + + ASSERT_NEQ(skel->bss->remote_pid, skel->rodata->local_pid, + "test task_under_cgroup"); + +cleanup: + test_task_under_cgroup__destroy(skel); + close(foo); +} diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index 2497716ee379..531621adef42 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -55,6 +55,7 @@ #include "verifier_spill_fill.skel.h" #include "verifier_spin_lock.skel.h" #include "verifier_stack_ptr.skel.h" +#include "verifier_subprog_precision.skel.h" #include "verifier_subreg.skel.h" #include "verifier_uninit.skel.h" #include "verifier_unpriv.skel.h" @@ -154,6 +155,7 @@ void test_verifier_sock(void) { RUN(verifier_sock); } void test_verifier_spill_fill(void) { RUN(verifier_spill_fill); } void test_verifier_spin_lock(void) { RUN(verifier_spin_lock); } void test_verifier_stack_ptr(void) { RUN(verifier_stack_ptr); } +void test_verifier_subprog_precision(void) { RUN(verifier_subprog_precision); } void test_verifier_subreg(void) { RUN(verifier_subreg); } void test_verifier_uninit(void) { RUN(verifier_uninit); } void test_verifier_unpriv(void) { RUN(verifier_unpriv); } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c index d19f79048ff6..c3b45745cbcc 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c @@ -18,6 +18,7 @@ #include <linux/if_bonding.h> #include <linux/limits.h> #include <linux/udp.h> +#include <uapi/linux/netdev.h> #include "xdp_dummy.skel.h" #include "xdp_redirect_multi_kern.skel.h" @@ -492,6 +493,123 @@ out: system("ip link del bond_nest2"); } +static void test_xdp_bonding_features(struct skeletons *skeletons) +{ + LIBBPF_OPTS(bpf_xdp_query_opts, query_opts); + int bond_idx, veth1_idx, err; + struct bpf_link *link = NULL; + + if (!ASSERT_OK(system("ip link add bond type bond"), "add bond")) + goto out; + + bond_idx = if_nametoindex("bond"); + if (!ASSERT_GE(bond_idx, 0, "if_nametoindex bond")) + goto out; + + /* query default xdp-feature for bond device */ + err = bpf_xdp_query(bond_idx, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "bond bpf_xdp_query")) + goto out; + + if (!ASSERT_EQ(query_opts.feature_flags, NETDEV_XDP_ACT_MASK, + "bond query_opts.feature_flags")) + goto out; + + if (!ASSERT_OK(system("ip link add veth0 type veth peer name veth1"), + "add veth{0,1} pair")) + goto out; + + if (!ASSERT_OK(system("ip link add veth2 type veth peer name veth3"), + "add veth{2,3} pair")) + goto out; + + if (!ASSERT_OK(system("ip link set veth0 master bond"), + "add veth0 to master bond")) + goto out; + + /* xdp-feature for bond device should be obtained from the single slave + * device (veth0) + */ + err = bpf_xdp_query(bond_idx, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "bond bpf_xdp_query")) + goto out; + + if (!ASSERT_EQ(query_opts.feature_flags, + NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_RX_SG, + "bond query_opts.feature_flags")) + goto out; + + veth1_idx = if_nametoindex("veth1"); + if (!ASSERT_GE(veth1_idx, 0, "if_nametoindex veth1")) + goto out; + + link = bpf_program__attach_xdp(skeletons->xdp_dummy->progs.xdp_dummy_prog, + veth1_idx); + if (!ASSERT_OK_PTR(link, "attach program to veth1")) + goto out; + + /* xdp-feature for veth0 are changed */ + err = bpf_xdp_query(bond_idx, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "bond bpf_xdp_query")) + goto out; + + if (!ASSERT_EQ(query_opts.feature_flags, + NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_RX_SG | NETDEV_XDP_ACT_NDO_XMIT | + NETDEV_XDP_ACT_NDO_XMIT_SG, + "bond query_opts.feature_flags")) + goto out; + + if (!ASSERT_OK(system("ip link set veth2 master bond"), + "add veth2 to master bond")) + goto out; + + err = bpf_xdp_query(bond_idx, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "bond bpf_xdp_query")) + goto out; + + /* xdp-feature for bond device should be set to the most restrict + * value obtained from attached slave devices (veth0 and veth2) + */ + if (!ASSERT_EQ(query_opts.feature_flags, + NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_RX_SG, + "bond query_opts.feature_flags")) + goto out; + + if (!ASSERT_OK(system("ip link set veth2 nomaster"), + "del veth2 to master bond")) + goto out; + + err = bpf_xdp_query(bond_idx, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "bond bpf_xdp_query")) + goto out; + + if (!ASSERT_EQ(query_opts.feature_flags, + NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_RX_SG | NETDEV_XDP_ACT_NDO_XMIT | + NETDEV_XDP_ACT_NDO_XMIT_SG, + "bond query_opts.feature_flags")) + goto out; + + if (!ASSERT_OK(system("ip link set veth0 nomaster"), + "del veth0 to master bond")) + goto out; + + err = bpf_xdp_query(bond_idx, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "bond bpf_xdp_query")) + goto out; + + ASSERT_EQ(query_opts.feature_flags, NETDEV_XDP_ACT_MASK, + "bond query_opts.feature_flags"); +out: + bpf_link__destroy(link); + system("ip link del veth0"); + system("ip link del veth2"); + system("ip link del bond"); +} + static int libbpf_debug_print(enum libbpf_print_level level, const char *format, va_list args) { @@ -546,6 +664,9 @@ void serial_test_xdp_bonding(void) if (test__start_subtest("xdp_bonding_nested")) test_xdp_bonding_nested(&skeletons); + if (test__start_subtest("xdp_bonding_features")) + test_xdp_bonding_features(&skeletons); + for (i = 0; i < ARRAY_SIZE(bond_test_cases); i++) { struct bond_test_case *test_case = &bond_test_cases[i]; diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h index d3c1217ba79a..38a57a2e70db 100644 --- a/tools/testing/selftests/bpf/progs/bpf_misc.h +++ b/tools/testing/selftests/bpf/progs/bpf_misc.h @@ -86,6 +86,10 @@ #define POINTER_VALUE 0xcafe4all #define TEST_DATA_LEN 64 +#ifndef __used +#define __used __attribute__((used)) +#endif + #if defined(__TARGET_ARCH_x86) #define SYSCALL_WRAPPER 1 #define SYS_PREFIX "__x64_" diff --git a/tools/testing/selftests/bpf/progs/cb_refs.c b/tools/testing/selftests/bpf/progs/cb_refs.c index 50f95ec61165..76d661b20e87 100644 --- a/tools/testing/selftests/bpf/progs/cb_refs.c +++ b/tools/testing/selftests/bpf/progs/cb_refs.c @@ -2,6 +2,7 @@ #include <vmlinux.h> #include <bpf/bpf_tracing.h> #include <bpf/bpf_helpers.h> +#include "../bpf_testmod/bpf_testmod_kfunc.h" struct map_value { struct prog_test_ref_kfunc __kptr *ptr; @@ -14,9 +15,6 @@ struct { __uint(max_entries, 16); } array_map SEC(".maps"); -extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym; -extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; - static __noinline int cb1(void *map, void *key, void *value, void *ctx) { void *p = *(void **)ctx; diff --git a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c index b2a409e6382a..932b8ecd4ae3 100644 --- a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c +++ b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c @@ -12,6 +12,7 @@ __u32 invocations = 0; __u32 assertion_error = 0; __u32 retval_value = 0; __u32 ctx_retval_value = 0; +__u32 page_size = 0; SEC("cgroup/getsockopt") int get_retval(struct bpf_sockopt *ctx) @@ -20,6 +21,10 @@ int get_retval(struct bpf_sockopt *ctx) ctx_retval_value = ctx->retval; __sync_fetch_and_add(&invocations, 1); + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } @@ -31,6 +36,10 @@ int set_eisconn(struct bpf_sockopt *ctx) if (bpf_set_retval(-EISCONN)) assertion_error = 1; + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } @@ -41,5 +50,9 @@ int clear_retval(struct bpf_sockopt *ctx) ctx->retval = 0; + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } diff --git a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c index d6e5903e06ba..b7fa8804e19d 100644 --- a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c +++ b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c @@ -11,6 +11,7 @@ __u32 invocations = 0; __u32 assertion_error = 0; __u32 retval_value = 0; +__u32 page_size = 0; SEC("cgroup/setsockopt") int get_retval(struct bpf_sockopt *ctx) @@ -18,6 +19,10 @@ int get_retval(struct bpf_sockopt *ctx) retval_value = bpf_get_retval(); __sync_fetch_and_add(&invocations, 1); + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } @@ -29,6 +34,10 @@ int set_eunatch(struct bpf_sockopt *ctx) if (bpf_set_retval(-EUNATCH)) assertion_error = 1; + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 0; } @@ -40,6 +49,10 @@ int set_eisconn(struct bpf_sockopt *ctx) if (bpf_set_retval(-EISCONN)) assertion_error = 1; + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 0; } @@ -48,5 +61,9 @@ int legacy_eperm(struct bpf_sockopt *ctx) { __sync_fetch_and_add(&invocations, 1); + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 0; } diff --git a/tools/testing/selftests/bpf/progs/dynptr_fail.c b/tools/testing/selftests/bpf/progs/dynptr_fail.c index 759eb5c245cd..7ce7e827d5f0 100644 --- a/tools/testing/selftests/bpf/progs/dynptr_fail.c +++ b/tools/testing/selftests/bpf/progs/dynptr_fail.c @@ -3,6 +3,7 @@ #include <errno.h> #include <string.h> +#include <stdbool.h> #include <linux/bpf.h> #include <bpf/bpf_helpers.h> #include <linux/if_ether.h> @@ -1378,3 +1379,310 @@ int invalid_slice_rdwr_rdonly(struct __sk_buff *skb) return 0; } + +/* bpf_dynptr_adjust can only be called on initialized dynptrs */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #1") +int dynptr_adjust_invalid(void *ctx) +{ + struct bpf_dynptr ptr; + + /* this should fail */ + bpf_dynptr_adjust(&ptr, 1, 2); + + return 0; +} + +/* bpf_dynptr_is_null can only be called on initialized dynptrs */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #1") +int dynptr_is_null_invalid(void *ctx) +{ + struct bpf_dynptr ptr; + + /* this should fail */ + bpf_dynptr_is_null(&ptr); + + return 0; +} + +/* bpf_dynptr_is_rdonly can only be called on initialized dynptrs */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #1") +int dynptr_is_rdonly_invalid(void *ctx) +{ + struct bpf_dynptr ptr; + + /* this should fail */ + bpf_dynptr_is_rdonly(&ptr); + + return 0; +} + +/* bpf_dynptr_size can only be called on initialized dynptrs */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #1") +int dynptr_size_invalid(void *ctx) +{ + struct bpf_dynptr ptr; + + /* this should fail */ + bpf_dynptr_size(&ptr); + + return 0; +} + +/* Only initialized dynptrs can be cloned */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #1") +int clone_invalid1(void *ctx) +{ + struct bpf_dynptr ptr1; + struct bpf_dynptr ptr2; + + /* this should fail */ + bpf_dynptr_clone(&ptr1, &ptr2); + + return 0; +} + +/* Can't overwrite an existing dynptr when cloning */ +SEC("?xdp") +__failure __msg("cannot overwrite referenced dynptr") +int clone_invalid2(struct xdp_md *xdp) +{ + struct bpf_dynptr ptr1; + struct bpf_dynptr clone; + + bpf_dynptr_from_xdp(xdp, 0, &ptr1); + + bpf_ringbuf_reserve_dynptr(&ringbuf, 64, 0, &clone); + + /* this should fail */ + bpf_dynptr_clone(&ptr1, &clone); + + bpf_ringbuf_submit_dynptr(&clone, 0); + + return 0; +} + +/* Invalidating a dynptr should invalidate its clones */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #3") +int clone_invalidate1(void *ctx) +{ + struct bpf_dynptr clone; + struct bpf_dynptr ptr; + char read_data[64]; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone); + + bpf_ringbuf_submit_dynptr(&ptr, 0); + + /* this should fail */ + bpf_dynptr_read(read_data, sizeof(read_data), &clone, 0, 0); + + return 0; +} + +/* Invalidating a dynptr should invalidate its parent */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #3") +int clone_invalidate2(void *ctx) +{ + struct bpf_dynptr ptr; + struct bpf_dynptr clone; + char read_data[64]; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone); + + bpf_ringbuf_submit_dynptr(&clone, 0); + + /* this should fail */ + bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0, 0); + + return 0; +} + +/* Invalidating a dynptr should invalidate its siblings */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #3") +int clone_invalidate3(void *ctx) +{ + struct bpf_dynptr ptr; + struct bpf_dynptr clone1; + struct bpf_dynptr clone2; + char read_data[64]; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone1); + + bpf_dynptr_clone(&ptr, &clone2); + + bpf_ringbuf_submit_dynptr(&clone2, 0); + + /* this should fail */ + bpf_dynptr_read(read_data, sizeof(read_data), &clone1, 0, 0); + + return 0; +} + +/* Invalidating a dynptr should invalidate any data slices + * of its clones + */ +SEC("?raw_tp") +__failure __msg("invalid mem access 'scalar'") +int clone_invalidate4(void *ctx) +{ + struct bpf_dynptr ptr; + struct bpf_dynptr clone; + int *data; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone); + data = bpf_dynptr_data(&clone, 0, sizeof(val)); + if (!data) + return 0; + + bpf_ringbuf_submit_dynptr(&ptr, 0); + + /* this should fail */ + *data = 123; + + return 0; +} + +/* Invalidating a dynptr should invalidate any data slices + * of its parent + */ +SEC("?raw_tp") +__failure __msg("invalid mem access 'scalar'") +int clone_invalidate5(void *ctx) +{ + struct bpf_dynptr ptr; + struct bpf_dynptr clone; + int *data; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + data = bpf_dynptr_data(&ptr, 0, sizeof(val)); + if (!data) + return 0; + + bpf_dynptr_clone(&ptr, &clone); + + bpf_ringbuf_submit_dynptr(&clone, 0); + + /* this should fail */ + *data = 123; + + return 0; +} + +/* Invalidating a dynptr should invalidate any data slices + * of its sibling + */ +SEC("?raw_tp") +__failure __msg("invalid mem access 'scalar'") +int clone_invalidate6(void *ctx) +{ + struct bpf_dynptr ptr; + struct bpf_dynptr clone1; + struct bpf_dynptr clone2; + int *data; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone1); + + bpf_dynptr_clone(&ptr, &clone2); + + data = bpf_dynptr_data(&clone1, 0, sizeof(val)); + if (!data) + return 0; + + bpf_ringbuf_submit_dynptr(&clone2, 0); + + /* this should fail */ + *data = 123; + + return 0; +} + +/* A skb clone's data slices should be invalid anytime packet data changes */ +SEC("?tc") +__failure __msg("invalid mem access 'scalar'") +int clone_skb_packet_data(struct __sk_buff *skb) +{ + char buffer[sizeof(__u32)] = {}; + struct bpf_dynptr clone; + struct bpf_dynptr ptr; + __u32 *data; + + bpf_dynptr_from_skb(skb, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone); + data = bpf_dynptr_slice_rdwr(&clone, 0, buffer, sizeof(buffer)); + if (!data) + return XDP_DROP; + + if (bpf_skb_pull_data(skb, skb->len)) + return SK_DROP; + + /* this should fail */ + *data = 123; + + return 0; +} + +/* A xdp clone's data slices should be invalid anytime packet data changes */ +SEC("?xdp") +__failure __msg("invalid mem access 'scalar'") +int clone_xdp_packet_data(struct xdp_md *xdp) +{ + char buffer[sizeof(__u32)] = {}; + struct bpf_dynptr clone; + struct bpf_dynptr ptr; + struct ethhdr *hdr; + __u32 *data; + + bpf_dynptr_from_xdp(xdp, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone); + data = bpf_dynptr_slice_rdwr(&clone, 0, buffer, sizeof(buffer)); + if (!data) + return XDP_DROP; + + if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(*hdr))) + return XDP_DROP; + + /* this should fail */ + *data = 123; + + return 0; +} + +/* Buffers that are provided must be sufficiently long */ +SEC("?cgroup_skb/egress") +__failure __msg("memory, len pair leads to invalid memory access") +int test_dynptr_skb_small_buff(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr; + char buffer[8] = {}; + __u64 *data; + + if (bpf_dynptr_from_skb(skb, 0, &ptr)) { + err = 1; + return 1; + } + + /* This may return NULL. SKB may require a buffer */ + data = bpf_dynptr_slice(&ptr, 0, buffer, 9); + + return !!data; +} diff --git a/tools/testing/selftests/bpf/progs/dynptr_success.c b/tools/testing/selftests/bpf/progs/dynptr_success.c index b2fa6c47ecc0..5985920d162e 100644 --- a/tools/testing/selftests/bpf/progs/dynptr_success.c +++ b/tools/testing/selftests/bpf/progs/dynptr_success.c @@ -2,6 +2,7 @@ /* Copyright (c) 2022 Facebook */ #include <string.h> +#include <stdbool.h> #include <linux/bpf.h> #include <bpf/bpf_helpers.h> #include "bpf_misc.h" @@ -207,3 +208,339 @@ int test_dynptr_skb_data(struct __sk_buff *skb) return 1; } + +SEC("tp/syscalls/sys_enter_nanosleep") +int test_adjust(void *ctx) +{ + struct bpf_dynptr ptr; + __u32 bytes = 64; + __u32 off = 10; + __u32 trim = 15; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + err = bpf_ringbuf_reserve_dynptr(&ringbuf, bytes, 0, &ptr); + if (err) { + err = 1; + goto done; + } + + if (bpf_dynptr_size(&ptr) != bytes) { + err = 2; + goto done; + } + + /* Advance the dynptr by off */ + err = bpf_dynptr_adjust(&ptr, off, bpf_dynptr_size(&ptr)); + if (err) { + err = 3; + goto done; + } + + if (bpf_dynptr_size(&ptr) != bytes - off) { + err = 4; + goto done; + } + + /* Trim the dynptr */ + err = bpf_dynptr_adjust(&ptr, off, 15); + if (err) { + err = 5; + goto done; + } + + /* Check that the size was adjusted correctly */ + if (bpf_dynptr_size(&ptr) != trim - off) { + err = 6; + goto done; + } + +done: + bpf_ringbuf_discard_dynptr(&ptr, 0); + return 0; +} + +SEC("tp/syscalls/sys_enter_nanosleep") +int test_adjust_err(void *ctx) +{ + char write_data[45] = "hello there, world!!"; + struct bpf_dynptr ptr; + __u32 size = 64; + __u32 off = 20; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + if (bpf_ringbuf_reserve_dynptr(&ringbuf, size, 0, &ptr)) { + err = 1; + goto done; + } + + /* Check that start can't be greater than end */ + if (bpf_dynptr_adjust(&ptr, 5, 1) != -EINVAL) { + err = 2; + goto done; + } + + /* Check that start can't be greater than size */ + if (bpf_dynptr_adjust(&ptr, size + 1, size + 1) != -ERANGE) { + err = 3; + goto done; + } + + /* Check that end can't be greater than size */ + if (bpf_dynptr_adjust(&ptr, 0, size + 1) != -ERANGE) { + err = 4; + goto done; + } + + if (bpf_dynptr_adjust(&ptr, off, size)) { + err = 5; + goto done; + } + + /* Check that you can't write more bytes than available into the dynptr + * after you've adjusted it + */ + if (bpf_dynptr_write(&ptr, 0, &write_data, sizeof(write_data), 0) != -E2BIG) { + err = 6; + goto done; + } + + /* Check that even after adjusting, submitting/discarding + * a ringbuf dynptr works + */ + bpf_ringbuf_submit_dynptr(&ptr, 0); + return 0; + +done: + bpf_ringbuf_discard_dynptr(&ptr, 0); + return 0; +} + +SEC("tp/syscalls/sys_enter_nanosleep") +int test_zero_size_dynptr(void *ctx) +{ + char write_data = 'x', read_data; + struct bpf_dynptr ptr; + __u32 size = 64; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + if (bpf_ringbuf_reserve_dynptr(&ringbuf, size, 0, &ptr)) { + err = 1; + goto done; + } + + /* After this, the dynptr has a size of 0 */ + if (bpf_dynptr_adjust(&ptr, size, size)) { + err = 2; + goto done; + } + + /* Test that reading + writing non-zero bytes is not ok */ + if (bpf_dynptr_read(&read_data, sizeof(read_data), &ptr, 0, 0) != -E2BIG) { + err = 3; + goto done; + } + + if (bpf_dynptr_write(&ptr, 0, &write_data, sizeof(write_data), 0) != -E2BIG) { + err = 4; + goto done; + } + + /* Test that reading + writing 0 bytes from a 0-size dynptr is ok */ + if (bpf_dynptr_read(&read_data, 0, &ptr, 0, 0)) { + err = 5; + goto done; + } + + if (bpf_dynptr_write(&ptr, 0, &write_data, 0, 0)) { + err = 6; + goto done; + } + + err = 0; + +done: + bpf_ringbuf_discard_dynptr(&ptr, 0); + return 0; +} + +SEC("tp/syscalls/sys_enter_nanosleep") +int test_dynptr_is_null(void *ctx) +{ + struct bpf_dynptr ptr1; + struct bpf_dynptr ptr2; + __u64 size = 4; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + /* Pass in invalid flags, get back an invalid dynptr */ + if (bpf_ringbuf_reserve_dynptr(&ringbuf, size, 123, &ptr1) != -EINVAL) { + err = 1; + goto exit_early; + } + + /* Test that the invalid dynptr is null */ + if (!bpf_dynptr_is_null(&ptr1)) { + err = 2; + goto exit_early; + } + + /* Get a valid dynptr */ + if (bpf_ringbuf_reserve_dynptr(&ringbuf, size, 0, &ptr2)) { + err = 3; + goto exit; + } + + /* Test that the valid dynptr is not null */ + if (bpf_dynptr_is_null(&ptr2)) { + err = 4; + goto exit; + } + +exit: + bpf_ringbuf_discard_dynptr(&ptr2, 0); +exit_early: + bpf_ringbuf_discard_dynptr(&ptr1, 0); + return 0; +} + +SEC("cgroup_skb/egress") +int test_dynptr_is_rdonly(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr1; + struct bpf_dynptr ptr2; + struct bpf_dynptr ptr3; + + /* Pass in invalid flags, get back an invalid dynptr */ + if (bpf_dynptr_from_skb(skb, 123, &ptr1) != -EINVAL) { + err = 1; + return 0; + } + + /* Test that an invalid dynptr is_rdonly returns false */ + if (bpf_dynptr_is_rdonly(&ptr1)) { + err = 2; + return 0; + } + + /* Get a read-only dynptr */ + if (bpf_dynptr_from_skb(skb, 0, &ptr2)) { + err = 3; + return 0; + } + + /* Test that the dynptr is read-only */ + if (!bpf_dynptr_is_rdonly(&ptr2)) { + err = 4; + return 0; + } + + /* Get a read-writeable dynptr */ + if (bpf_ringbuf_reserve_dynptr(&ringbuf, 64, 0, &ptr3)) { + err = 5; + goto done; + } + + /* Test that the dynptr is read-only */ + if (bpf_dynptr_is_rdonly(&ptr3)) { + err = 6; + goto done; + } + +done: + bpf_ringbuf_discard_dynptr(&ptr3, 0); + return 0; +} + +SEC("cgroup_skb/egress") +int test_dynptr_clone(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr1; + struct bpf_dynptr ptr2; + __u32 off = 2, size; + + /* Get a dynptr */ + if (bpf_dynptr_from_skb(skb, 0, &ptr1)) { + err = 1; + return 0; + } + + if (bpf_dynptr_adjust(&ptr1, off, bpf_dynptr_size(&ptr1))) { + err = 2; + return 0; + } + + /* Clone the dynptr */ + if (bpf_dynptr_clone(&ptr1, &ptr2)) { + err = 3; + return 0; + } + + size = bpf_dynptr_size(&ptr1); + + /* Check that the clone has the same size and rd-only */ + if (bpf_dynptr_size(&ptr2) != size) { + err = 4; + return 0; + } + + if (bpf_dynptr_is_rdonly(&ptr2) != bpf_dynptr_is_rdonly(&ptr1)) { + err = 5; + return 0; + } + + /* Advance and trim the original dynptr */ + bpf_dynptr_adjust(&ptr1, 5, 5); + + /* Check that only original dynptr was affected, and the clone wasn't */ + if (bpf_dynptr_size(&ptr2) != size) { + err = 6; + return 0; + } + + return 0; +} + +SEC("?cgroup_skb/egress") +int test_dynptr_skb_no_buff(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr; + __u64 *data; + + if (bpf_dynptr_from_skb(skb, 0, &ptr)) { + err = 1; + return 1; + } + + /* This may return NULL. SKB may require a buffer */ + data = bpf_dynptr_slice(&ptr, 0, NULL, 1); + + return !!data; +} + +SEC("?cgroup_skb/egress") +int test_dynptr_skb_strcmp(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr; + char *data; + + if (bpf_dynptr_from_skb(skb, 0, &ptr)) { + err = 1; + return 1; + } + + /* This may return NULL. SKB may require a buffer */ + data = bpf_dynptr_slice(&ptr, 0, NULL, 10); + if (data) { + bpf_strncmp(data, 10, "foo"); + return 1; + } + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c index be16143ae292..6b9b3c56f009 100644 --- a/tools/testing/selftests/bpf/progs/iters.c +++ b/tools/testing/selftests/bpf/progs/iters.c @@ -651,29 +651,25 @@ int iter_stack_array_loop(const void *ctx) return sum; } -#define ARR_SZ 16 - -static __noinline void fill(struct bpf_iter_num *it, int *arr, int mul) +static __noinline void fill(struct bpf_iter_num *it, int *arr, __u32 n, int mul) { - int *t; - __u64 i; + int *t, i; while ((t = bpf_iter_num_next(it))) { i = *t; - if (i >= ARR_SZ) + if (i >= n) break; arr[i] = i * mul; } } -static __noinline int sum(struct bpf_iter_num *it, int *arr) +static __noinline int sum(struct bpf_iter_num *it, int *arr, __u32 n) { - int *t, sum = 0;; - __u64 i; + int *t, i, sum = 0;; while ((t = bpf_iter_num_next(it))) { i = *t; - if (i >= ARR_SZ) + if (i >= n) break; sum += arr[i]; } @@ -685,7 +681,7 @@ SEC("raw_tp") __success int iter_pass_iter_ptr_to_subprog(const void *ctx) { - int arr1[ARR_SZ], arr2[ARR_SZ]; + int arr1[16], arr2[32]; struct bpf_iter_num it; int n, sum1, sum2; @@ -694,25 +690,25 @@ int iter_pass_iter_ptr_to_subprog(const void *ctx) /* fill arr1 */ n = ARRAY_SIZE(arr1); bpf_iter_num_new(&it, 0, n); - fill(&it, arr1, 2); + fill(&it, arr1, n, 2); bpf_iter_num_destroy(&it); /* fill arr2 */ n = ARRAY_SIZE(arr2); bpf_iter_num_new(&it, 0, n); - fill(&it, arr2, 10); + fill(&it, arr2, n, 10); bpf_iter_num_destroy(&it); /* sum arr1 */ n = ARRAY_SIZE(arr1); bpf_iter_num_new(&it, 0, n); - sum1 = sum(&it, arr1); + sum1 = sum(&it, arr1, n); bpf_iter_num_destroy(&it); /* sum arr2 */ n = ARRAY_SIZE(arr2); bpf_iter_num_new(&it, 0, n); - sum2 = sum(&it, arr2); + sum2 = sum(&it, arr2, n); bpf_iter_num_destroy(&it); bpf_printk("sum1=%d, sum2=%d", sum1, sum2); diff --git a/tools/testing/selftests/bpf/progs/jit_probe_mem.c b/tools/testing/selftests/bpf/progs/jit_probe_mem.c index 13f00ca2ed0a..f9789e668297 100644 --- a/tools/testing/selftests/bpf/progs/jit_probe_mem.c +++ b/tools/testing/selftests/bpf/progs/jit_probe_mem.c @@ -3,13 +3,11 @@ #include <vmlinux.h> #include <bpf/bpf_tracing.h> #include <bpf/bpf_helpers.h> +#include "../bpf_testmod/bpf_testmod_kfunc.h" static struct prog_test_ref_kfunc __kptr *v; long total_sum = -1; -extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym; -extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; - SEC("tc") int test_jit_probe_mem(struct __sk_buff *ctx) { diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_destructive.c b/tools/testing/selftests/bpf/progs/kfunc_call_destructive.c index 767472bc5a97..7632d9ecb253 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_destructive.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_destructive.c @@ -1,8 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <vmlinux.h> #include <bpf/bpf_helpers.h> - -extern void bpf_kfunc_call_test_destructive(void) __ksym; +#include "../bpf_testmod/bpf_testmod_kfunc.h" SEC("tc") int kfunc_destructive_test(void) diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_fail.c b/tools/testing/selftests/bpf/progs/kfunc_call_fail.c index b98313d391c6..4b0b7b79cdfb 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_fail.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_fail.c @@ -2,14 +2,7 @@ /* Copyright (c) 2021 Facebook */ #include <vmlinux.h> #include <bpf/bpf_helpers.h> - -extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym; -extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; -extern void bpf_kfunc_call_test_mem_len_pass1(void *mem, int len) __ksym; -extern int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p, const int rdwr_buf_size) __ksym; -extern int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) __ksym; -extern int *bpf_kfunc_call_test_acq_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) __ksym; -extern void bpf_kfunc_call_int_mem_release(int *p) __ksym; +#include "../bpf_testmod/bpf_testmod_kfunc.h" struct syscall_test_args { __u8 data[16]; diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_race.c b/tools/testing/selftests/bpf/progs/kfunc_call_race.c index 4e8fed75a4e0..d532af07decf 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_race.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_race.c @@ -1,8 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <vmlinux.h> #include <bpf/bpf_helpers.h> - -extern void bpf_testmod_test_mod_kfunc(int i) __ksym; +#include "../bpf_testmod/bpf_testmod_kfunc.h" SEC("tc") int kfunc_call_fail(struct __sk_buff *ctx) diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test.c b/tools/testing/selftests/bpf/progs/kfunc_call_test.c index 7daa8f5720b9..cf68d1e48a0f 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_test.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_test.c @@ -2,22 +2,7 @@ /* Copyright (c) 2021 Facebook */ #include <vmlinux.h> #include <bpf/bpf_helpers.h> - -extern long bpf_kfunc_call_test4(signed char a, short b, int c, long d) __ksym; -extern int bpf_kfunc_call_test2(struct sock *sk, __u32 a, __u32 b) __ksym; -extern __u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b, - __u32 c, __u64 d) __ksym; - -extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym; -extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; -extern void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb) __ksym; -extern void bpf_kfunc_call_test_pass1(struct prog_test_pass1 *p) __ksym; -extern void bpf_kfunc_call_test_pass2(struct prog_test_pass2 *p) __ksym; -extern void bpf_kfunc_call_test_mem_len_pass1(void *mem, int len) __ksym; -extern void bpf_kfunc_call_test_mem_len_fail2(__u64 *mem, int len) __ksym; -extern int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p, const int rdwr_buf_size) __ksym; -extern int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) __ksym; -extern u32 bpf_kfunc_call_test_static_unused_arg(u32 arg, u32 unused) __ksym; +#include "../bpf_testmod/bpf_testmod_kfunc.h" SEC("tc") int kfunc_call_test4(struct __sk_buff *skb) diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c index c1fdecabeabf..2380c75e74ce 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c @@ -1,13 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2021 Facebook */ -#include <linux/bpf.h> -#include <bpf/bpf_helpers.h> -#include "bpf_tcp_helpers.h" +#include "../bpf_testmod/bpf_testmod_kfunc.h" extern const int bpf_prog_active __ksym; -extern __u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b, - __u32 c, __u64 d) __ksym; -extern struct sock *bpf_kfunc_call_test3(struct sock *sk) __ksym; int active_res = -1; int sk_state_res = -1; @@ -28,7 +23,7 @@ int __noinline f1(struct __sk_buff *skb) if (active) active_res = *active; - sk_state_res = bpf_kfunc_call_test3((struct sock *)sk)->sk_state; + sk_state_res = bpf_kfunc_call_test3((struct sock *)sk)->__sk_common.skc_state; return (__u32)bpf_kfunc_call_test1((struct sock *)sk, 1, 2, 3, 4); } diff --git a/tools/testing/selftests/bpf/progs/local_kptr_stash.c b/tools/testing/selftests/bpf/progs/local_kptr_stash.c index 0ef286da092b..06838083079c 100644 --- a/tools/testing/selftests/bpf/progs/local_kptr_stash.c +++ b/tools/testing/selftests/bpf/progs/local_kptr_stash.c @@ -5,7 +5,8 @@ #include <bpf/bpf_tracing.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_core_read.h> -#include "bpf_experimental.h" +#include "../bpf_experimental.h" +#include "../bpf_testmod/bpf_testmod_kfunc.h" struct node_data { long key; @@ -32,8 +33,6 @@ struct map_value { */ struct node_data *just_here_because_btf_bug; -extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; - struct { __uint(type, BPF_MAP_TYPE_ARRAY); __type(key, int); diff --git a/tools/testing/selftests/bpf/progs/map_kptr.c b/tools/testing/selftests/bpf/progs/map_kptr.c index d7150041e5d1..da30f0d59364 100644 --- a/tools/testing/selftests/bpf/progs/map_kptr.c +++ b/tools/testing/selftests/bpf/progs/map_kptr.c @@ -2,6 +2,7 @@ #include <vmlinux.h> #include <bpf/bpf_tracing.h> #include <bpf/bpf_helpers.h> +#include "../bpf_testmod/bpf_testmod_kfunc.h" struct map_value { struct prog_test_ref_kfunc __kptr_untrusted *unref_ptr; @@ -114,10 +115,6 @@ DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_HASH_OF_MAPS, hash_map, hash_of_hash_maps); DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_HASH_OF_MAPS, hash_malloc_map, hash_of_hash_malloc_maps); DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_HASH_OF_MAPS, lru_hash_map, hash_of_lru_hash_maps); -extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym; -extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; -void bpf_kfunc_call_test_ref(struct prog_test_ref_kfunc *p) __ksym; - #define WRITE_ONCE(x, val) ((*(volatile typeof(x) *) &(x)) = (val)) static void test_kptr_unref(struct map_value *v) diff --git a/tools/testing/selftests/bpf/progs/map_kptr_fail.c b/tools/testing/selftests/bpf/progs/map_kptr_fail.c index da8c724f839b..450bb373b179 100644 --- a/tools/testing/selftests/bpf/progs/map_kptr_fail.c +++ b/tools/testing/selftests/bpf/progs/map_kptr_fail.c @@ -4,6 +4,7 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_core_read.h> #include "bpf_misc.h" +#include "../bpf_testmod/bpf_testmod_kfunc.h" struct map_value { char buf[8]; @@ -19,9 +20,6 @@ struct array_map { __uint(max_entries, 1); } array_map SEC(".maps"); -extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym; -extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; - SEC("?tc") __failure __msg("kptr access size must be BPF_DW") int size_not_bpf_dw(struct __sk_buff *ctx) diff --git a/tools/testing/selftests/bpf/progs/sock_destroy_prog.c b/tools/testing/selftests/bpf/progs/sock_destroy_prog.c new file mode 100644 index 000000000000..9e0bf7a54cec --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sock_destroy_prog.c @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#include "bpf_tracing_net.h" + +__be16 serv_port = 0; + +int bpf_sock_destroy(struct sock_common *sk) __ksym; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} tcp_conn_sockets SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} udp_conn_sockets SEC(".maps"); + +SEC("cgroup/connect6") +int sock_connect(struct bpf_sock_addr *ctx) +{ + __u64 sock_cookie = 0; + int key = 0; + __u32 keyc = 0; + + if (ctx->family != AF_INET6 || ctx->user_family != AF_INET6) + return 1; + + sock_cookie = bpf_get_socket_cookie(ctx); + if (ctx->protocol == IPPROTO_TCP) + bpf_map_update_elem(&tcp_conn_sockets, &key, &sock_cookie, 0); + else if (ctx->protocol == IPPROTO_UDP) + bpf_map_update_elem(&udp_conn_sockets, &keyc, &sock_cookie, 0); + else + return 1; + + return 1; +} + +SEC("iter/tcp") +int iter_tcp6_client(struct bpf_iter__tcp *ctx) +{ + struct sock_common *sk_common = ctx->sk_common; + __u64 sock_cookie = 0; + __u64 *val; + int key = 0; + + if (!sk_common) + return 0; + + if (sk_common->skc_family != AF_INET6) + return 0; + + sock_cookie = bpf_get_socket_cookie(sk_common); + val = bpf_map_lookup_elem(&tcp_conn_sockets, &key); + if (!val) + return 0; + /* Destroy connected client sockets. */ + if (sock_cookie == *val) + bpf_sock_destroy(sk_common); + + return 0; +} + +SEC("iter/tcp") +int iter_tcp6_server(struct bpf_iter__tcp *ctx) +{ + struct sock_common *sk_common = ctx->sk_common; + const struct inet_connection_sock *icsk; + const struct inet_sock *inet; + struct tcp6_sock *tcp_sk; + __be16 srcp; + + if (!sk_common) + return 0; + + if (sk_common->skc_family != AF_INET6) + return 0; + + tcp_sk = bpf_skc_to_tcp6_sock(sk_common); + if (!tcp_sk) + return 0; + + icsk = &tcp_sk->tcp.inet_conn; + inet = &icsk->icsk_inet; + srcp = inet->inet_sport; + + /* Destroy server sockets. */ + if (srcp == serv_port) + bpf_sock_destroy(sk_common); + + return 0; +} + + +SEC("iter/udp") +int iter_udp6_client(struct bpf_iter__udp *ctx) +{ + struct udp_sock *udp_sk = ctx->udp_sk; + struct sock *sk = (struct sock *) udp_sk; + __u64 sock_cookie = 0, *val; + int key = 0; + + if (!sk) + return 0; + + sock_cookie = bpf_get_socket_cookie(sk); + val = bpf_map_lookup_elem(&udp_conn_sockets, &key); + if (!val) + return 0; + /* Destroy connected client sockets. */ + if (sock_cookie == *val) + bpf_sock_destroy((struct sock_common *)sk); + + return 0; +} + +SEC("iter/udp") +int iter_udp6_server(struct bpf_iter__udp *ctx) +{ + struct udp_sock *udp_sk = ctx->udp_sk; + struct sock *sk = (struct sock *) udp_sk; + struct inet_sock *inet; + __be16 srcp; + + if (!sk) + return 0; + + inet = &udp_sk->inet; + srcp = inet->inet_sport; + if (srcp == serv_port) + bpf_sock_destroy((struct sock_common *)sk); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/sock_destroy_prog_fail.c b/tools/testing/selftests/bpf/progs/sock_destroy_prog_fail.c new file mode 100644 index 000000000000..dd6850b58e25 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sock_destroy_prog_fail.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +int bpf_sock_destroy(struct sock_common *sk) __ksym; + +SEC("tp_btf/tcp_destroy_sock") +__failure __msg("calling kernel function bpf_sock_destroy is not allowed") +int BPF_PROG(trace_tcp_destroy_sock, struct sock *sk) +{ + /* should not load */ + bpf_sock_destroy((struct sock_common *)sk); + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/sockopt_inherit.c b/tools/testing/selftests/bpf/progs/sockopt_inherit.c index 9fb241b97291..c8f59caa4639 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_inherit.c +++ b/tools/testing/selftests/bpf/progs/sockopt_inherit.c @@ -9,6 +9,8 @@ char _license[] SEC("license") = "GPL"; #define CUSTOM_INHERIT2 1 #define CUSTOM_LISTENER 2 +__u32 page_size = 0; + struct sockopt_inherit { __u8 val; }; @@ -55,7 +57,7 @@ int _getsockopt(struct bpf_sockopt *ctx) __u8 *optval = ctx->optval; if (ctx->level != SOL_CUSTOM) - return 1; /* only interested in SOL_CUSTOM */ + goto out; /* only interested in SOL_CUSTOM */ if (optval + 1 > optval_end) return 0; /* EPERM, bounds check */ @@ -70,6 +72,12 @@ int _getsockopt(struct bpf_sockopt *ctx) ctx->optlen = 1; return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } SEC("cgroup/setsockopt") @@ -80,7 +88,7 @@ int _setsockopt(struct bpf_sockopt *ctx) __u8 *optval = ctx->optval; if (ctx->level != SOL_CUSTOM) - return 1; /* only interested in SOL_CUSTOM */ + goto out; /* only interested in SOL_CUSTOM */ if (optval + 1 > optval_end) return 0; /* EPERM, bounds check */ @@ -93,4 +101,10 @@ int _setsockopt(struct bpf_sockopt *ctx) ctx->optlen = -1; return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } diff --git a/tools/testing/selftests/bpf/progs/sockopt_multi.c b/tools/testing/selftests/bpf/progs/sockopt_multi.c index 177a59069dae..96f29fce050b 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_multi.c +++ b/tools/testing/selftests/bpf/progs/sockopt_multi.c @@ -5,6 +5,8 @@ char _license[] SEC("license") = "GPL"; +__u32 page_size = 0; + SEC("cgroup/getsockopt") int _getsockopt_child(struct bpf_sockopt *ctx) { @@ -12,7 +14,7 @@ int _getsockopt_child(struct bpf_sockopt *ctx) __u8 *optval = ctx->optval; if (ctx->level != SOL_IP || ctx->optname != IP_TOS) - return 1; + goto out; if (optval + 1 > optval_end) return 0; /* EPERM, bounds check */ @@ -26,6 +28,12 @@ int _getsockopt_child(struct bpf_sockopt *ctx) ctx->optlen = 1; return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } SEC("cgroup/getsockopt") @@ -35,7 +43,7 @@ int _getsockopt_parent(struct bpf_sockopt *ctx) __u8 *optval = ctx->optval; if (ctx->level != SOL_IP || ctx->optname != IP_TOS) - return 1; + goto out; if (optval + 1 > optval_end) return 0; /* EPERM, bounds check */ @@ -49,6 +57,12 @@ int _getsockopt_parent(struct bpf_sockopt *ctx) ctx->optlen = 1; return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } SEC("cgroup/setsockopt") @@ -58,7 +72,7 @@ int _setsockopt(struct bpf_sockopt *ctx) __u8 *optval = ctx->optval; if (ctx->level != SOL_IP || ctx->optname != IP_TOS) - return 1; + goto out; if (optval + 1 > optval_end) return 0; /* EPERM, bounds check */ @@ -67,4 +81,10 @@ int _setsockopt(struct bpf_sockopt *ctx) ctx->optlen = 1; return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } diff --git a/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c b/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c index 1bce83b6e3a7..dbe235ede7f3 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c +++ b/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c @@ -9,6 +9,8 @@ char _license[] SEC("license") = "GPL"; +__u32 page_size = 0; + SEC("cgroup/setsockopt") int sockopt_qos_to_cc(struct bpf_sockopt *ctx) { @@ -19,7 +21,7 @@ int sockopt_qos_to_cc(struct bpf_sockopt *ctx) char cc_cubic[TCP_CA_NAME_MAX] = "cubic"; if (ctx->level != SOL_IPV6 || ctx->optname != IPV6_TCLASS) - return 1; + goto out; if (optval + 1 > optval_end) return 0; /* EPERM, bounds check */ @@ -36,4 +38,10 @@ int sockopt_qos_to_cc(struct bpf_sockopt *ctx) return 0; } return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c index fe1df4cd206e..cb990a7d3d45 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_sk.c +++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c @@ -37,7 +37,7 @@ int _getsockopt(struct bpf_sockopt *ctx) /* Bypass AF_NETLINK. */ sk = ctx->sk; if (sk && sk->family == AF_NETLINK) - return 1; + goto out; /* Make sure bpf_get_netns_cookie is callable. */ @@ -52,8 +52,7 @@ int _getsockopt(struct bpf_sockopt *ctx) * let next BPF program in the cgroup chain or kernel * handle it. */ - ctx->optlen = 0; /* bypass optval>PAGE_SIZE */ - return 1; + goto out; } if (ctx->level == SOL_SOCKET && ctx->optname == SO_SNDBUF) { @@ -61,7 +60,7 @@ int _getsockopt(struct bpf_sockopt *ctx) * let next BPF program in the cgroup chain or kernel * handle it. */ - return 1; + goto out; } if (ctx->level == SOL_TCP && ctx->optname == TCP_CONGESTION) { @@ -69,7 +68,7 @@ int _getsockopt(struct bpf_sockopt *ctx) * let next BPF program in the cgroup chain or kernel * handle it. */ - return 1; + goto out; } if (ctx->level == SOL_TCP && ctx->optname == TCP_ZEROCOPY_RECEIVE) { @@ -85,7 +84,7 @@ int _getsockopt(struct bpf_sockopt *ctx) if (((struct tcp_zerocopy_receive *)optval)->address != 0) return 0; /* unexpected data */ - return 1; + goto out; } if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) { @@ -129,6 +128,12 @@ int _getsockopt(struct bpf_sockopt *ctx) ctx->optlen = 1; return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } SEC("cgroup/setsockopt") @@ -142,7 +147,7 @@ int _setsockopt(struct bpf_sockopt *ctx) /* Bypass AF_NETLINK. */ sk = ctx->sk; if (sk && sk->family == AF_NETLINK) - return 1; + goto out; /* Make sure bpf_get_netns_cookie is callable. */ @@ -224,4 +229,10 @@ int _setsockopt(struct bpf_sockopt *ctx) */ return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } diff --git a/tools/testing/selftests/bpf/progs/test_global_func1.c b/tools/testing/selftests/bpf/progs/test_global_func1.c index b85fc8c423ba..17a9f59bf5f3 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func1.c +++ b/tools/testing/selftests/bpf/progs/test_global_func1.c @@ -10,6 +10,8 @@ static __attribute__ ((noinline)) int f0(int var, struct __sk_buff *skb) { + asm volatile (""); + return skb->len; } diff --git a/tools/testing/selftests/bpf/progs/test_global_map_resize.c b/tools/testing/selftests/bpf/progs/test_global_map_resize.c new file mode 100644 index 000000000000..2588f2384246 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_map_resize.c @@ -0,0 +1,58 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +/* rodata section */ +const volatile pid_t pid; +const volatile size_t bss_array_len; +const volatile size_t data_array_len; + +/* bss section */ +int sum = 0; +int array[1]; + +/* custom data secton */ +int my_array[1] SEC(".data.custom"); + +/* custom data section which should NOT be resizable, + * since it contains a single var which is not an array + */ +int my_int SEC(".data.non_array"); + +/* custom data section which should NOT be resizable, + * since its last var is not an array + */ +int my_array_first[1] SEC(".data.array_not_last"); +int my_int_last SEC(".data.array_not_last"); + +SEC("tp/syscalls/sys_enter_getpid") +int bss_array_sum(void *ctx) +{ + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + sum = 0; + + for (size_t i = 0; i < bss_array_len; ++i) + sum += array[i]; + + return 0; +} + +SEC("tp/syscalls/sys_enter_getuid") +int data_array_sum(void *ctx) +{ + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + sum = 0; + + for (size_t i = 0; i < data_array_len; ++i) + sum += my_array[i]; + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields.c b/tools/testing/selftests/bpf/progs/test_sock_fields.c index bbad3c2d9aa5..f75e531bf36f 100644 --- a/tools/testing/selftests/bpf/progs/test_sock_fields.c +++ b/tools/testing/selftests/bpf/progs/test_sock_fields.c @@ -265,7 +265,10 @@ static __noinline bool sk_dst_port__load_word(struct bpf_sock *sk) static __noinline bool sk_dst_port__load_half(struct bpf_sock *sk) { - __u16 *half = (__u16 *)&sk->dst_port; + __u16 *half; + + asm volatile (""); + half = (__u16 *)&sk->dst_port; return half[0] == bpf_htons(0xcafe); } diff --git a/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c b/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c new file mode 100644 index 000000000000..56cdc0a553f0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Bytedance */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +#include "bpf_misc.h" + +struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym; +long bpf_task_under_cgroup(struct task_struct *task, struct cgroup *ancestor) __ksym; +void bpf_cgroup_release(struct cgroup *p) __ksym; +struct task_struct *bpf_task_acquire(struct task_struct *p) __ksym; +void bpf_task_release(struct task_struct *p) __ksym; + +const volatile int local_pid; +const volatile __u64 cgid; +int remote_pid; + +SEC("tp_btf/task_newtask") +int BPF_PROG(handle__task_newtask, struct task_struct *task, u64 clone_flags) +{ + struct cgroup *cgrp = NULL; + struct task_struct *acquired; + + if (local_pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + acquired = bpf_task_acquire(task); + if (!acquired) + return 0; + + if (local_pid == acquired->tgid) + goto out; + + cgrp = bpf_cgroup_from_id(cgid); + if (!cgrp) + goto out; + + if (bpf_task_under_cgroup(acquired, cgrp)) + remote_pid = acquired->tgid; + +out: + if (cgrp) + bpf_cgroup_release(cgrp); + bpf_task_release(acquired); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c b/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c index 25ee4a22e48d..78c368e71797 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c @@ -2,6 +2,7 @@ /* Copyright (c) 2022 Meta */ #include <stddef.h> #include <string.h> +#include <stdbool.h> #include <linux/bpf.h> #include <linux/if_ether.h> #include <linux/if_packet.h> diff --git a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c new file mode 100644 index 000000000000..db6b3143338b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c @@ -0,0 +1,536 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include <errno.h> +#include <string.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#define ARRAY_SIZE(x) (sizeof(x) / sizeof(x[0])) + +int vals[] SEC(".data.vals") = {1, 2, 3, 4}; + +__naked __noinline __used +static unsigned long identity_subprog() +{ + /* the simplest *static* 64-bit identity function */ + asm volatile ( + "r0 = r1;" + "exit;" + ); +} + +__noinline __used +unsigned long global_identity_subprog(__u64 x) +{ + /* the simplest *global* 64-bit identity function */ + return x; +} + +__naked __noinline __used +static unsigned long callback_subprog() +{ + /* the simplest callback function */ + asm volatile ( + "r0 = 0;" + "exit;" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("7: (0f) r1 += r0") +__msg("mark_precise: frame0: regs=r0 stack= before 6: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r0 stack= before 5: (27) r0 *= 4") +__msg("mark_precise: frame0: regs=r0 stack= before 11: (95) exit") +__msg("mark_precise: frame1: regs=r0 stack= before 10: (bf) r0 = r1") +__msg("mark_precise: frame1: regs=r1 stack= before 4: (85) call pc+5") +__msg("mark_precise: frame0: regs=r1 stack= before 3: (bf) r1 = r6") +__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 3") +__naked int subprog_result_precise(void) +{ + asm volatile ( + "r6 = 3;" + /* pass r6 through r1 into subprog to get it back as r0; + * this whole chain will have to be marked as precise later + */ + "r1 = r6;" + "call identity_subprog;" + /* now use subprog's returned value (which is a + * r6 -> r1 -> r0 chain), as index into vals array, forcing + * all of that to be known precisely + */ + "r0 *= 4;" + "r1 = %[vals];" + /* here r0->r1->r6 chain is forced to be precise and has to be + * propagated back to the beginning, including through the + * subprog call + */ + "r1 += r0;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("9: (0f) r1 += r0") +__msg("mark_precise: frame0: last_idx 9 first_idx 0") +__msg("mark_precise: frame0: regs=r0 stack= before 8: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r0 stack= before 7: (27) r0 *= 4") +__msg("mark_precise: frame0: regs=r0 stack= before 5: (a5) if r0 < 0x4 goto pc+1") +__msg("mark_precise: frame0: regs=r0 stack= before 4: (85) call pc+7") +__naked int global_subprog_result_precise(void) +{ + asm volatile ( + "r6 = 3;" + /* pass r6 through r1 into subprog to get it back as r0; + * given global_identity_subprog is global, precision won't + * propagate all the way back to r6 + */ + "r1 = r6;" + "call global_identity_subprog;" + /* now use subprog's returned value (which is unknown now, so + * we need to clamp it), as index into vals array, forcing r0 + * to be marked precise (with no effect on r6, though) + */ + "if r0 < %[vals_arr_sz] goto 1f;" + "r0 = %[vals_arr_sz] - 1;" + "1:" + "r0 *= 4;" + "r1 = %[vals];" + /* here r0 is forced to be precise and has to be + * propagated back to the global subprog call, but it + * shouldn't go all the way to mark r6 as precise + */ + "r1 += r0;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals), + __imm_const(vals_arr_sz, ARRAY_SIZE(vals)) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("14: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 14 first_idx 10") +__msg("mark_precise: frame0: regs=r6 stack= before 13: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 12: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 11: (25) if r6 > 0x3 goto pc+4") +__msg("mark_precise: frame0: regs=r6 stack= before 10: (bf) r6 = r0") +__msg("mark_precise: frame0: parent state regs=r0 stack=:") +__msg("mark_precise: frame0: last_idx 18 first_idx 0") +__msg("mark_precise: frame0: regs=r0 stack= before 18: (95) exit") +__naked int callback_result_precise(void) +{ + asm volatile ( + "r6 = 3;" + + /* call subprog and use result; r0 shouldn't propagate back to + * callback_subprog + */ + "r1 = r6;" /* nr_loops */ + "r2 = %[callback_subprog];" /* callback_fn */ + "r3 = 0;" /* callback_ctx */ + "r4 = 0;" /* flags */ + "call %[bpf_loop];" + + "r6 = r0;" + "if r6 > 3 goto 1f;" + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the bpf_loop() call, but not beyond + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "1:" + "exit;" + : + : __imm_ptr(vals), + __imm_ptr(callback_subprog), + __imm(bpf_loop) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("7: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 7 first_idx 0") +__msg("mark_precise: frame0: regs=r6 stack= before 6: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 5: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 11: (95) exit") +__msg("mark_precise: frame1: regs= stack= before 10: (bf) r0 = r1") +__msg("mark_precise: frame1: regs= stack= before 4: (85) call pc+5") +__msg("mark_precise: frame0: regs=r6 stack= before 3: (b7) r1 = 0") +__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 3") +__naked int parent_callee_saved_reg_precise(void) +{ + asm volatile ( + "r6 = 3;" + + /* call subprog and ignore result; we need this call only to + * complicate jump history + */ + "r1 = 0;" + "call identity_subprog;" + + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the beginning, handling (and ignoring) subprog call + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("7: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 7 first_idx 0") +__msg("mark_precise: frame0: regs=r6 stack= before 6: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 5: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 4: (85) call pc+5") +__msg("mark_precise: frame0: regs=r6 stack= before 3: (b7) r1 = 0") +__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 3") +__naked int parent_callee_saved_reg_precise_global(void) +{ + asm volatile ( + "r6 = 3;" + + /* call subprog and ignore result; we need this call only to + * complicate jump history + */ + "r1 = 0;" + "call global_identity_subprog;" + + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the beginning, handling (and ignoring) subprog call + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("12: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 12 first_idx 10") +__msg("mark_precise: frame0: regs=r6 stack= before 11: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 10: (27) r6 *= 4") +__msg("mark_precise: frame0: parent state regs=r6 stack=:") +__msg("mark_precise: frame0: last_idx 16 first_idx 0") +__msg("mark_precise: frame0: regs=r6 stack= before 16: (95) exit") +__msg("mark_precise: frame1: regs= stack= before 15: (b7) r0 = 0") +__msg("mark_precise: frame1: regs= stack= before 9: (85) call bpf_loop#181") +__msg("mark_precise: frame0: regs=r6 stack= before 8: (b7) r4 = 0") +__msg("mark_precise: frame0: regs=r6 stack= before 7: (b7) r3 = 0") +__msg("mark_precise: frame0: regs=r6 stack= before 6: (bf) r2 = r8") +__msg("mark_precise: frame0: regs=r6 stack= before 5: (b7) r1 = 1") +__msg("mark_precise: frame0: regs=r6 stack= before 4: (b7) r6 = 3") +__naked int parent_callee_saved_reg_precise_with_callback(void) +{ + asm volatile ( + "r6 = 3;" + + /* call subprog and ignore result; we need this call only to + * complicate jump history + */ + "r1 = 1;" /* nr_loops */ + "r2 = %[callback_subprog];" /* callback_fn */ + "r3 = 0;" /* callback_ctx */ + "r4 = 0;" /* flags */ + "call %[bpf_loop];" + + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the beginning, handling (and ignoring) callback call + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals), + __imm_ptr(callback_subprog), + __imm(bpf_loop) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("9: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 9 first_idx 6") +__msg("mark_precise: frame0: regs=r6 stack= before 8: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 7: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 6: (79) r6 = *(u64 *)(r10 -8)") +__msg("mark_precise: frame0: parent state regs= stack=-8:") +__msg("mark_precise: frame0: last_idx 13 first_idx 0") +__msg("mark_precise: frame0: regs= stack=-8 before 13: (95) exit") +__msg("mark_precise: frame1: regs= stack= before 12: (bf) r0 = r1") +__msg("mark_precise: frame1: regs= stack= before 5: (85) call pc+6") +__msg("mark_precise: frame0: regs= stack=-8 before 4: (b7) r1 = 0") +__msg("mark_precise: frame0: regs= stack=-8 before 3: (7b) *(u64 *)(r10 -8) = r6") +__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 3") +__naked int parent_stack_slot_precise(void) +{ + asm volatile ( + /* spill reg */ + "r6 = 3;" + "*(u64 *)(r10 - 8) = r6;" + + /* call subprog and ignore result; we need this call only to + * complicate jump history + */ + "r1 = 0;" + "call identity_subprog;" + + /* restore reg from stack; in this case we'll be carrying + * stack mask when going back into subprog through jump + * history + */ + "r6 = *(u64 *)(r10 - 8);" + + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the beginning, handling (and ignoring) subprog call + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("9: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 9 first_idx 6") +__msg("mark_precise: frame0: regs=r6 stack= before 8: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 7: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 6: (79) r6 = *(u64 *)(r10 -8)") +__msg("mark_precise: frame0: parent state regs= stack=-8:") +__msg("mark_precise: frame0: last_idx 5 first_idx 0") +__msg("mark_precise: frame0: regs= stack=-8 before 5: (85) call pc+6") +__msg("mark_precise: frame0: regs= stack=-8 before 4: (b7) r1 = 0") +__msg("mark_precise: frame0: regs= stack=-8 before 3: (7b) *(u64 *)(r10 -8) = r6") +__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 3") +__naked int parent_stack_slot_precise_global(void) +{ + asm volatile ( + /* spill reg */ + "r6 = 3;" + "*(u64 *)(r10 - 8) = r6;" + + /* call subprog and ignore result; we need this call only to + * complicate jump history + */ + "r1 = 0;" + "call global_identity_subprog;" + + /* restore reg from stack; in this case we'll be carrying + * stack mask when going back into subprog through jump + * history + */ + "r6 = *(u64 *)(r10 - 8);" + + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the beginning, handling (and ignoring) subprog call + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("14: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 14 first_idx 11") +__msg("mark_precise: frame0: regs=r6 stack= before 13: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 12: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 11: (79) r6 = *(u64 *)(r10 -8)") +__msg("mark_precise: frame0: parent state regs= stack=-8:") +__msg("mark_precise: frame0: last_idx 18 first_idx 0") +__msg("mark_precise: frame0: regs= stack=-8 before 18: (95) exit") +__msg("mark_precise: frame1: regs= stack= before 17: (b7) r0 = 0") +__msg("mark_precise: frame1: regs= stack= before 10: (85) call bpf_loop#181") +__msg("mark_precise: frame0: regs= stack=-8 before 9: (b7) r4 = 0") +__msg("mark_precise: frame0: regs= stack=-8 before 8: (b7) r3 = 0") +__msg("mark_precise: frame0: regs= stack=-8 before 7: (bf) r2 = r8") +__msg("mark_precise: frame0: regs= stack=-8 before 6: (bf) r1 = r6") +__msg("mark_precise: frame0: regs= stack=-8 before 5: (7b) *(u64 *)(r10 -8) = r6") +__msg("mark_precise: frame0: regs=r6 stack= before 4: (b7) r6 = 3") +__naked int parent_stack_slot_precise_with_callback(void) +{ + asm volatile ( + /* spill reg */ + "r6 = 3;" + "*(u64 *)(r10 - 8) = r6;" + + /* ensure we have callback frame in jump history */ + "r1 = r6;" /* nr_loops */ + "r2 = %[callback_subprog];" /* callback_fn */ + "r3 = 0;" /* callback_ctx */ + "r4 = 0;" /* flags */ + "call %[bpf_loop];" + + /* restore reg from stack; in this case we'll be carrying + * stack mask when going back into subprog through jump + * history + */ + "r6 = *(u64 *)(r10 - 8);" + + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the beginning, handling (and ignoring) subprog call + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals), + __imm_ptr(callback_subprog), + __imm(bpf_loop) + : __clobber_common, "r6" + ); +} + +__noinline __used +static __u64 subprog_with_precise_arg(__u64 x) +{ + return vals[x]; /* x is forced to be precise */ +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("8: (0f) r2 += r1") +__msg("mark_precise: frame1: last_idx 8 first_idx 0") +__msg("mark_precise: frame1: regs=r1 stack= before 6: (18) r2 = ") +__msg("mark_precise: frame1: regs=r1 stack= before 5: (67) r1 <<= 2") +__msg("mark_precise: frame1: regs=r1 stack= before 2: (85) call pc+2") +__msg("mark_precise: frame0: regs=r1 stack= before 1: (bf) r1 = r6") +__msg("mark_precise: frame0: regs=r6 stack= before 0: (b7) r6 = 3") +__naked int subprog_arg_precise(void) +{ + asm volatile ( + "r6 = 3;" + "r1 = r6;" + /* subprog_with_precise_arg expects its argument to be + * precise, so r1->r6 will be marked precise from inside the + * subprog + */ + "call subprog_with_precise_arg;" + "r0 += r6;" + "exit;" + : + : + : __clobber_common, "r6" + ); +} + +/* r1 is pointer to stack slot; + * r2 is a register to spill into that slot + * subprog also spills r2 into its own stack slot + */ +__naked __noinline __used +static __u64 subprog_spill_reg_precise(void) +{ + asm volatile ( + /* spill to parent stack */ + "*(u64 *)(r1 + 0) = r2;" + /* spill to subprog stack (we use -16 offset to avoid + * accidental confusion with parent's -8 stack slot in + * verifier log output) + */ + "*(u64 *)(r10 - 16) = r2;" + /* use both spills as return result to propagete precision everywhere */ + "r0 = *(u64 *)(r10 - 16);" + "r2 = *(u64 *)(r1 + 0);" + "r0 += r2;" + "exit;" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +/* precision backtracking can't currently handle stack access not through r10, + * so we won't be able to mark stack slot fp-8 as precise, and so will + * fallback to forcing all as precise + */ +__msg("mark_precise: frame0: falling back to forcing all scalars precise") +__naked int subprog_spill_into_parent_stack_slot_precise(void) +{ + asm volatile ( + "r6 = 1;" + + /* pass pointer to stack slot and r6 to subprog; + * r6 will be marked precise and spilled into fp-8 slot, which + * also should be marked precise + */ + "r1 = r10;" + "r1 += -8;" + "r2 = r6;" + "call subprog_spill_reg_precise;" + + /* restore reg from stack; in this case we'll be carrying + * stack mask when going back into subprog through jump + * history + */ + "r7 = *(u64 *)(r10 - 8);" + + "r7 *= 4;" + "r1 = %[vals];" + /* here r7 is forced to be precise and has to be propagated + * back to the beginning, handling subprog call and logic + */ + "r1 += r7;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals) + : __clobber_common, "r6", "r7" + ); +} + +__naked __noinline __used +static __u64 subprog_with_checkpoint(void) +{ + asm volatile ( + "r0 = 0;" + /* guaranteed checkpoint if BPF_F_TEST_STATE_FREQ is used */ + "goto +0;" + "exit;" + ); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c index e1c787815e44..b2dfd7066c6e 100644 --- a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c @@ -77,7 +77,9 @@ int rx(struct xdp_md *ctx) } err = bpf_xdp_metadata_rx_timestamp(ctx, &meta->rx_timestamp); - if (err) + if (!err) + meta->xdp_timestamp = bpf_ktime_get_tai_ns(); + else meta->rx_timestamp = 0; /* Used by AF_XDP as not avail signal */ err = bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, &meta->rx_hash_type); diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index ea82921110da..4d582cac2c09 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -11,7 +11,6 @@ #include <signal.h> #include <string.h> #include <execinfo.h> /* backtrace */ -#include <linux/membarrier.h> #include <sys/sysinfo.h> /* get_nprocs */ #include <netinet/in.h> #include <sys/select.h> @@ -629,68 +628,6 @@ out: return err; } -static int finit_module(int fd, const char *param_values, int flags) -{ - return syscall(__NR_finit_module, fd, param_values, flags); -} - -static int delete_module(const char *name, int flags) -{ - return syscall(__NR_delete_module, name, flags); -} - -/* - * Trigger synchronize_rcu() in kernel. - */ -int kern_sync_rcu(void) -{ - return syscall(__NR_membarrier, MEMBARRIER_CMD_SHARED, 0, 0); -} - -static void unload_bpf_testmod(void) -{ - if (kern_sync_rcu()) - fprintf(env.stderr, "Failed to trigger kernel-side RCU sync!\n"); - if (delete_module("bpf_testmod", 0)) { - if (errno == ENOENT) { - if (verbose()) - fprintf(stdout, "bpf_testmod.ko is already unloaded.\n"); - return; - } - fprintf(env.stderr, "Failed to unload bpf_testmod.ko from kernel: %d\n", -errno); - return; - } - if (verbose()) - fprintf(stdout, "Successfully unloaded bpf_testmod.ko.\n"); -} - -static int load_bpf_testmod(void) -{ - int fd; - - /* ensure previous instance of the module is unloaded */ - unload_bpf_testmod(); - - if (verbose()) - fprintf(stdout, "Loading bpf_testmod.ko...\n"); - - fd = open("bpf_testmod.ko", O_RDONLY); - if (fd < 0) { - fprintf(env.stderr, "Can't find bpf_testmod.ko kernel module: %d\n", -errno); - return -ENOENT; - } - if (finit_module(fd, "", 0)) { - fprintf(env.stderr, "Failed to load bpf_testmod.ko into the kernel: %d\n", -errno); - close(fd); - return -EINVAL; - } - close(fd); - - if (verbose()) - fprintf(stdout, "Successfully loaded bpf_testmod.ko.\n"); - return 0; -} - /* extern declarations for test funcs */ #define DEFINE_TEST(name) \ extern void test_##name(void) __weak; \ @@ -714,7 +651,13 @@ static struct test_state test_states[ARRAY_SIZE(prog_test_defs)]; const char *argp_program_version = "test_progs 0.1"; const char *argp_program_bug_address = "<bpf@vger.kernel.org>"; -static const char argp_program_doc[] = "BPF selftests test runner"; +static const char argp_program_doc[] = +"BPF selftests test runner\v" +"Options accepting the NAMES parameter take either a comma-separated list\n" +"of test names, or a filename prefixed with @. The file contains one name\n" +"(or wildcard pattern) per line, and comments beginning with # are ignored.\n" +"\n" +"These options can be passed repeatedly to read multiple files.\n"; enum ARG_KEYS { ARG_TEST_NUM = 'n', @@ -797,6 +740,7 @@ extern int extra_prog_load_log_flags; static error_t parse_arg(int key, char *arg, struct argp_state *state) { struct test_env *env = state->input; + int err = 0; switch (key) { case ARG_TEST_NUM: { @@ -821,18 +765,28 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state) } case ARG_TEST_NAME_GLOB_ALLOWLIST: case ARG_TEST_NAME: { - if (parse_test_list(arg, - &env->test_selector.whitelist, - key == ARG_TEST_NAME_GLOB_ALLOWLIST)) - return -ENOMEM; + if (arg[0] == '@') + err = parse_test_list_file(arg + 1, + &env->test_selector.whitelist, + key == ARG_TEST_NAME_GLOB_ALLOWLIST); + else + err = parse_test_list(arg, + &env->test_selector.whitelist, + key == ARG_TEST_NAME_GLOB_ALLOWLIST); + break; } case ARG_TEST_NAME_GLOB_DENYLIST: case ARG_TEST_NAME_BLACKLIST: { - if (parse_test_list(arg, - &env->test_selector.blacklist, - key == ARG_TEST_NAME_GLOB_DENYLIST)) - return -ENOMEM; + if (arg[0] == '@') + err = parse_test_list_file(arg + 1, + &env->test_selector.blacklist, + key == ARG_TEST_NAME_GLOB_DENYLIST); + else + err = parse_test_list(arg, + &env->test_selector.blacklist, + key == ARG_TEST_NAME_GLOB_DENYLIST); + break; } case ARG_VERIFIER_STATS: @@ -900,7 +854,7 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state) default: return ARGP_ERR_UNKNOWN; } - return 0; + return err; } /* @@ -1703,9 +1657,14 @@ int main(int argc, char **argv) env.stderr = stderr; env.has_testmod = true; - if (!env.list_test_names && load_bpf_testmod()) { - fprintf(env.stderr, "WARNING! Selftests relying on bpf_testmod.ko will be skipped.\n"); - env.has_testmod = false; + if (!env.list_test_names) { + /* ensure previous instance of the module is unloaded */ + unload_bpf_testmod(verbose()); + + if (load_bpf_testmod(verbose())) { + fprintf(env.stderr, "WARNING! Selftests relying on bpf_testmod.ko will be skipped.\n"); + env.has_testmod = false; + } } /* initializing tests */ @@ -1802,7 +1761,7 @@ int main(int argc, char **argv) close(env.saved_netns_fd); out: if (!env.list_test_names && env.has_testmod) - unload_bpf_testmod(); + unload_bpf_testmod(verbose()); free_test_selector(&env.test_selector); free_test_selector(&env.subtest_selector); diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index 0ed3134333d4..77bd492c6024 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -405,7 +405,6 @@ static inline void *u64_to_ptr(__u64 ptr) int bpf_find_map(const char *test, struct bpf_object *obj, const char *name); int compare_map_keys(int map1_fd, int map2_fd); int compare_stack_ips(int smap_fd, int amap_fd, int stack_trace_len); -int kern_sync_rcu(void); int trigger_module_test_read(int read_sz); int trigger_module_test_write(int write_sz); int write_sysctl(const char *sysctl, const char *value); diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index e4657c5bc3f1..71704a38cac3 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -40,6 +40,7 @@ #include "bpf_util.h" #include "test_btf.h" #include "../../../include/linux/filter.h" +#include "testing_helpers.h" #ifndef ENOTSUPP #define ENOTSUPP 524 @@ -873,8 +874,140 @@ static int create_map_kptr(void) return fd; } +static void set_root(bool set) +{ + __u64 caps; + + if (set) { + if (cap_enable_effective(1ULL << CAP_SYS_ADMIN, &caps)) + perror("cap_disable_effective(CAP_SYS_ADMIN)"); + } else { + if (cap_disable_effective(1ULL << CAP_SYS_ADMIN, &caps)) + perror("cap_disable_effective(CAP_SYS_ADMIN)"); + } +} + +static __u64 ptr_to_u64(const void *ptr) +{ + return (uintptr_t) ptr; +} + +static struct btf *btf__load_testmod_btf(struct btf *vmlinux) +{ + struct bpf_btf_info info; + __u32 len = sizeof(info); + struct btf *btf = NULL; + char name[64]; + __u32 id = 0; + int err, fd; + + /* Iterate all loaded BTF objects and find bpf_testmod, + * we need SYS_ADMIN cap for that. + */ + set_root(true); + + while (true) { + err = bpf_btf_get_next_id(id, &id); + if (err) { + if (errno == ENOENT) + break; + perror("bpf_btf_get_next_id failed"); + break; + } + + fd = bpf_btf_get_fd_by_id(id); + if (fd < 0) { + if (errno == ENOENT) + continue; + perror("bpf_btf_get_fd_by_id failed"); + break; + } + + memset(&info, 0, sizeof(info)); + info.name_len = sizeof(name); + info.name = ptr_to_u64(name); + len = sizeof(info); + + err = bpf_obj_get_info_by_fd(fd, &info, &len); + if (err) { + close(fd); + perror("bpf_obj_get_info_by_fd failed"); + break; + } + + if (strcmp("bpf_testmod", name)) { + close(fd); + continue; + } + + btf = btf__load_from_kernel_by_id_split(id, vmlinux); + if (!btf) { + close(fd); + break; + } + + /* We need the fd to stay open so it can be used in fd_array. + * The final cleanup call to btf__free will free btf object + * and close the file descriptor. + */ + btf__set_fd(btf, fd); + break; + } + + set_root(false); + return btf; +} + +static struct btf *testmod_btf; +static struct btf *vmlinux_btf; + +static void kfuncs_cleanup(void) +{ + btf__free(testmod_btf); + btf__free(vmlinux_btf); +} + +static void fixup_prog_kfuncs(struct bpf_insn *prog, int *fd_array, + struct kfunc_btf_id_pair *fixup_kfunc_btf_id) +{ + /* Patch in kfunc BTF IDs */ + while (fixup_kfunc_btf_id->kfunc) { + int btf_id = 0; + + /* try to find kfunc in kernel BTF */ + vmlinux_btf = vmlinux_btf ?: btf__load_vmlinux_btf(); + if (vmlinux_btf) { + btf_id = btf__find_by_name_kind(vmlinux_btf, + fixup_kfunc_btf_id->kfunc, + BTF_KIND_FUNC); + btf_id = btf_id < 0 ? 0 : btf_id; + } + + /* kfunc not found in kernel BTF, try bpf_testmod BTF */ + if (!btf_id) { + testmod_btf = testmod_btf ?: btf__load_testmod_btf(vmlinux_btf); + if (testmod_btf) { + btf_id = btf__find_by_name_kind(testmod_btf, + fixup_kfunc_btf_id->kfunc, + BTF_KIND_FUNC); + btf_id = btf_id < 0 ? 0 : btf_id; + if (btf_id) { + /* We put bpf_testmod module fd into fd_array + * and its index 1 into instruction 'off'. + */ + *fd_array = btf__fd(testmod_btf); + prog[fixup_kfunc_btf_id->insn_idx].off = 1; + } + } + } + + prog[fixup_kfunc_btf_id->insn_idx].imm = btf_id; + fixup_kfunc_btf_id++; + } +} + static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, - struct bpf_insn *prog, int *map_fds) + struct bpf_insn *prog, int *map_fds, int *fd_array) { int *fixup_map_hash_8b = test->fixup_map_hash_8b; int *fixup_map_hash_48b = test->fixup_map_hash_48b; @@ -899,7 +1032,6 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, int *fixup_map_ringbuf = test->fixup_map_ringbuf; int *fixup_map_timer = test->fixup_map_timer; int *fixup_map_kptr = test->fixup_map_kptr; - struct kfunc_btf_id_pair *fixup_kfunc_btf_id = test->fixup_kfunc_btf_id; if (test->fill_helper) { test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn)); @@ -1100,25 +1232,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, } while (*fixup_map_kptr); } - /* Patch in kfunc BTF IDs */ - if (fixup_kfunc_btf_id->kfunc) { - struct btf *btf; - int btf_id; - - do { - btf_id = 0; - btf = btf__load_vmlinux_btf(); - if (btf) { - btf_id = btf__find_by_name_kind(btf, - fixup_kfunc_btf_id->kfunc, - BTF_KIND_FUNC); - btf_id = btf_id < 0 ? 0 : btf_id; - } - btf__free(btf); - prog[fixup_kfunc_btf_id->insn_idx].imm = btf_id; - fixup_kfunc_btf_id++; - } while (fixup_kfunc_btf_id->kfunc); - } + fixup_prog_kfuncs(prog, fd_array, test->fixup_kfunc_btf_id); } struct libcap { @@ -1445,6 +1559,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv, int run_errs, run_successes; int map_fds[MAX_NR_MAPS]; const char *expected_err; + int fd_array[2] = { -1, -1 }; int saved_errno; int fixup_skips; __u32 pflags; @@ -1458,7 +1573,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv, if (!prog_type) prog_type = BPF_PROG_TYPE_SOCKET_FILTER; fixup_skips = skips; - do_test_fixup(test, prog_type, prog, map_fds); + do_test_fixup(test, prog_type, prog, map_fds, &fd_array[1]); if (test->fill_insns) { prog = test->fill_insns; prog_len = test->prog_len; @@ -1492,6 +1607,8 @@ static void do_test_single(struct bpf_test *test, bool unpriv, else opts.log_level = DEFAULT_LIBBPF_LOG_LEVEL; opts.prog_flags = pflags; + if (fd_array[1] != -1) + opts.fd_array = &fd_array[0]; if ((prog_type == BPF_PROG_TYPE_TRACING || prog_type == BPF_PROG_TYPE_LSM) && test->kfunc) { @@ -1684,6 +1801,12 @@ static int do_test(bool unpriv, unsigned int from, unsigned int to) { int i, passes = 0, errors = 0; + /* ensure previous instance of the module is unloaded */ + unload_bpf_testmod(verbose); + + if (load_bpf_testmod(verbose)) + return EXIT_FAILURE; + for (i = from; i < to; i++) { struct bpf_test *test = &tests[i]; @@ -1711,6 +1834,9 @@ static int do_test(bool unpriv, unsigned int from, unsigned int to) } } + unload_bpf_testmod(verbose); + kfuncs_cleanup(); + printf("Summary: %d PASSED, %d SKIPPED, %d FAILED\n", passes, skips, errors); return errors ? EXIT_FAILURE : EXIT_SUCCESS; diff --git a/tools/testing/selftests/bpf/test_xsk.sh b/tools/testing/selftests/bpf/test_xsk.sh index 377fb157a57c..c2ad50f26b63 100755 --- a/tools/testing/selftests/bpf/test_xsk.sh +++ b/tools/testing/selftests/bpf/test_xsk.sh @@ -68,9 +68,6 @@ # Run with verbose output: # sudo ./test_xsk.sh -v # -# Run and dump packet contents: -# sudo ./test_xsk.sh -D -# # Set up veth interfaces and leave them up so xskxceiver can be launched in a debugger: # sudo ./test_xsk.sh -d # @@ -81,11 +78,10 @@ ETH="" -while getopts "vDi:d" flag +while getopts "vi:d" flag do case "${flag}" in v) verbose=1;; - D) dump_pkts=1;; d) debug=1;; i) ETH=${OPTARG};; esac @@ -157,10 +153,6 @@ if [[ $verbose -eq 1 ]]; then ARGS+="-v " fi -if [[ $dump_pkts -eq 1 ]]; then - ARGS="-D " -fi - retval=$? test_status $retval "${TEST_NAME}" diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c index 0b5e0829e5be..8d994884c7b4 100644 --- a/tools/testing/selftests/bpf/testing_helpers.c +++ b/tools/testing/selftests/bpf/testing_helpers.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) /* Copyright (C) 2019 Netronome Systems, Inc. */ /* Copyright (C) 2020 Facebook, Inc. */ +#include <ctype.h> #include <stdlib.h> #include <string.h> #include <errno.h> @@ -8,6 +9,7 @@ #include <bpf/libbpf.h> #include "test_progs.h" #include "testing_helpers.h" +#include <linux/membarrier.h> int parse_num_list(const char *s, bool **num_set, int *num_set_len) { @@ -70,92 +72,168 @@ int parse_num_list(const char *s, bool **num_set, int *num_set_len) return 0; } -int parse_test_list(const char *s, - struct test_filter_set *set, - bool is_glob_pattern) +static int do_insert_test(struct test_filter_set *set, + char *test_str, + char *subtest_str) { - char *input, *state = NULL, *next; - struct test_filter *tmp, *tests = NULL; - int i, j, cnt = 0; + struct test_filter *tmp, *test; + char **ctmp; + int i; - input = strdup(s); - if (!input) + for (i = 0; i < set->cnt; i++) { + test = &set->tests[i]; + + if (strcmp(test_str, test->name) == 0) { + free(test_str); + goto subtest; + } + } + + tmp = realloc(set->tests, sizeof(*test) * (set->cnt + 1)); + if (!tmp) return -ENOMEM; - while ((next = strtok_r(state ? NULL : input, ",", &state))) { - char *subtest_str = strchr(next, '/'); - char *pattern = NULL; - int glob_chars = 0; + set->tests = tmp; + test = &set->tests[set->cnt]; - tmp = realloc(tests, sizeof(*tests) * (cnt + 1)); - if (!tmp) - goto err; - tests = tmp; + test->name = test_str; + test->subtests = NULL; + test->subtest_cnt = 0; - tests[cnt].subtest_cnt = 0; - tests[cnt].subtests = NULL; + set->cnt++; - if (is_glob_pattern) { - pattern = "%s"; - } else { - pattern = "*%s*"; - glob_chars = 2; - } +subtest: + if (!subtest_str) + return 0; - if (subtest_str) { - char **tmp_subtests = NULL; - int subtest_cnt = tests[cnt].subtest_cnt; - - *subtest_str = '\0'; - subtest_str += 1; - tmp_subtests = realloc(tests[cnt].subtests, - sizeof(*tmp_subtests) * - (subtest_cnt + 1)); - if (!tmp_subtests) - goto err; - tests[cnt].subtests = tmp_subtests; - - tests[cnt].subtests[subtest_cnt] = - malloc(strlen(subtest_str) + glob_chars + 1); - if (!tests[cnt].subtests[subtest_cnt]) - goto err; - sprintf(tests[cnt].subtests[subtest_cnt], - pattern, - subtest_str); - - tests[cnt].subtest_cnt++; + for (i = 0; i < test->subtest_cnt; i++) { + if (strcmp(subtest_str, test->subtests[i]) == 0) { + free(subtest_str); + return 0; } + } - tests[cnt].name = malloc(strlen(next) + glob_chars + 1); - if (!tests[cnt].name) - goto err; - sprintf(tests[cnt].name, pattern, next); + ctmp = realloc(test->subtests, + sizeof(*test->subtests) * (test->subtest_cnt + 1)); + if (!ctmp) + return -ENOMEM; - cnt++; + test->subtests = ctmp; + test->subtests[test->subtest_cnt] = subtest_str; + + test->subtest_cnt++; + + return 0; +} + +static int insert_test(struct test_filter_set *set, + char *test_spec, + bool is_glob_pattern) +{ + char *pattern, *subtest_str, *ext_test_str, *ext_subtest_str = NULL; + int glob_chars = 0; + + if (is_glob_pattern) { + pattern = "%s"; + } else { + pattern = "*%s*"; + glob_chars = 2; } - tmp = realloc(set->tests, sizeof(*tests) * (cnt + set->cnt)); - if (!tmp) + subtest_str = strchr(test_spec, '/'); + if (subtest_str) { + *subtest_str = '\0'; + subtest_str += 1; + } + + ext_test_str = malloc(strlen(test_spec) + glob_chars + 1); + if (!ext_test_str) goto err; - memcpy(tmp + set->cnt, tests, sizeof(*tests) * cnt); - set->tests = tmp; - set->cnt += cnt; + sprintf(ext_test_str, pattern, test_spec); - free(tests); - free(input); - return 0; + if (subtest_str) { + ext_subtest_str = malloc(strlen(subtest_str) + glob_chars + 1); + if (!ext_subtest_str) + goto err; + + sprintf(ext_subtest_str, pattern, subtest_str); + } + + return do_insert_test(set, ext_test_str, ext_subtest_str); err: - for (i = 0; i < cnt; i++) { - for (j = 0; j < tests[i].subtest_cnt; j++) - free(tests[i].subtests[j]); + free(ext_test_str); + free(ext_subtest_str); + + return -ENOMEM; +} + +int parse_test_list_file(const char *path, + struct test_filter_set *set, + bool is_glob_pattern) +{ + char *buf = NULL, *capture_start, *capture_end, *scan_end; + size_t buflen = 0; + int err = 0; + FILE *f; + + f = fopen(path, "r"); + if (!f) { + err = -errno; + fprintf(stderr, "Failed to open '%s': %d\n", path, err); + return err; + } + + while (getline(&buf, &buflen, f) != -1) { + capture_start = buf; + + while (isspace(*capture_start)) + ++capture_start; + + capture_end = capture_start; + scan_end = capture_start; + + while (*scan_end && *scan_end != '#') { + if (!isspace(*scan_end)) + capture_end = scan_end; + + ++scan_end; + } + + if (capture_end == capture_start) + continue; + + *(++capture_end) = '\0'; + + err = insert_test(set, capture_start, is_glob_pattern); + if (err) + break; + } + + fclose(f); + return err; +} + +int parse_test_list(const char *s, + struct test_filter_set *set, + bool is_glob_pattern) +{ + char *input, *state = NULL, *test_spec; + int err = 0; + + input = strdup(s); + if (!input) + return -ENOMEM; - free(tests[i].name); + while ((test_spec = strtok_r(state ? NULL : input, ",", &state))) { + err = insert_test(set, test_spec, is_glob_pattern); + if (err) + break; } - free(tests); + free(input); - return -ENOMEM; + return err; } __u32 link_info_prog_id(const struct bpf_link *link, struct bpf_link_info *info) @@ -249,3 +327,63 @@ __u64 read_perf_max_sample_freq(void) fclose(f); return sample_freq; } + +static int finit_module(int fd, const char *param_values, int flags) +{ + return syscall(__NR_finit_module, fd, param_values, flags); +} + +static int delete_module(const char *name, int flags) +{ + return syscall(__NR_delete_module, name, flags); +} + +int unload_bpf_testmod(bool verbose) +{ + if (kern_sync_rcu()) + fprintf(stdout, "Failed to trigger kernel-side RCU sync!\n"); + if (delete_module("bpf_testmod", 0)) { + if (errno == ENOENT) { + if (verbose) + fprintf(stdout, "bpf_testmod.ko is already unloaded.\n"); + return -1; + } + fprintf(stdout, "Failed to unload bpf_testmod.ko from kernel: %d\n", -errno); + return -1; + } + if (verbose) + fprintf(stdout, "Successfully unloaded bpf_testmod.ko.\n"); + return 0; +} + +int load_bpf_testmod(bool verbose) +{ + int fd; + + if (verbose) + fprintf(stdout, "Loading bpf_testmod.ko...\n"); + + fd = open("bpf_testmod.ko", O_RDONLY); + if (fd < 0) { + fprintf(stdout, "Can't find bpf_testmod.ko kernel module: %d\n", -errno); + return -ENOENT; + } + if (finit_module(fd, "", 0)) { + fprintf(stdout, "Failed to load bpf_testmod.ko into the kernel: %d\n", -errno); + close(fd); + return -EINVAL; + } + close(fd); + + if (verbose) + fprintf(stdout, "Successfully loaded bpf_testmod.ko.\n"); + return 0; +} + +/* + * Trigger synchronize_rcu() in kernel. + */ +int kern_sync_rcu(void) +{ + return syscall(__NR_membarrier, MEMBARRIER_CMD_SHARED, 0, 0); +} diff --git a/tools/testing/selftests/bpf/testing_helpers.h b/tools/testing/selftests/bpf/testing_helpers.h index eb8790f928e4..5312323881b6 100644 --- a/tools/testing/selftests/bpf/testing_helpers.h +++ b/tools/testing/selftests/bpf/testing_helpers.h @@ -1,5 +1,9 @@ /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ /* Copyright (C) 2020 Facebook, Inc. */ + +#ifndef __TESTING_HELPERS_H +#define __TESTING_HELPERS_H + #include <stdbool.h> #include <bpf/bpf.h> #include <bpf/libbpf.h> @@ -20,5 +24,13 @@ struct test_filter_set; int parse_test_list(const char *s, struct test_filter_set *test_set, bool is_glob_pattern); +int parse_test_list_file(const char *path, + struct test_filter_set *test_set, + bool is_glob_pattern); __u64 read_perf_max_sample_freq(void); +int load_bpf_testmod(bool verbose); +int unload_bpf_testmod(bool verbose); +int kern_sync_rcu(void); + +#endif /* __TESTING_HELPERS_H */ diff --git a/tools/testing/selftests/bpf/verifier/precise.c b/tools/testing/selftests/bpf/verifier/precise.c index 6c03a7d805f9..b8c0aae8e7ec 100644 --- a/tools/testing/selftests/bpf/verifier/precise.c +++ b/tools/testing/selftests/bpf/verifier/precise.c @@ -38,25 +38,24 @@ .fixup_map_array_48b = { 1 }, .result = VERBOSE_ACCEPT, .errstr = - "26: (85) call bpf_probe_read_kernel#113\ - last_idx 26 first_idx 20\ - regs=4 stack=0 before 25\ - regs=4 stack=0 before 24\ - regs=4 stack=0 before 23\ - regs=4 stack=0 before 22\ - regs=4 stack=0 before 20\ - parent didn't have regs=4 stack=0 marks\ - last_idx 19 first_idx 10\ - regs=4 stack=0 before 19\ - regs=200 stack=0 before 18\ - regs=300 stack=0 before 17\ - regs=201 stack=0 before 15\ - regs=201 stack=0 before 14\ - regs=200 stack=0 before 13\ - regs=200 stack=0 before 12\ - regs=200 stack=0 before 11\ - regs=200 stack=0 before 10\ - parent already had regs=0 stack=0 marks", + "mark_precise: frame0: last_idx 26 first_idx 20\ + mark_precise: frame0: regs=r2 stack= before 25\ + mark_precise: frame0: regs=r2 stack= before 24\ + mark_precise: frame0: regs=r2 stack= before 23\ + mark_precise: frame0: regs=r2 stack= before 22\ + mark_precise: frame0: regs=r2 stack= before 20\ + mark_precise: frame0: parent state regs=r2 stack=:\ + mark_precise: frame0: last_idx 19 first_idx 10\ + mark_precise: frame0: regs=r2 stack= before 19\ + mark_precise: frame0: regs=r9 stack= before 18\ + mark_precise: frame0: regs=r8,r9 stack= before 17\ + mark_precise: frame0: regs=r0,r9 stack= before 15\ + mark_precise: frame0: regs=r0,r9 stack= before 14\ + mark_precise: frame0: regs=r9 stack= before 13\ + mark_precise: frame0: regs=r9 stack= before 12\ + mark_precise: frame0: regs=r9 stack= before 11\ + mark_precise: frame0: regs=r9 stack= before 10\ + mark_precise: frame0: parent state regs= stack=:", }, { "precise: test 2", @@ -100,20 +99,20 @@ .flags = BPF_F_TEST_STATE_FREQ, .errstr = "26: (85) call bpf_probe_read_kernel#113\ - last_idx 26 first_idx 22\ - regs=4 stack=0 before 25\ - regs=4 stack=0 before 24\ - regs=4 stack=0 before 23\ - regs=4 stack=0 before 22\ - parent didn't have regs=4 stack=0 marks\ - last_idx 20 first_idx 20\ - regs=4 stack=0 before 20\ - parent didn't have regs=4 stack=0 marks\ - last_idx 19 first_idx 17\ - regs=4 stack=0 before 19\ - regs=200 stack=0 before 18\ - regs=300 stack=0 before 17\ - parent already had regs=0 stack=0 marks", + mark_precise: frame0: last_idx 26 first_idx 22\ + mark_precise: frame0: regs=r2 stack= before 25\ + mark_precise: frame0: regs=r2 stack= before 24\ + mark_precise: frame0: regs=r2 stack= before 23\ + mark_precise: frame0: regs=r2 stack= before 22\ + mark_precise: frame0: parent state regs=r2 stack=:\ + mark_precise: frame0: last_idx 20 first_idx 20\ + mark_precise: frame0: regs=r2 stack= before 20\ + mark_precise: frame0: parent state regs=r2 stack=:\ + mark_precise: frame0: last_idx 19 first_idx 17\ + mark_precise: frame0: regs=r2 stack= before 19\ + mark_precise: frame0: regs=r9 stack= before 18\ + mark_precise: frame0: regs=r8,r9 stack= before 17\ + mark_precise: frame0: parent state regs= stack=:", }, { "precise: cross frame pruning", @@ -153,15 +152,16 @@ }, .prog_type = BPF_PROG_TYPE_XDP, .flags = BPF_F_TEST_STATE_FREQ, - .errstr = "5: (2d) if r4 > r0 goto pc+0\ - last_idx 5 first_idx 5\ - parent didn't have regs=10 stack=0 marks\ - last_idx 4 first_idx 2\ - regs=10 stack=0 before 4\ - regs=10 stack=0 before 3\ - regs=0 stack=1 before 2\ - last_idx 5 first_idx 5\ - parent didn't have regs=1 stack=0 marks", + .errstr = "mark_precise: frame0: last_idx 5 first_idx 5\ + mark_precise: frame0: parent state regs=r4 stack=:\ + mark_precise: frame0: last_idx 4 first_idx 2\ + mark_precise: frame0: regs=r4 stack= before 4\ + mark_precise: frame0: regs=r4 stack= before 3\ + mark_precise: frame0: regs= stack=-8 before 2\ + mark_precise: frame0: falling back to forcing all scalars precise\ + force_precise: frame0: forcing r0 to be precise\ + mark_precise: frame0: last_idx 5 first_idx 5\ + mark_precise: frame0: parent state regs= stack=:", .result = VERBOSE_ACCEPT, .retval = -1, }, @@ -179,16 +179,19 @@ }, .prog_type = BPF_PROG_TYPE_XDP, .flags = BPF_F_TEST_STATE_FREQ, - .errstr = "last_idx 6 first_idx 6\ - parent didn't have regs=10 stack=0 marks\ - last_idx 5 first_idx 3\ - regs=10 stack=0 before 5\ - regs=10 stack=0 before 4\ - regs=0 stack=1 before 3\ - last_idx 6 first_idx 6\ - parent didn't have regs=1 stack=0 marks\ - last_idx 5 first_idx 3\ - regs=1 stack=0 before 5", + .errstr = "mark_precise: frame0: last_idx 6 first_idx 6\ + mark_precise: frame0: parent state regs=r4 stack=:\ + mark_precise: frame0: last_idx 5 first_idx 3\ + mark_precise: frame0: regs=r4 stack= before 5\ + mark_precise: frame0: regs=r4 stack= before 4\ + mark_precise: frame0: regs= stack=-8 before 3\ + mark_precise: frame0: falling back to forcing all scalars precise\ + force_precise: frame0: forcing r0 to be precise\ + force_precise: frame0: forcing r0 to be precise\ + force_precise: frame0: forcing r0 to be precise\ + force_precise: frame0: forcing r0 to be precise\ + mark_precise: frame0: last_idx 6 first_idx 6\ + mark_precise: frame0: parent state regs= stack=:", .result = VERBOSE_ACCEPT, .retval = -1, }, @@ -217,3 +220,39 @@ .errstr = "invalid access to memory, mem_size=1 off=42 size=8", .result = REJECT, }, +{ + "precise: program doesn't prematurely prune branches", + .insns = { + BPF_ALU64_IMM(BPF_MOV, BPF_REG_6, 0x400), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_7, 0), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_8, 0), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_9, 0x80000000), + BPF_ALU64_IMM(BPF_MOD, BPF_REG_6, 0x401), + BPF_JMP_IMM(BPF_JA, 0, 0, 0), + BPF_JMP_REG(BPF_JLE, BPF_REG_6, BPF_REG_9, 2), + BPF_ALU64_IMM(BPF_MOD, BPF_REG_6, 1), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_9, 0), + BPF_JMP_REG(BPF_JLE, BPF_REG_6, BPF_REG_9, 1), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_6, 0), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), + BPF_LD_MAP_FD(BPF_REG_4, 0), + BPF_ALU64_REG(BPF_MOV, BPF_REG_1, BPF_REG_4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_6, 10), + BPF_ALU64_IMM(BPF_MUL, BPF_REG_6, 8192), + BPF_ALU64_REG(BPF_MOV, BPF_REG_1, BPF_REG_0), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_6), + BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_3, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 13 }, + .prog_type = BPF_PROG_TYPE_XDP, + .result = REJECT, + .errstr = "register with unbounded min value is not allowed", +}, diff --git a/tools/testing/selftests/bpf/veristat.c b/tools/testing/selftests/bpf/veristat.c index 1db7185181da..655095810d4a 100644 --- a/tools/testing/selftests/bpf/veristat.c +++ b/tools/testing/selftests/bpf/veristat.c @@ -141,6 +141,7 @@ static struct env { bool verbose; bool debug; bool quiet; + bool force_checkpoints; enum resfmt out_fmt; bool show_version; bool comparison_mode; @@ -209,6 +210,8 @@ static const struct argp_option opts[] = { { "log-level", 'l', "LEVEL", 0, "Verifier log level (default 0 for normal mode, 1 for verbose mode)" }, { "log-fixed", OPT_LOG_FIXED, NULL, 0, "Disable verifier log rotation" }, { "log-size", OPT_LOG_SIZE, "BYTES", 0, "Customize verifier log size (default to 16MB)" }, + { "test-states", 't', NULL, 0, + "Force frequent BPF verifier state checkpointing (set BPF_F_TEST_STATE_FREQ program flag)" }, { "quiet", 'q', NULL, 0, "Quiet mode" }, { "emit", 'e', "SPEC", 0, "Specify stats to be emitted" }, { "sort", 's', "SPEC", 0, "Specify sort order" }, @@ -284,6 +287,9 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state) argp_usage(state); } break; + case 't': + env.force_checkpoints = true; + break; case 'C': env.comparison_mode = true; break; @@ -989,6 +995,9 @@ static int process_prog(const char *filename, struct bpf_object *obj, struct bpf /* increase chances of successful BPF object loading */ fixup_obj(obj, prog, base_filename); + if (env.force_checkpoints) + bpf_program__set_flags(prog, bpf_program__flags(prog) | BPF_F_TEST_STATE_FREQ); + err = bpf_object__load(obj); env.progs_processed++; diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c index 987cf0db5ebc..613321eb84c1 100644 --- a/tools/testing/selftests/bpf/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c @@ -27,6 +27,7 @@ #include <sys/mman.h> #include <net/if.h> #include <poll.h> +#include <time.h> #include "xdp_metadata.h" @@ -134,18 +135,52 @@ static void refill_rx(struct xsk *xsk, __u64 addr) } } -static void verify_xdp_metadata(void *data) +#define NANOSEC_PER_SEC 1000000000 /* 10^9 */ +static __u64 gettime(clockid_t clock_id) +{ + struct timespec t; + int res; + + /* See man clock_gettime(2) for type of clock_id's */ + res = clock_gettime(clock_id, &t); + + if (res < 0) + error(res, errno, "Error with clock_gettime()"); + + return (__u64) t.tv_sec * NANOSEC_PER_SEC + t.tv_nsec; +} + +static void verify_xdp_metadata(void *data, clockid_t clock_id) { struct xdp_meta *meta; meta = data - sizeof(*meta); - printf("rx_timestamp: %llu\n", meta->rx_timestamp); if (meta->rx_hash_err < 0) printf("No rx_hash err=%d\n", meta->rx_hash_err); else printf("rx_hash: 0x%X with RSS type:0x%X\n", meta->rx_hash, meta->rx_hash_type); + + printf("rx_timestamp: %llu (sec:%0.4f)\n", meta->rx_timestamp, + (double)meta->rx_timestamp / NANOSEC_PER_SEC); + if (meta->rx_timestamp) { + __u64 usr_clock = gettime(clock_id); + __u64 xdp_clock = meta->xdp_timestamp; + __s64 delta_X = xdp_clock - meta->rx_timestamp; + __s64 delta_X2U = usr_clock - xdp_clock; + + printf("XDP RX-time: %llu (sec:%0.4f) delta sec:%0.4f (%0.3f usec)\n", + xdp_clock, (double)xdp_clock / NANOSEC_PER_SEC, + (double)delta_X / NANOSEC_PER_SEC, + (double)delta_X / 1000); + + printf("AF_XDP time: %llu (sec:%0.4f) delta sec:%0.4f (%0.3f usec)\n", + usr_clock, (double)usr_clock / NANOSEC_PER_SEC, + (double)delta_X2U / NANOSEC_PER_SEC, + (double)delta_X2U / 1000); + } + } static void verify_skb_metadata(int fd) @@ -193,7 +228,7 @@ static void verify_skb_metadata(int fd) printf("skb hwtstamp is not found!\n"); } -static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd) +static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd, clockid_t clock_id) { const struct xdp_desc *rx_desc; struct pollfd fds[rxq + 1]; @@ -243,7 +278,8 @@ static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd) addr = xsk_umem__add_offset_to_addr(rx_desc->addr); printf("%p: rx_desc[%u]->addr=%llx addr=%llx comp_addr=%llx\n", xsk, idx, rx_desc->addr, addr, comp_addr); - verify_xdp_metadata(xsk_umem__get_data(xsk->umem_area, addr)); + verify_xdp_metadata(xsk_umem__get_data(xsk->umem_area, addr), + clock_id); xsk_ring_cons__release(&xsk->rx, 1); refill_rx(xsk, comp_addr); } @@ -370,6 +406,7 @@ static void timestamping_enable(int fd, int val) int main(int argc, char *argv[]) { + clockid_t clock_id = CLOCK_TAI; int server_fd = -1; int ret; int i; @@ -443,7 +480,7 @@ int main(int argc, char *argv[]) error(1, -ret, "bpf_xdp_attach"); signal(SIGINT, handle_signal); - ret = verify_metadata(rx_xsk, rxq, server_fd); + ret = verify_metadata(rx_xsk, rxq, server_fd, clock_id); close(server_fd); cleanup(); if (ret) diff --git a/tools/testing/selftests/bpf/xdp_metadata.h b/tools/testing/selftests/bpf/xdp_metadata.h index 0c4624dc6f2f..938a729bd307 100644 --- a/tools/testing/selftests/bpf/xdp_metadata.h +++ b/tools/testing/selftests/bpf/xdp_metadata.h @@ -11,6 +11,7 @@ struct xdp_meta { __u64 rx_timestamp; + __u64 xdp_timestamp; __u32 rx_hash; union { __u32 rx_hash_type; diff --git a/tools/testing/selftests/bpf/xsk.h b/tools/testing/selftests/bpf/xsk.h index 04ed8b544712..8da8d557768b 100644 --- a/tools/testing/selftests/bpf/xsk.h +++ b/tools/testing/selftests/bpf/xsk.h @@ -134,6 +134,11 @@ static inline void xsk_ring_prod__submit(struct xsk_ring_prod *prod, __u32 nb) __atomic_store_n(prod->producer, *prod->producer + nb, __ATOMIC_RELEASE); } +static inline void xsk_ring_prod__cancel(struct xsk_ring_prod *prod, __u32 nb) +{ + prod->cached_prod -= nb; +} + static inline __u32 xsk_ring_cons__peek(struct xsk_ring_cons *cons, __u32 nb, __u32 *idx) { __u32 entries = xsk_cons_nb_avail(cons, nb); diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c index f144d0604ddf..218d7f694e5c 100644 --- a/tools/testing/selftests/bpf/xskxceiver.c +++ b/tools/testing/selftests/bpf/xskxceiver.c @@ -76,16 +76,13 @@ #include <asm/barrier.h> #include <linux/if_link.h> #include <linux/if_ether.h> -#include <linux/ip.h> #include <linux/mman.h> -#include <linux/udp.h> #include <arpa/inet.h> #include <net/if.h> #include <locale.h> #include <poll.h> #include <pthread.h> #include <signal.h> -#include <stdbool.h> #include <stdio.h> #include <stdlib.h> #include <string.h> @@ -94,10 +91,8 @@ #include <sys/socket.h> #include <sys/time.h> #include <sys/types.h> -#include <sys/queue.h> #include <time.h> #include <unistd.h> -#include <stdatomic.h> #include "xsk_xdp_progs.skel.h" #include "xsk.h" @@ -109,10 +104,6 @@ static const char *MAC1 = "\x00\x0A\x56\x9E\xEE\x62"; static const char *MAC2 = "\x00\x0A\x56\x9E\xEE\x61"; -static const char *IP1 = "192.168.100.162"; -static const char *IP2 = "192.168.100.161"; -static const u16 UDP_PORT1 = 2020; -static const u16 UDP_PORT2 = 2121; static void __exit_with_error(int error, const char *file, const char *func, int line) { @@ -147,112 +138,25 @@ static void report_failure(struct test_spec *test) test->fail = true; } -static void memset32_htonl(void *dest, u32 val, u32 size) -{ - u32 *ptr = (u32 *)dest; - int i; - - val = htonl(val); - - for (i = 0; i < (size & (~0x3)); i += 4) - ptr[i >> 2] = val; -} - -/* - * Fold a partial checksum - * This function code has been taken from - * Linux kernel include/asm-generic/checksum.h - */ -static __u16 csum_fold(__u32 csum) -{ - u32 sum = (__force u32)csum; - - sum = (sum & 0xffff) + (sum >> 16); - sum = (sum & 0xffff) + (sum >> 16); - return (__force __u16)~sum; -} - -/* - * This function code has been taken from - * Linux kernel lib/checksum.c - */ -static u32 from64to32(u64 x) -{ - /* add up 32-bit and 32-bit for 32+c bit */ - x = (x & 0xffffffff) + (x >> 32); - /* add up carry.. */ - x = (x & 0xffffffff) + (x >> 32); - return (u32)x; -} - -/* - * This function code has been taken from - * Linux kernel lib/checksum.c - */ -static __u32 csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u32 sum) -{ - unsigned long long s = (__force u32)sum; - - s += (__force u32)saddr; - s += (__force u32)daddr; -#ifdef __BIG_ENDIAN__ - s += proto + len; -#else - s += (proto + len) << 8; -#endif - return (__force __u32)from64to32(s); -} - -/* - * This function has been taken from - * Linux kernel include/asm-generic/checksum.h +/* The payload is a word consisting of a packet sequence number in the upper + * 16-bits and a intra packet data sequence number in the lower 16 bits. So the 3rd packet's + * 5th word of data will contain the number (2<<16) | 4 as they are numbered from 0. */ -static __u16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u32 sum) -{ - return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum)); -} - -static u16 udp_csum(u32 saddr, u32 daddr, u32 len, u8 proto, u16 *udp_pkt) +static void write_payload(void *dest, u32 pkt_nb, u32 start, u32 size) { - u32 csum = 0; - u32 cnt = 0; - - /* udp hdr and data */ - for (; cnt < len; cnt += 2) - csum += udp_pkt[cnt >> 1]; + u32 *ptr = (u32 *)dest, i; - return csum_tcpudp_magic(saddr, daddr, len, proto, csum); + start /= sizeof(*ptr); + size /= sizeof(*ptr); + for (i = 0; i < size; i++) + ptr[i] = htonl(pkt_nb << 16 | (i + start)); } static void gen_eth_hdr(struct ifobject *ifobject, struct ethhdr *eth_hdr) { memcpy(eth_hdr->h_dest, ifobject->dst_mac, ETH_ALEN); memcpy(eth_hdr->h_source, ifobject->src_mac, ETH_ALEN); - eth_hdr->h_proto = htons(ETH_P_IP); -} - -static void gen_ip_hdr(struct ifobject *ifobject, struct iphdr *ip_hdr) -{ - ip_hdr->version = IP_PKT_VER; - ip_hdr->ihl = 0x5; - ip_hdr->tos = IP_PKT_TOS; - ip_hdr->tot_len = htons(IP_PKT_SIZE); - ip_hdr->id = 0; - ip_hdr->frag_off = 0; - ip_hdr->ttl = IPDEFTTL; - ip_hdr->protocol = IPPROTO_UDP; - ip_hdr->saddr = ifobject->src_ip; - ip_hdr->daddr = ifobject->dst_ip; - ip_hdr->check = 0; -} - -static void gen_udp_hdr(u32 payload, void *pkt, struct ifobject *ifobject, - struct udphdr *udp_hdr) -{ - udp_hdr->source = htons(ifobject->src_port); - udp_hdr->dest = htons(ifobject->dst_port); - udp_hdr->len = htons(UDP_PKT_SIZE); - memset32_htonl(pkt + PKT_HDR_SIZE, payload, UDP_PKT_DATA_SIZE); + eth_hdr->h_proto = htons(ETH_P_LOOPBACK); } static bool is_umem_valid(struct ifobject *ifobj) @@ -260,19 +164,18 @@ static bool is_umem_valid(struct ifobject *ifobj) return !!ifobj->umem->umem; } -static void gen_udp_csum(struct udphdr *udp_hdr, struct iphdr *ip_hdr) +static u32 mode_to_xdp_flags(enum test_mode mode) { - udp_hdr->check = 0; - udp_hdr->check = - udp_csum(ip_hdr->saddr, ip_hdr->daddr, UDP_PKT_SIZE, IPPROTO_UDP, (u16 *)udp_hdr); + return (mode == TEST_MODE_SKB) ? XDP_FLAGS_SKB_MODE : XDP_FLAGS_DRV_MODE; } -static u32 mode_to_xdp_flags(enum test_mode mode) +static u64 umem_size(struct xsk_umem_info *umem) { - return (mode == TEST_MODE_SKB) ? XDP_FLAGS_SKB_MODE : XDP_FLAGS_DRV_MODE; + return umem->num_frames * umem->frame_size; } -static int xsk_configure_umem(struct xsk_umem_info *umem, void *buffer, u64 size) +static int xsk_configure_umem(struct ifobject *ifobj, struct xsk_umem_info *umem, void *buffer, + u64 size) { struct xsk_umem_config cfg = { .fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS, @@ -292,9 +195,31 @@ static int xsk_configure_umem(struct xsk_umem_info *umem, void *buffer, u64 size return ret; umem->buffer = buffer; + if (ifobj->shared_umem && ifobj->rx_on) { + umem->base_addr = umem_size(umem); + umem->next_buffer = umem_size(umem); + } + return 0; } +static u64 umem_alloc_buffer(struct xsk_umem_info *umem) +{ + u64 addr; + + addr = umem->next_buffer; + umem->next_buffer += umem->frame_size; + if (umem->next_buffer >= umem->base_addr + umem_size(umem)) + umem->next_buffer = umem->base_addr; + + return addr; +} + +static void umem_reset_alloc(struct xsk_umem_info *umem) +{ + umem->next_buffer = 0; +} + static void enable_busy_poll(struct xsk_socket_info *xsk) { int sock_opt; @@ -354,7 +279,7 @@ static bool ifobj_zc_avail(struct ifobject *ifobject) exit_with_error(ENOMEM); } umem->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; - ret = xsk_configure_umem(umem, bufs, umem_sz); + ret = xsk_configure_umem(ifobject, umem, bufs, umem_sz); if (ret) exit_with_error(-ret); @@ -380,7 +305,6 @@ out: static struct option long_options[] = { {"interface", required_argument, 0, 'i'}, {"busy-poll", no_argument, 0, 'b'}, - {"dump-pkts", no_argument, 0, 'D'}, {"verbose", no_argument, 0, 'v'}, {0, 0, 0, 0} }; @@ -391,7 +315,6 @@ static void usage(const char *prog) " Usage: %s [OPTIONS]\n" " Options:\n" " -i, --interface Use interface\n" - " -D, --dump-pkts Dump packets L2 - L5\n" " -v, --verbose Verbose output\n" " -b, --busy-poll Enable busy poll\n"; @@ -415,7 +338,7 @@ static void parse_command_line(struct ifobject *ifobj_tx, struct ifobject *ifobj opterr = 0; for (;;) { - c = getopt_long(argc, argv, "i:Dvb", long_options, &option_index); + c = getopt_long(argc, argv, "i:vb", long_options, &option_index); if (c == -1) break; @@ -437,9 +360,6 @@ static void parse_command_line(struct ifobject *ifobj_tx, struct ifobject *ifobj interface_nb++; break; - case 'D': - opt_pkt_dump = true; - break; case 'v': opt_verbose = true; break; @@ -482,9 +402,6 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx, memset(ifobj->umem, 0, sizeof(*ifobj->umem)); ifobj->umem->num_frames = DEFAULT_UMEM_BUFFERS; ifobj->umem->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; - if (ifobj->shared_umem && ifobj->rx_on) - ifobj->umem->base_addr = DEFAULT_UMEM_BUFFERS * - XSK_UMEM__DEFAULT_FRAME_SIZE; for (j = 0; j < MAX_SOCKETS; j++) { memset(&ifobj->xsk_arr[j], 0, sizeof(ifobj->xsk_arr[j])); @@ -554,24 +471,24 @@ static void test_spec_set_xdp_prog(struct test_spec *test, struct bpf_program *x static void pkt_stream_reset(struct pkt_stream *pkt_stream) { if (pkt_stream) - pkt_stream->rx_pkt_nb = 0; + pkt_stream->current_pkt_nb = 0; } -static struct pkt *pkt_stream_get_pkt(struct pkt_stream *pkt_stream, u32 pkt_nb) +static struct pkt *pkt_stream_get_next_tx_pkt(struct pkt_stream *pkt_stream) { - if (pkt_nb >= pkt_stream->nb_pkts) + if (pkt_stream->current_pkt_nb >= pkt_stream->nb_pkts) return NULL; - return &pkt_stream->pkts[pkt_nb]; + return &pkt_stream->pkts[pkt_stream->current_pkt_nb++]; } static struct pkt *pkt_stream_get_next_rx_pkt(struct pkt_stream *pkt_stream, u32 *pkts_sent) { - while (pkt_stream->rx_pkt_nb < pkt_stream->nb_pkts) { + while (pkt_stream->current_pkt_nb < pkt_stream->nb_pkts) { (*pkts_sent)++; - if (pkt_stream->pkts[pkt_stream->rx_pkt_nb].valid) - return &pkt_stream->pkts[pkt_stream->rx_pkt_nb++]; - pkt_stream->rx_pkt_nb++; + if (pkt_stream->pkts[pkt_stream->current_pkt_nb].valid) + return &pkt_stream->pkts[pkt_stream->current_pkt_nb++]; + pkt_stream->current_pkt_nb++; } return NULL; } @@ -616,9 +533,21 @@ static struct pkt_stream *__pkt_stream_alloc(u32 nb_pkts) return pkt_stream; } -static void pkt_set(struct xsk_umem_info *umem, struct pkt *pkt, u64 addr, u32 len) +static u32 ceil_u32(u32 a, u32 b) +{ + return (a + b - 1) / b; +} + +static u32 pkt_nb_frags(u32 frame_size, struct pkt *pkt) +{ + if (!pkt || !pkt->valid) + return 1; + return ceil_u32(pkt->len, frame_size); +} + +static void pkt_set(struct xsk_umem_info *umem, struct pkt *pkt, int offset, u32 len) { - pkt->addr = addr + umem->base_addr; + pkt->offset = offset; pkt->len = len; if (len > umem->frame_size - XDP_PACKET_HEADROOM - MIN_PKT_SIZE * 2 - umem->frame_headroom) pkt->valid = false; @@ -626,6 +555,11 @@ static void pkt_set(struct xsk_umem_info *umem, struct pkt *pkt, u64 addr, u32 l pkt->valid = true; } +static u32 pkt_get_buffer_len(struct xsk_umem_info *umem, u32 len) +{ + return ceil_u32(len, umem->frame_size) * umem->frame_size; +} + static struct pkt_stream *pkt_stream_generate(struct xsk_umem_info *umem, u32 nb_pkts, u32 pkt_len) { struct pkt_stream *pkt_stream; @@ -635,10 +569,13 @@ static struct pkt_stream *pkt_stream_generate(struct xsk_umem_info *umem, u32 nb if (!pkt_stream) exit_with_error(ENOMEM); + pkt_stream->nb_pkts = nb_pkts; + pkt_stream->max_pkt_len = pkt_len; for (i = 0; i < nb_pkts; i++) { - pkt_set(umem, &pkt_stream->pkts[i], (i % umem->num_frames) * umem->frame_size, - pkt_len); - pkt_stream->pkts[i].payload = i; + struct pkt *pkt = &pkt_stream->pkts[i]; + + pkt_set(umem, pkt, 0, pkt_len); + pkt->pkt_nb = i; } return pkt_stream; @@ -669,8 +606,7 @@ static void __pkt_stream_replace_half(struct ifobject *ifobj, u32 pkt_len, pkt_stream = pkt_stream_clone(umem, ifobj->pkt_stream); for (i = 1; i < ifobj->pkt_stream->nb_pkts; i += 2) - pkt_set(umem, &pkt_stream->pkts[i], - (i % umem->num_frames) * umem->frame_size + offset, pkt_len); + pkt_set(umem, &pkt_stream->pkts[i], offset, pkt_len); ifobj->pkt_stream = pkt_stream; } @@ -694,30 +630,31 @@ static void pkt_stream_receive_half(struct test_spec *test) pkt_stream->pkts[i].valid = false; } -static struct pkt *pkt_generate(struct ifobject *ifobject, u32 pkt_nb) +static u64 pkt_get_addr(struct pkt *pkt, struct xsk_umem_info *umem) { - struct pkt *pkt = pkt_stream_get_pkt(ifobject->pkt_stream, pkt_nb); - struct udphdr *udp_hdr; - struct ethhdr *eth_hdr; - struct iphdr *ip_hdr; - void *data; + if (!pkt->valid) + return pkt->offset; + return pkt->offset + umem_alloc_buffer(umem); +} - if (!pkt) - return NULL; - if (!pkt->valid || pkt->len < MIN_PKT_SIZE) - return pkt; +static void pkt_generate(struct ifobject *ifobject, u64 addr, u32 len, u32 pkt_nb, + u32 bytes_written) +{ + void *data = xsk_umem__get_data(ifobject->umem->buffer, addr); - data = xsk_umem__get_data(ifobject->umem->buffer, pkt->addr); - udp_hdr = (struct udphdr *)(data + sizeof(struct ethhdr) + sizeof(struct iphdr)); - ip_hdr = (struct iphdr *)(data + sizeof(struct ethhdr)); - eth_hdr = (struct ethhdr *)data; + if (len < MIN_PKT_SIZE) + return; - gen_udp_hdr(pkt_nb, data, ifobject, udp_hdr); - gen_ip_hdr(ifobject, ip_hdr); - gen_udp_csum(udp_hdr, ip_hdr); - gen_eth_hdr(ifobject, eth_hdr); + if (!bytes_written) { + gen_eth_hdr(ifobject, data); - return pkt; + len -= PKT_HDR_SIZE; + data += PKT_HDR_SIZE; + } else { + bytes_written -= PKT_HDR_SIZE; + } + + write_payload(data, pkt_nb, bytes_written, len); } static void __pkt_stream_generate_custom(struct ifobject *ifobj, @@ -731,10 +668,14 @@ static void __pkt_stream_generate_custom(struct ifobject *ifobj, exit_with_error(ENOMEM); for (i = 0; i < nb_pkts; i++) { - pkt_stream->pkts[i].addr = pkts[i].addr + ifobj->umem->base_addr; - pkt_stream->pkts[i].len = pkts[i].len; - pkt_stream->pkts[i].payload = i; - pkt_stream->pkts[i].valid = pkts[i].valid; + struct pkt *pkt = &pkt_stream->pkts[i]; + + pkt->offset = pkts[i].offset; + pkt->len = pkts[i].len; + pkt->pkt_nb = i; + pkt->valid = pkts[i].valid; + if (pkt->len > pkt_stream->max_pkt_len) + pkt_stream->max_pkt_len = pkt->len; } ifobj->pkt_stream = pkt_stream; @@ -746,53 +687,62 @@ static void pkt_stream_generate_custom(struct test_spec *test, struct pkt *pkts, __pkt_stream_generate_custom(test->ifobj_rx, pkts, nb_pkts); } -static void pkt_dump(void *pkt, u32 len) -{ - char s[INET_ADDRSTRLEN]; - struct ethhdr *ethhdr; - struct udphdr *udphdr; - struct iphdr *iphdr; - u32 payload, i; - - ethhdr = pkt; - iphdr = pkt + sizeof(*ethhdr); - udphdr = pkt + sizeof(*ethhdr) + sizeof(*iphdr); - - /*extract L2 frame */ - fprintf(stdout, "DEBUG>> L2: dst mac: "); - for (i = 0; i < ETH_ALEN; i++) - fprintf(stdout, "%02X", ethhdr->h_dest[i]); - - fprintf(stdout, "\nDEBUG>> L2: src mac: "); - for (i = 0; i < ETH_ALEN; i++) - fprintf(stdout, "%02X", ethhdr->h_source[i]); - - /*extract L3 frame */ - fprintf(stdout, "\nDEBUG>> L3: ip_hdr->ihl: %02X\n", iphdr->ihl); - fprintf(stdout, "DEBUG>> L3: ip_hdr->saddr: %s\n", - inet_ntop(AF_INET, &iphdr->saddr, s, sizeof(s))); - fprintf(stdout, "DEBUG>> L3: ip_hdr->daddr: %s\n", - inet_ntop(AF_INET, &iphdr->daddr, s, sizeof(s))); - /*extract L4 frame */ - fprintf(stdout, "DEBUG>> L4: udp_hdr->src: %d\n", ntohs(udphdr->source)); - fprintf(stdout, "DEBUG>> L4: udp_hdr->dst: %d\n", ntohs(udphdr->dest)); - /*extract L5 frame */ - payload = ntohl(*((u32 *)(pkt + PKT_HDR_SIZE))); +static void pkt_print_data(u32 *data, u32 cnt) +{ + u32 i; + + for (i = 0; i < cnt; i++) { + u32 seqnum, pkt_nb; - fprintf(stdout, "DEBUG>> L5: payload: %d\n", payload); - fprintf(stdout, "---------------------------------------\n"); + seqnum = ntohl(*data) & 0xffff; + pkt_nb = ntohl(*data) >> 16; + fprintf(stdout, "%u:%u ", pkt_nb, seqnum); + data++; + } } -static bool is_offset_correct(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream, u64 addr, - u64 pkt_stream_addr) +static void pkt_dump(void *pkt, u32 len, bool eth_header) +{ + struct ethhdr *ethhdr = pkt; + u32 i, *data; + + if (eth_header) { + /*extract L2 frame */ + fprintf(stdout, "DEBUG>> L2: dst mac: "); + for (i = 0; i < ETH_ALEN; i++) + fprintf(stdout, "%02X", ethhdr->h_dest[i]); + + fprintf(stdout, "\nDEBUG>> L2: src mac: "); + for (i = 0; i < ETH_ALEN; i++) + fprintf(stdout, "%02X", ethhdr->h_source[i]); + + data = pkt + PKT_HDR_SIZE; + } else { + data = pkt; + } + + /*extract L5 frame */ + fprintf(stdout, "\nDEBUG>> L5: seqnum: "); + pkt_print_data(data, PKT_DUMP_NB_TO_PRINT); + fprintf(stdout, "...."); + if (len > PKT_DUMP_NB_TO_PRINT * sizeof(u32)) { + fprintf(stdout, "\n.... "); + pkt_print_data(data + len / sizeof(u32) - PKT_DUMP_NB_TO_PRINT, + PKT_DUMP_NB_TO_PRINT); + } + fprintf(stdout, "\n---------------------------------------\n"); +} + +static bool is_offset_correct(struct xsk_umem_info *umem, struct pkt *pkt, u64 addr) { u32 headroom = umem->unaligned_mode ? 0 : umem->frame_headroom; - u32 offset = addr % umem->frame_size, expected_offset = 0; + u32 offset = addr % umem->frame_size, expected_offset; + int pkt_offset = pkt->valid ? pkt->offset : 0; - if (!pkt_stream->use_addr_for_fill) - pkt_stream_addr = 0; + if (!umem->unaligned_mode) + pkt_offset = 0; - expected_offset += (pkt_stream_addr + headroom + XDP_PACKET_HEADROOM) % umem->frame_size; + expected_offset = (pkt_offset + headroom + XDP_PACKET_HEADROOM) % umem->frame_size; if (offset == expected_offset) return true; @@ -806,9 +756,9 @@ static bool is_metadata_correct(struct pkt *pkt, void *buffer, u64 addr) void *data = xsk_umem__get_data(buffer, addr); struct xdp_info *meta = data - sizeof(struct xdp_info); - if (meta->count != pkt->payload) { + if (meta->count != pkt->pkt_nb) { ksft_print_msg("[%s] expected meta_count [%d], got meta_count [%d]\n", - __func__, pkt->payload, meta->count); + __func__, pkt->pkt_nb, meta->count); return false; } @@ -818,11 +768,11 @@ static bool is_metadata_correct(struct pkt *pkt, void *buffer, u64 addr) static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len) { void *data = xsk_umem__get_data(buffer, addr); - struct iphdr *iphdr = (struct iphdr *)(data + sizeof(struct ethhdr)); + u32 seqnum, pkt_data; if (!pkt) { ksft_print_msg("[%s] too many packets received\n", __func__); - return false; + goto error; } if (len < MIN_PKT_SIZE || pkt->len < MIN_PKT_SIZE) { @@ -833,28 +783,23 @@ static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len) if (pkt->len != len) { ksft_print_msg("[%s] expected length [%d], got length [%d]\n", __func__, pkt->len, len); - return false; + goto error; } - if (iphdr->version == IP_PKT_VER && iphdr->tos == IP_PKT_TOS) { - u32 seqnum = ntohl(*((u32 *)(data + PKT_HDR_SIZE))); - - if (opt_pkt_dump) - pkt_dump(data, PKT_SIZE); + pkt_data = ntohl(*((u32 *)(data + PKT_HDR_SIZE))); + seqnum = pkt_data >> 16; - if (pkt->payload != seqnum) { - ksft_print_msg("[%s] expected seqnum [%d], got seqnum [%d]\n", - __func__, pkt->payload, seqnum); - return false; - } - } else { - ksft_print_msg("Invalid frame received: "); - ksft_print_msg("[IP_PKT_VER: %02X], [IP_PKT_TOS: %02X]\n", iphdr->version, - iphdr->tos); - return false; + if (pkt->pkt_nb != seqnum) { + ksft_print_msg("[%s] expected seqnum [%d], got seqnum [%d]\n", + __func__, pkt->pkt_nb, seqnum); + goto error; } return true; + +error: + pkt_dump(data, len, true); + return false; } static void kick_tx(struct xsk_socket_info *xsk) @@ -976,7 +921,7 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds) addr = xsk_umem__add_offset_to_addr(addr); if (!is_pkt_valid(pkt, umem->buffer, addr, desc->len) || - !is_offset_correct(umem, pkt_stream, addr, pkt->addr) || + !is_offset_correct(umem, pkt, addr) || (ifobj->use_metadata && !is_metadata_correct(pkt, umem->buffer, addr))) return TEST_FAILURE; @@ -992,8 +937,6 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds) pthread_mutex_lock(&pacing_mutex); pkts_in_flight -= pkts_sent; - if (pkts_in_flight < umem->num_frames) - pthread_cond_signal(&pacing_cond); pthread_mutex_unlock(&pacing_mutex); pkts_sent = 0; } @@ -1001,14 +944,21 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds) return TEST_PASS; } -static int __send_pkts(struct ifobject *ifobject, u32 *pkt_nb, struct pollfd *fds, - bool timeout) +static int __send_pkts(struct ifobject *ifobject, struct pollfd *fds, bool timeout) { struct xsk_socket_info *xsk = ifobject->xsk; + struct xsk_umem_info *umem = ifobject->umem; + u32 i, idx = 0, valid_pkts = 0, buffer_len; bool use_poll = ifobject->use_poll; - u32 i, idx = 0, valid_pkts = 0; int ret; + buffer_len = pkt_get_buffer_len(umem, ifobject->pkt_stream->max_pkt_len); + /* pkts_in_flight might be negative if many invalid packets are sent */ + if (pkts_in_flight >= (int)((umem_size(umem) - BATCH_SIZE * buffer_len) / buffer_len)) { + kick_tx(xsk); + return TEST_CONTINUE; + } + while (xsk_ring_prod__reserve(&xsk->tx, BATCH_SIZE, &idx) < BATCH_SIZE) { if (use_poll) { ret = poll(fds, 1, POLL_TMOUT); @@ -1034,25 +984,21 @@ static int __send_pkts(struct ifobject *ifobject, u32 *pkt_nb, struct pollfd *fd for (i = 0; i < BATCH_SIZE; i++) { struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx + i); - struct pkt *pkt = pkt_generate(ifobject, *pkt_nb); + struct pkt *pkt = pkt_stream_get_next_tx_pkt(ifobject->pkt_stream); if (!pkt) break; - tx_desc->addr = pkt->addr; + tx_desc->addr = pkt_get_addr(pkt, umem); tx_desc->len = pkt->len; - (*pkt_nb)++; - if (pkt->valid) + if (pkt->valid) { valid_pkts++; + pkt_generate(ifobject, tx_desc->addr, tx_desc->len, pkt->pkt_nb, 0); + } } pthread_mutex_lock(&pacing_mutex); pkts_in_flight += valid_pkts; - /* pkts_in_flight might be negative if many invalid packets are sent */ - if (pkts_in_flight >= (int)(ifobject->umem->num_frames - BATCH_SIZE)) { - kick_tx(xsk); - pthread_cond_wait(&pacing_cond, &pacing_mutex); - } pthread_mutex_unlock(&pacing_mutex); xsk_ring_prod__submit(&xsk->tx, i); @@ -1088,18 +1034,21 @@ static void wait_for_tx_completion(struct xsk_socket_info *xsk) static int send_pkts(struct test_spec *test, struct ifobject *ifobject) { + struct pkt_stream *pkt_stream = ifobject->pkt_stream; bool timeout = !is_umem_valid(test->ifobj_rx); struct pollfd fds = { }; - u32 pkt_cnt = 0, ret; + u32 ret; fds.fd = xsk_socket__fd(ifobject->xsk->xsk); fds.events = POLLOUT; - while (pkt_cnt < ifobject->pkt_stream->nb_pkts) { - ret = __send_pkts(ifobject, &pkt_cnt, &fds, timeout); + while (pkt_stream->current_pkt_nb < pkt_stream->nb_pkts) { + ret = __send_pkts(ifobject, &fds, timeout); + if (ret == TEST_CONTINUE && !test->fail) + continue; if ((ret || test->fail) && !timeout) return TEST_FAILURE; - else if (ret == TEST_PASS && timeout) + if (ret == TEST_PASS && timeout) return ret; } @@ -1249,11 +1198,14 @@ static void thread_common_ops_tx(struct test_spec *test, struct ifobject *ifobje ifobject->xsk = &ifobject->xsk_arr[0]; ifobject->xskmap = test->ifobj_rx->xskmap; memcpy(ifobject->umem, test->ifobj_rx->umem, sizeof(struct xsk_umem_info)); + ifobject->umem->base_addr = 0; } -static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream) +static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream, + bool fill_up) { - u32 idx = 0, i, buffers_to_fill; + u32 rx_frame_size = umem->frame_size - XDP_PACKET_HEADROOM; + u32 idx = 0, filled = 0, buffers_to_fill, nb_pkts; int ret; if (umem->num_frames < XSK_RING_PROD__DEFAULT_NUM_DESCS) @@ -1264,22 +1216,33 @@ static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream ret = xsk_ring_prod__reserve(&umem->fq, buffers_to_fill, &idx); if (ret != buffers_to_fill) exit_with_error(ENOSPC); - for (i = 0; i < buffers_to_fill; i++) { - u64 addr; - if (pkt_stream->use_addr_for_fill) { - struct pkt *pkt = pkt_stream_get_pkt(pkt_stream, i); + while (filled < buffers_to_fill) { + struct pkt *pkt = pkt_stream_get_next_rx_pkt(pkt_stream, &nb_pkts); + u64 addr; + u32 i; + + for (i = 0; i < pkt_nb_frags(rx_frame_size, pkt); i++) { + if (!pkt) { + if (!fill_up) + break; + addr = filled * umem->frame_size + umem->base_addr; + } else if (pkt->offset >= 0) { + addr = pkt->offset % umem->frame_size + umem_alloc_buffer(umem); + } else { + addr = pkt->offset + umem_alloc_buffer(umem); + } - if (!pkt) + *xsk_ring_prod__fill_addr(&umem->fq, idx++) = addr; + if (++filled >= buffers_to_fill) break; - addr = pkt->addr; - } else { - addr = i * umem->frame_size; } - - *xsk_ring_prod__fill_addr(&umem->fq, idx++) = addr; } - xsk_ring_prod__submit(&umem->fq, i); + xsk_ring_prod__submit(&umem->fq, filled); + xsk_ring_prod__cancel(&umem->fq, buffers_to_fill - filled); + + pkt_stream_reset(pkt_stream); + umem_reset_alloc(umem); } static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) @@ -1300,12 +1263,10 @@ static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) if (bufs == MAP_FAILED) exit_with_error(errno); - ret = xsk_configure_umem(ifobject->umem, bufs, umem_sz); + ret = xsk_configure_umem(ifobject, ifobject->umem, bufs, umem_sz); if (ret) exit_with_error(-ret); - xsk_populate_fill_ring(ifobject->umem, ifobject->pkt_stream); - xsk_configure_socket(test, ifobject, ifobject->umem, false); ifobject->xsk = &ifobject->xsk_arr[0]; @@ -1313,6 +1274,8 @@ static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) if (!ifobject->rx_on) return; + xsk_populate_fill_ring(ifobject->umem, ifobject->pkt_stream, ifobject->use_fill_ring); + ret = xsk_update_xskmap(ifobject->xskmap, ifobject->xsk->xsk); if (ret) exit_with_error(errno); @@ -1370,12 +1333,8 @@ static void *worker_testapp_validate_rx(void *arg) if (!err && ifobject->validation_func) err = ifobject->validation_func(ifobject); - if (err) { + if (err) report_failure(test); - pthread_mutex_lock(&pacing_mutex); - pthread_cond_signal(&pacing_cond); - pthread_mutex_unlock(&pacing_mutex); - } pthread_exit(NULL); } @@ -1402,11 +1361,20 @@ static void handler(int signum) pthread_exit(NULL); } -static bool xdp_prog_changed(struct test_spec *test, struct ifobject *ifobj) +static bool xdp_prog_changed_rx(struct test_spec *test) { + struct ifobject *ifobj = test->ifobj_rx; + return ifobj->xdp_prog != test->xdp_prog_rx || ifobj->mode != test->mode; } +static bool xdp_prog_changed_tx(struct test_spec *test) +{ + struct ifobject *ifobj = test->ifobj_tx; + + return ifobj->xdp_prog != test->xdp_prog_tx || ifobj->mode != test->mode; +} + static void xsk_reattach_xdp(struct ifobject *ifobj, struct bpf_program *xdp_prog, struct bpf_map *xskmap, enum test_mode mode) { @@ -1433,13 +1401,13 @@ static void xsk_reattach_xdp(struct ifobject *ifobj, struct bpf_program *xdp_pro static void xsk_attach_xdp_progs(struct test_spec *test, struct ifobject *ifobj_rx, struct ifobject *ifobj_tx) { - if (xdp_prog_changed(test, ifobj_rx)) + if (xdp_prog_changed_rx(test)) xsk_reattach_xdp(ifobj_rx, test->xdp_prog_rx, test->xskmap_rx, test->mode); if (!ifobj_tx || ifobj_tx->shared_umem) return; - if (xdp_prog_changed(test, ifobj_tx)) + if (xdp_prog_changed_tx(test)) xsk_reattach_xdp(ifobj_tx, test->xdp_prog_tx, test->xskmap_tx, test->mode); } @@ -1448,9 +1416,11 @@ static int __testapp_validate_traffic(struct test_spec *test, struct ifobject *i { pthread_t t0, t1; - if (ifobj2) + if (ifobj2) { if (pthread_barrier_init(&barr, NULL, 2)) exit_with_error(errno); + pkt_stream_reset(ifobj2->pkt_stream); + } test->current_step++; pkt_stream_reset(ifobj1->pkt_stream); @@ -1493,6 +1463,12 @@ static int testapp_validate_traffic(struct test_spec *test) struct ifobject *ifobj_rx = test->ifobj_rx; struct ifobject *ifobj_tx = test->ifobj_tx; + if ((ifobj_rx->umem->unaligned_mode && !ifobj_rx->unaligned_supp) || + (ifobj_tx->umem->unaligned_mode && !ifobj_tx->unaligned_supp)) { + ksft_test_result_skip("No huge pages present.\n"); + return TEST_SKIP; + } + xsk_attach_xdp_progs(test, ifobj_rx, ifobj_tx); return __testapp_validate_traffic(test, ifobj_rx, ifobj_tx); } @@ -1502,16 +1478,18 @@ static int testapp_validate_traffic_single_thread(struct test_spec *test, struct return __testapp_validate_traffic(test, ifobj, NULL); } -static void testapp_teardown(struct test_spec *test) +static int testapp_teardown(struct test_spec *test) { int i; test_spec_set_name(test, "TEARDOWN"); for (i = 0; i < MAX_TEARDOWN_ITER; i++) { if (testapp_validate_traffic(test)) - return; + return TEST_FAILURE; test_spec_reset(test); } + + return TEST_PASS; } static void swap_directions(struct ifobject **ifobj1, struct ifobject **ifobj2) @@ -1526,20 +1504,23 @@ static void swap_directions(struct ifobject **ifobj1, struct ifobject **ifobj2) *ifobj2 = tmp_ifobj; } -static void testapp_bidi(struct test_spec *test) +static int testapp_bidi(struct test_spec *test) { + int res; + test_spec_set_name(test, "BIDIRECTIONAL"); test->ifobj_tx->rx_on = true; test->ifobj_rx->tx_on = true; test->total_steps = 2; if (testapp_validate_traffic(test)) - return; + return TEST_FAILURE; print_verbose("Switching Tx/Rx vectors\n"); swap_directions(&test->ifobj_rx, &test->ifobj_tx); - __testapp_validate_traffic(test, test->ifobj_rx, test->ifobj_tx); + res = __testapp_validate_traffic(test, test->ifobj_rx, test->ifobj_tx); swap_directions(&test->ifobj_rx, &test->ifobj_tx); + return res; } static void swap_xsk_resources(struct ifobject *ifobj_tx, struct ifobject *ifobj_rx) @@ -1556,160 +1537,139 @@ static void swap_xsk_resources(struct ifobject *ifobj_tx, struct ifobject *ifobj exit_with_error(errno); } -static void testapp_bpf_res(struct test_spec *test) +static int testapp_bpf_res(struct test_spec *test) { test_spec_set_name(test, "BPF_RES"); test->total_steps = 2; test->nb_sockets = 2; if (testapp_validate_traffic(test)) - return; + return TEST_FAILURE; swap_xsk_resources(test->ifobj_tx, test->ifobj_rx); - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_headroom(struct test_spec *test) +static int testapp_headroom(struct test_spec *test) { test_spec_set_name(test, "UMEM_HEADROOM"); test->ifobj_rx->umem->frame_headroom = UMEM_HEADROOM_TEST_SIZE; - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_stats_rx_dropped(struct test_spec *test) +static int testapp_stats_rx_dropped(struct test_spec *test) { test_spec_set_name(test, "STAT_RX_DROPPED"); + if (test->mode == TEST_MODE_ZC) { + ksft_test_result_skip("Can not run RX_DROPPED test for ZC mode\n"); + return TEST_SKIP; + } + pkt_stream_replace_half(test, MIN_PKT_SIZE * 4, 0); test->ifobj_rx->umem->frame_headroom = test->ifobj_rx->umem->frame_size - XDP_PACKET_HEADROOM - MIN_PKT_SIZE * 3; pkt_stream_receive_half(test); test->ifobj_rx->validation_func = validate_rx_dropped; - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_stats_tx_invalid_descs(struct test_spec *test) +static int testapp_stats_tx_invalid_descs(struct test_spec *test) { test_spec_set_name(test, "STAT_TX_INVALID"); pkt_stream_replace_half(test, XSK_UMEM__INVALID_FRAME_SIZE, 0); test->ifobj_tx->validation_func = validate_tx_invalid_descs; - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_stats_rx_full(struct test_spec *test) +static int testapp_stats_rx_full(struct test_spec *test) { test_spec_set_name(test, "STAT_RX_FULL"); - pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, PKT_SIZE); + pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE); test->ifobj_rx->pkt_stream = pkt_stream_generate(test->ifobj_rx->umem, - DEFAULT_UMEM_BUFFERS, PKT_SIZE); - if (!test->ifobj_rx->pkt_stream) - exit_with_error(ENOMEM); + DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE); test->ifobj_rx->xsk->rxqsize = DEFAULT_UMEM_BUFFERS; test->ifobj_rx->release_rx = false; test->ifobj_rx->validation_func = validate_rx_full; - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_stats_fill_empty(struct test_spec *test) +static int testapp_stats_fill_empty(struct test_spec *test) { test_spec_set_name(test, "STAT_RX_FILL_EMPTY"); - pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, PKT_SIZE); + pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE); test->ifobj_rx->pkt_stream = pkt_stream_generate(test->ifobj_rx->umem, - DEFAULT_UMEM_BUFFERS, PKT_SIZE); - if (!test->ifobj_rx->pkt_stream) - exit_with_error(ENOMEM); + DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE); test->ifobj_rx->use_fill_ring = false; test->ifobj_rx->validation_func = validate_fill_empty; - testapp_validate_traffic(test); -} - -/* Simple test */ -static bool hugepages_present(struct ifobject *ifobject) -{ - size_t mmap_sz = 2 * ifobject->umem->num_frames * ifobject->umem->frame_size; - void *bufs; - - bufs = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, - MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB | MAP_HUGE_2MB, -1, 0); - if (bufs == MAP_FAILED) - return false; - - mmap_sz = ceil_u64(mmap_sz, HUGEPAGE_SIZE) * HUGEPAGE_SIZE; - munmap(bufs, mmap_sz); - return true; + return testapp_validate_traffic(test); } -static bool testapp_unaligned(struct test_spec *test) +static int testapp_unaligned(struct test_spec *test) { - if (!hugepages_present(test->ifobj_tx)) { - ksft_test_result_skip("No 2M huge pages present.\n"); - return false; - } - test_spec_set_name(test, "UNALIGNED_MODE"); test->ifobj_tx->umem->unaligned_mode = true; test->ifobj_rx->umem->unaligned_mode = true; - /* Let half of the packets straddle a buffer boundrary */ - pkt_stream_replace_half(test, PKT_SIZE, -PKT_SIZE / 2); - test->ifobj_rx->pkt_stream->use_addr_for_fill = true; - testapp_validate_traffic(test); + /* Let half of the packets straddle a 4K buffer boundary */ + pkt_stream_replace_half(test, MIN_PKT_SIZE, -MIN_PKT_SIZE / 2); - return true; + return testapp_validate_traffic(test); } -static void testapp_single_pkt(struct test_spec *test) +static int testapp_single_pkt(struct test_spec *test) { - struct pkt pkts[] = {{0x1000, PKT_SIZE, 0, true}}; + struct pkt pkts[] = {{0, MIN_PKT_SIZE, 0, true}}; pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)); - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_invalid_desc(struct test_spec *test) +static int testapp_invalid_desc(struct test_spec *test) { - u64 umem_size = test->ifobj_tx->umem->num_frames * test->ifobj_tx->umem->frame_size; + struct xsk_umem_info *umem = test->ifobj_tx->umem; + u64 umem_size = umem->num_frames * umem->frame_size; struct pkt pkts[] = { /* Zero packet address allowed */ - {0, PKT_SIZE, 0, true}, + {0, MIN_PKT_SIZE, 0, true}, /* Allowed packet */ - {0x1000, PKT_SIZE, 0, true}, + {0, MIN_PKT_SIZE, 0, true}, /* Straddling the start of umem */ - {-2, PKT_SIZE, 0, false}, + {-2, MIN_PKT_SIZE, 0, false}, /* Packet too large */ - {0x2000, XSK_UMEM__INVALID_FRAME_SIZE, 0, false}, + {0, XSK_UMEM__INVALID_FRAME_SIZE, 0, false}, /* Up to end of umem allowed */ - {umem_size - PKT_SIZE, PKT_SIZE, 0, true}, + {umem_size - MIN_PKT_SIZE - 2 * umem->frame_size, MIN_PKT_SIZE, 0, true}, /* After umem ends */ - {umem_size, PKT_SIZE, 0, false}, + {umem_size, MIN_PKT_SIZE, 0, false}, /* Straddle the end of umem */ - {umem_size - PKT_SIZE / 2, PKT_SIZE, 0, false}, - /* Straddle a page boundrary */ - {0x3000 - PKT_SIZE / 2, PKT_SIZE, 0, false}, - /* Straddle a 2K boundrary */ - {0x3800 - PKT_SIZE / 2, PKT_SIZE, 0, true}, + {umem_size - MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, false}, + /* Straddle a 4K boundary */ + {0x1000 - MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, false}, + /* Straddle a 2K boundary */ + {0x800 - MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, true}, /* Valid packet for synch so that something is received */ - {0x4000, PKT_SIZE, 0, true}}; + {0, MIN_PKT_SIZE, 0, true}}; - if (test->ifobj_tx->umem->unaligned_mode) { - /* Crossing a page boundrary allowed */ + if (umem->unaligned_mode) { + /* Crossing a page boundary allowed */ pkts[7].valid = true; } - if (test->ifobj_tx->umem->frame_size == XSK_UMEM__DEFAULT_FRAME_SIZE / 2) { - /* Crossing a 2K frame size boundrary not allowed */ + if (umem->frame_size == XSK_UMEM__DEFAULT_FRAME_SIZE / 2) { + /* Crossing a 2K frame size boundary not allowed */ pkts[8].valid = false; } if (test->ifobj_tx->shared_umem) { - pkts[4].addr += umem_size; - pkts[5].addr += umem_size; - pkts[6].addr += umem_size; + pkts[4].offset += umem_size; + pkts[5].offset += umem_size; + pkts[6].offset += umem_size; } pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)); - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_xdp_drop(struct test_spec *test) +static int testapp_xdp_drop(struct test_spec *test) { struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs; struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs; @@ -1719,10 +1679,10 @@ static void testapp_xdp_drop(struct test_spec *test) skel_rx->maps.xsk, skel_tx->maps.xsk); pkt_stream_receive_half(test); - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_xdp_metadata_count(struct test_spec *test) +static int testapp_xdp_metadata_count(struct test_spec *test) { struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs; struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs; @@ -1743,10 +1703,10 @@ static void testapp_xdp_metadata_count(struct test_spec *test) if (bpf_map_update_elem(bpf_map__fd(data_map), &key, &count, BPF_ANY)) exit_with_error(errno); - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_poll_txq_tmout(struct test_spec *test) +static int testapp_poll_txq_tmout(struct test_spec *test) { test_spec_set_name(test, "POLL_TXQ_FULL"); @@ -1754,14 +1714,14 @@ static void testapp_poll_txq_tmout(struct test_spec *test) /* create invalid frame by set umem frame_size and pkt length equal to 2048 */ test->ifobj_tx->umem->frame_size = 2048; pkt_stream_replace(test, 2 * DEFAULT_PKT_CNT, 2048); - testapp_validate_traffic_single_thread(test, test->ifobj_tx); + return testapp_validate_traffic_single_thread(test, test->ifobj_tx); } -static void testapp_poll_rxq_tmout(struct test_spec *test) +static int testapp_poll_rxq_tmout(struct test_spec *test) { test_spec_set_name(test, "POLL_RXQ_EMPTY"); test->ifobj_rx->use_poll = true; - testapp_validate_traffic_single_thread(test, test->ifobj_rx); + return testapp_validate_traffic_single_thread(test, test->ifobj_rx); } static int xsk_load_xdp_programs(struct ifobject *ifobj) @@ -1778,25 +1738,30 @@ static void xsk_unload_xdp_programs(struct ifobject *ifobj) xsk_xdp_progs__destroy(ifobj->xdp_progs); } +/* Simple test */ +static bool hugepages_present(void) +{ + size_t mmap_sz = 2 * DEFAULT_UMEM_BUFFERS * XSK_UMEM__DEFAULT_FRAME_SIZE; + void *bufs; + + bufs = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, -1, MAP_HUGE_2MB); + if (bufs == MAP_FAILED) + return false; + + mmap_sz = ceil_u64(mmap_sz, HUGEPAGE_SIZE) * HUGEPAGE_SIZE; + munmap(bufs, mmap_sz); + return true; +} + static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *src_mac, - const char *dst_ip, const char *src_ip, const u16 dst_port, - const u16 src_port, thread_func_t func_ptr) + thread_func_t func_ptr) { - struct in_addr ip; int err; memcpy(ifobj->dst_mac, dst_mac, ETH_ALEN); memcpy(ifobj->src_mac, src_mac, ETH_ALEN); - inet_aton(dst_ip, &ip); - ifobj->dst_ip = ip.s_addr; - - inet_aton(src_ip, &ip); - ifobj->src_ip = ip.s_addr; - - ifobj->dst_port = dst_port; - ifobj->src_port = src_port; - ifobj->func_ptr = func_ptr; err = xsk_load_xdp_programs(ifobj); @@ -1804,94 +1769,87 @@ static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char * printf("Error loading XDP program\n"); exit_with_error(err); } + + if (hugepages_present()) + ifobj->unaligned_supp = true; } static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_type type) { + int ret = TEST_SKIP; + switch (type) { case TEST_TYPE_STATS_RX_DROPPED: - if (mode == TEST_MODE_ZC) { - ksft_test_result_skip("Can not run RX_DROPPED test for ZC mode\n"); - return; - } - testapp_stats_rx_dropped(test); + ret = testapp_stats_rx_dropped(test); break; case TEST_TYPE_STATS_TX_INVALID_DESCS: - testapp_stats_tx_invalid_descs(test); + ret = testapp_stats_tx_invalid_descs(test); break; case TEST_TYPE_STATS_RX_FULL: - testapp_stats_rx_full(test); + ret = testapp_stats_rx_full(test); break; case TEST_TYPE_STATS_FILL_EMPTY: - testapp_stats_fill_empty(test); + ret = testapp_stats_fill_empty(test); break; case TEST_TYPE_TEARDOWN: - testapp_teardown(test); + ret = testapp_teardown(test); break; case TEST_TYPE_BIDI: - testapp_bidi(test); + ret = testapp_bidi(test); break; case TEST_TYPE_BPF_RES: - testapp_bpf_res(test); + ret = testapp_bpf_res(test); break; case TEST_TYPE_RUN_TO_COMPLETION: test_spec_set_name(test, "RUN_TO_COMPLETION"); - testapp_validate_traffic(test); + ret = testapp_validate_traffic(test); break; case TEST_TYPE_RUN_TO_COMPLETION_SINGLE_PKT: test_spec_set_name(test, "RUN_TO_COMPLETION_SINGLE_PKT"); - testapp_single_pkt(test); + ret = testapp_single_pkt(test); break; case TEST_TYPE_RUN_TO_COMPLETION_2K_FRAME: test_spec_set_name(test, "RUN_TO_COMPLETION_2K_FRAME_SIZE"); test->ifobj_tx->umem->frame_size = 2048; test->ifobj_rx->umem->frame_size = 2048; - pkt_stream_replace(test, DEFAULT_PKT_CNT, PKT_SIZE); - testapp_validate_traffic(test); + pkt_stream_replace(test, DEFAULT_PKT_CNT, MIN_PKT_SIZE); + ret = testapp_validate_traffic(test); break; case TEST_TYPE_RX_POLL: test->ifobj_rx->use_poll = true; test_spec_set_name(test, "POLL_RX"); - testapp_validate_traffic(test); + ret = testapp_validate_traffic(test); break; case TEST_TYPE_TX_POLL: test->ifobj_tx->use_poll = true; test_spec_set_name(test, "POLL_TX"); - testapp_validate_traffic(test); + ret = testapp_validate_traffic(test); break; case TEST_TYPE_POLL_TXQ_TMOUT: - testapp_poll_txq_tmout(test); + ret = testapp_poll_txq_tmout(test); break; case TEST_TYPE_POLL_RXQ_TMOUT: - testapp_poll_rxq_tmout(test); + ret = testapp_poll_rxq_tmout(test); break; case TEST_TYPE_ALIGNED_INV_DESC: test_spec_set_name(test, "ALIGNED_INV_DESC"); - testapp_invalid_desc(test); + ret = testapp_invalid_desc(test); break; case TEST_TYPE_ALIGNED_INV_DESC_2K_FRAME: test_spec_set_name(test, "ALIGNED_INV_DESC_2K_FRAME_SIZE"); test->ifobj_tx->umem->frame_size = 2048; test->ifobj_rx->umem->frame_size = 2048; - testapp_invalid_desc(test); + ret = testapp_invalid_desc(test); break; case TEST_TYPE_UNALIGNED_INV_DESC: - if (!hugepages_present(test->ifobj_tx)) { - ksft_test_result_skip("No 2M huge pages present.\n"); - return; - } test_spec_set_name(test, "UNALIGNED_INV_DESC"); test->ifobj_tx->umem->unaligned_mode = true; test->ifobj_rx->umem->unaligned_mode = true; - testapp_invalid_desc(test); + ret = testapp_invalid_desc(test); break; case TEST_TYPE_UNALIGNED_INV_DESC_4K1_FRAME: { u64 page_size, umem_size; - if (!hugepages_present(test->ifobj_tx)) { - ksft_test_result_skip("No 2M huge pages present.\n"); - return; - } test_spec_set_name(test, "UNALIGNED_INV_DESC_4K1_FRAME_SIZE"); /* Odd frame size so the UMEM doesn't end near a page boundary. */ test->ifobj_tx->umem->frame_size = 4001; @@ -1903,29 +1861,28 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_ */ page_size = sysconf(_SC_PAGESIZE); umem_size = test->ifobj_tx->umem->num_frames * test->ifobj_tx->umem->frame_size; - assert(umem_size % page_size > PKT_SIZE); - assert(umem_size % page_size < page_size - PKT_SIZE); - testapp_invalid_desc(test); + assert(umem_size % page_size > MIN_PKT_SIZE); + assert(umem_size % page_size < page_size - MIN_PKT_SIZE); + ret = testapp_invalid_desc(test); break; } case TEST_TYPE_UNALIGNED: - if (!testapp_unaligned(test)) - return; + ret = testapp_unaligned(test); break; case TEST_TYPE_HEADROOM: - testapp_headroom(test); + ret = testapp_headroom(test); break; case TEST_TYPE_XDP_DROP_HALF: - testapp_xdp_drop(test); + ret = testapp_xdp_drop(test); break; case TEST_TYPE_XDP_METADATA_COUNT: - testapp_xdp_metadata_count(test); + ret = testapp_xdp_metadata_count(test); break; default: break; } - if (!test->fail) + if (ret == TEST_PASS) ksft_test_result_pass("PASS: %s %s%s\n", mode_string(test), busy_poll_string(test), test->name); pkt_stream_restore_default(test); @@ -2030,14 +1987,12 @@ int main(int argc, char **argv) modes++; } - init_iface(ifobj_rx, MAC1, MAC2, IP1, IP2, UDP_PORT1, UDP_PORT2, - worker_testapp_validate_rx); - init_iface(ifobj_tx, MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1, - worker_testapp_validate_tx); + init_iface(ifobj_rx, MAC1, MAC2, worker_testapp_validate_rx); + init_iface(ifobj_tx, MAC2, MAC1, worker_testapp_validate_tx); test_spec_init(&test, ifobj_tx, ifobj_rx, 0); - tx_pkt_stream_default = pkt_stream_generate(ifobj_tx->umem, DEFAULT_PKT_CNT, PKT_SIZE); - rx_pkt_stream_default = pkt_stream_generate(ifobj_rx->umem, DEFAULT_PKT_CNT, PKT_SIZE); + tx_pkt_stream_default = pkt_stream_generate(ifobj_tx->umem, DEFAULT_PKT_CNT, MIN_PKT_SIZE); + rx_pkt_stream_default = pkt_stream_generate(ifobj_rx->umem, DEFAULT_PKT_CNT, MIN_PKT_SIZE); if (!tx_pkt_stream_default || !rx_pkt_stream_default) exit_with_error(ENOMEM); test.tx_pkt_stream_default = tx_pkt_stream_default; diff --git a/tools/testing/selftests/bpf/xskxceiver.h b/tools/testing/selftests/bpf/xskxceiver.h index c535aeab2ca3..aaf27e067640 100644 --- a/tools/testing/selftests/bpf/xskxceiver.h +++ b/tools/testing/selftests/bpf/xskxceiver.h @@ -30,22 +30,14 @@ #define TEST_PASS 0 #define TEST_FAILURE -1 #define TEST_CONTINUE 1 +#define TEST_SKIP 2 #define MAX_INTERFACES 2 #define MAX_INTERFACE_NAME_CHARS 16 #define MAX_SOCKETS 2 #define MAX_TEST_NAME_SIZE 32 #define MAX_TEARDOWN_ITER 10 -#define PKT_HDR_SIZE (sizeof(struct ethhdr) + sizeof(struct iphdr) + \ - sizeof(struct udphdr)) -#define MIN_ETH_PKT_SIZE 64 -#define ETH_FCS_SIZE 4 -#define MIN_PKT_SIZE (MIN_ETH_PKT_SIZE - ETH_FCS_SIZE) -#define PKT_SIZE (MIN_PKT_SIZE) -#define IP_PKT_SIZE (PKT_SIZE - sizeof(struct ethhdr)) -#define IP_PKT_VER 0x4 -#define IP_PKT_TOS 0x9 -#define UDP_PKT_SIZE (IP_PKT_SIZE - sizeof(struct iphdr)) -#define UDP_PKT_DATA_SIZE (UDP_PKT_SIZE - sizeof(struct udphdr)) +#define PKT_HDR_SIZE (sizeof(struct ethhdr) + 2) /* Just to align the data in the packet */ +#define MIN_PKT_SIZE 64 #define USLEEP_MAX 10000 #define SOCK_RECONF_CTR 10 #define BATCH_SIZE 64 @@ -57,6 +49,7 @@ #define UMEM_HEADROOM_TEST_SIZE 128 #define XSK_UMEM__INVALID_FRAME_SIZE (XSK_UMEM__DEFAULT_FRAME_SIZE + 1) #define HUGEPAGE_SIZE (2 * 1024 * 1024) +#define PKT_DUMP_NB_TO_PRINT 16 #define print_verbose(x...) do { if (opt_verbose) ksft_print_msg(x); } while (0) @@ -93,13 +86,13 @@ enum test_type { TEST_TYPE_MAX }; -static bool opt_pkt_dump; static bool opt_verbose; struct xsk_umem_info { struct xsk_ring_prod fq; struct xsk_ring_cons cq; struct xsk_umem *umem; + u64 next_buffer; u32 num_frames; u32 frame_headroom; void *buffer; @@ -118,17 +111,17 @@ struct xsk_socket_info { }; struct pkt { - u64 addr; + int offset; u32 len; - u32 payload; + u32 pkt_nb; bool valid; }; struct pkt_stream { u32 nb_pkts; - u32 rx_pkt_nb; + u32 current_pkt_nb; struct pkt *pkts; - bool use_addr_for_fill; + u32 max_pkt_len; }; struct ifobject; @@ -148,11 +141,7 @@ struct ifobject { struct bpf_program *xdp_prog; enum test_mode mode; int ifindex; - u32 dst_ip; - u32 src_ip; u32 bind_flags; - u16 src_port; - u16 dst_port; bool tx_on; bool rx_on; bool use_poll; @@ -161,6 +150,7 @@ struct ifobject { bool release_rx; bool shared_umem; bool use_metadata; + bool unaligned_supp; u8 dst_mac[ETH_ALEN]; u8 src_mac[ETH_ALEN]; }; @@ -184,7 +174,6 @@ struct test_spec { pthread_barrier_t barr; pthread_mutex_t pacing_mutex = PTHREAD_MUTEX_INITIALIZER; -pthread_cond_t pacing_cond = PTHREAD_COND_INITIALIZER; int pkts_in_flight; diff --git a/tools/testing/selftests/drivers/net/bonding/bond-eth-type-change.sh b/tools/testing/selftests/drivers/net/bonding/bond-eth-type-change.sh index 5cdd22048ba7..862e947e17c7 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond-eth-type-change.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond-eth-type-change.sh @@ -53,7 +53,6 @@ bond_test_enslave_type_change() # restore ARPHRD_ETHER type by enslaving such device ip link set dev "$devbond2" master "$devbond0" check_err $? "could not enslave $devbond2 to $devbond0" - ip link set dev "$devbond1" nomaster bond_check_flags "$devbond0" diff --git a/tools/testing/selftests/drivers/net/mlxsw/egress_vid_classification.sh b/tools/testing/selftests/drivers/net/mlxsw/egress_vid_classification.sh index 0cf9e47e3209..a5c2aec52898 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/egress_vid_classification.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/egress_vid_classification.sh @@ -16,10 +16,9 @@ # +----------------|--+ +--|-----------------+ # | | # +----------------|-------------------------|-----------------+ -# | SW | | | +# | SW $swp1 + + $swp2 | +# | | | | # | +--------------|-------------------------|---------------+ | -# | | $swp1 + + $swp2 | | -# | | | | | | # | | $swp1.10 + + $swp2.10 | | # | | | | # | | br0 | | diff --git a/tools/testing/selftests/drivers/net/mlxsw/ingress_rif_conf_1d.sh b/tools/testing/selftests/drivers/net/mlxsw/ingress_rif_conf_1d.sh index df2b09966886..7d7f862c809c 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/ingress_rif_conf_1d.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/ingress_rif_conf_1d.sh @@ -15,10 +15,9 @@ # +----------------|--+ +--|-----------------+ # | | # +----------------|-------------------------|-----------------+ -# | SW | | | +# | SW $swp1 + + $swp2 | +# | | | | # | +--------------|-------------------------|---------------+ | -# | | $swp1 + + $swp2 | | -# | | | | | | # | | $swp1.10 + + $swp2.10 | | # | | | | # | | br0 | | diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index c12df57d5539..7f3ab2a93ed6 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -84,6 +84,7 @@ TEST_GEN_FILES += ip_local_port_range TEST_GEN_FILES += bind_wildcard TEST_PROGS += test_vxlan_mdb.sh TEST_PROGS += test_bridge_neigh_suppress.sh +TEST_PROGS += test_vxlan_nolocalbypass.sh TEST_FILES := settings diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 21ca91473c09..05b5c4af7a08 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -585,6 +585,20 @@ ipv4_ping_novrf() done # + # out, but don't use gateway if peer is not on link + # + a=${NSB_IP} + log_start + run_cmd ping -c 1 -w 1 -r ${a} + log_test_addr ${a} $? 0 "ping out (don't route), peer on link" + + a=${NSB_LO_IP} + log_start + show_hint "Fails since peer is not on link" + run_cmd ping -c 1 -w 1 -r ${a} + log_test_addr ${a} $? 1 "ping out (don't route), peer not on link" + + # # in # for a in ${NSA_IP} ${NSA_LO_IP} @@ -1098,6 +1112,59 @@ test_ipv4_md5_vrf__global_server__bind_ifindex0() set_sysctl net.ipv4.tcp_l3mdev_accept="$old_tcp_l3mdev_accept" } +ipv4_tcp_dontroute() +{ + local syncookies=$1 + local nsa_syncookies + local nsb_syncookies + local a + + # + # Link local connection tests (SO_DONTROUTE). + # Connections should succeed only when the remote IP address is + # on link (doesn't need to be routed through a gateway). + # + + nsa_syncookies=$(ip netns exec "${NSA}" sysctl -n net.ipv4.tcp_syncookies) + nsb_syncookies=$(ip netns exec "${NSB}" sysctl -n net.ipv4.tcp_syncookies) + ip netns exec "${NSA}" sysctl -wq net.ipv4.tcp_syncookies=${syncookies} + ip netns exec "${NSB}" sysctl -wq net.ipv4.tcp_syncookies=${syncookies} + + # Test with eth1 address (on link). + + a=${NSB_IP} + log_start + do_run_cmd nettest -B -N "${NSA}" -O "${NSB}" -r ${a} --client-dontroute + log_test_addr ${a} $? 0 "SO_DONTROUTE client, syncookies=${syncookies}" + + a=${NSB_IP} + log_start + do_run_cmd nettest -B -N "${NSA}" -O "${NSB}" -r ${a} --server-dontroute + log_test_addr ${a} $? 0 "SO_DONTROUTE server, syncookies=${syncookies}" + + # Test with loopback address (routed). + # + # The client would use the eth1 address as source IP by default. + # Therefore, we need to use the -c option here, to force the use of the + # routed (loopback) address as source IP (so that the server will try + # to respond to a routed address and not a link local one). + + a=${NSB_LO_IP} + log_start + show_hint "Should fail 'Network is unreachable' since server is not on link" + do_run_cmd nettest -B -N "${NSA}" -O "${NSB}" -c "${NSA_LO_IP}" -r ${a} --client-dontroute + log_test_addr ${a} $? 1 "SO_DONTROUTE client, syncookies=${syncookies}" + + a=${NSB_LO_IP} + log_start + show_hint "Should timeout since server cannot respond (client is not on link)" + do_run_cmd nettest -B -N "${NSA}" -O "${NSB}" -c "${NSA_LO_IP}" -r ${a} --server-dontroute + log_test_addr ${a} $? 2 "SO_DONTROUTE server, syncookies=${syncookies}" + + ip netns exec "${NSB}" sysctl -wq net.ipv4.tcp_syncookies=${nsb_syncookies} + ip netns exec "${NSA}" sysctl -wq net.ipv4.tcp_syncookies=${nsa_syncookies} +} + ipv4_tcp_novrf() { local a @@ -1217,6 +1284,9 @@ ipv4_tcp_novrf() log_test_addr ${a} $? 1 "No server, device client, local conn" ipv4_tcp_md5_novrf + + ipv4_tcp_dontroute 0 + ipv4_tcp_dontroute 2 } ipv4_tcp_vrf() @@ -1585,6 +1655,23 @@ ipv4_udp_novrf() log_start run_cmd nettest -D -d ${NSA_DEV} -r ${a} log_test_addr ${a} $? 2 "No server, device client, local conn" + + # + # Link local connection tests (SO_DONTROUTE). + # Connections should succeed only when the remote IP address is + # on link (doesn't need to be routed through a gateway). + # + + a=${NSB_IP} + log_start + do_run_cmd nettest -B -D -N "${NSA}" -O "${NSB}" -r ${a} --client-dontroute + log_test_addr ${a} $? 0 "SO_DONTROUTE client" + + a=${NSB_LO_IP} + log_start + show_hint "Should fail 'Network is unreachable' since server is not on link" + do_run_cmd nettest -B -D -N "${NSA}" -O "${NSB}" -r ${a} --client-dontroute + log_test_addr ${a} $? 1 "SO_DONTROUTE client" } ipv4_udp_vrf() diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index a474c60fe348..9d0062b542e5 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -83,6 +83,7 @@ TEST_PROGS = bridge_igmp.sh \ tc_chains.sh \ tc_flower_router.sh \ tc_flower.sh \ + tc_flower_l2_miss.sh \ tc_mpls_l2vpn.sh \ tc_police.sh \ tc_shblocks.sh \ diff --git a/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh b/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh index fa6a88c50750..de2b2d5480dd 100755 --- a/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh +++ b/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh @@ -1,6 +1,28 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +# +------------------------+ +----------------------+ +# | H1 (vrf) | | H2 (vrf) | +# | + $h1.555 | | + $h2 | +# | | 192.0.2.1/28 | | | 192.0.2.130/28 | +# | | 2001:db8:1::1/64 | | | 2001:db8:2::2/64 | +# | | | | | | +# | + $h1 | | | | +# +----|-------------------+ +--|-------------------+ +# | | +# +----|--------------------------------------------------|-------------------+ +# | SW | | | +# | +--|-------------------------------+ + $swp2 | +# | | + $swp1 | 192.0.2.129/28 | +# | | vid 555 | 2001:db8:2::1/64 | +# | | | | +# | | + BR1 (802.1q) | | +# | | vid 555 pvid untagged | | +# | | 192.0.2.2/28 | | +# | | 2001:db8:1::2/64 | | +# | +----------------------------------+ | +# +---------------------------------------------------------------------------+ + ALL_TESTS=" ping_ipv4 ping_ipv6 @@ -41,7 +63,7 @@ h2_destroy() router_create() { - ip link add name br1 type bridge vlan_filtering 1 + ip link add name br1 type bridge vlan_filtering 1 vlan_default_pvid 0 ip link set dev br1 up ip link set dev $swp1 master br1 diff --git a/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh b/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh new file mode 100755 index 000000000000..37b0369b5246 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh @@ -0,0 +1,350 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +-----------------------+ +----------------------+ +# | H1 (vrf) | | H2 (vrf) | +# | + $h1 | | $h2 + | +# | | 192.0.2.1/28 | | 192.0.2.2/28 | | +# | | 2001:db8:1::1/64 | | 2001:db8:1::2/64 | | +# +----|------------------+ +------------------|---+ +# | | +# +----|-------------------------------------------------------------------|---+ +# | SW | | | +# | +-|-------------------------------------------------------------------|-+ | +# | | + $swp1 BR $swp2 + | | +# | +-----------------------------------------------------------------------+ | +# +----------------------------------------------------------------------------+ + +ALL_TESTS=" + test_l2_miss_unicast + test_l2_miss_multicast + test_l2_miss_ll_multicast + test_l2_miss_broadcast +" + +NUM_NETIFS=4 +source lib.sh +source tc_common.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/28 2001:db8:1::1/64 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.2/28 2001:db8:1::2/64 +} + +h2_destroy() +{ + simple_if_fini $h2 192.0.2.2/28 2001:db8:1::2/64 +} + +switch_create() +{ + ip link add name br1 up type bridge + ip link set dev $swp1 master br1 + ip link set dev $swp1 up + ip link set dev $swp2 master br1 + ip link set dev $swp2 up + + tc qdisc add dev $swp2 clsact +} + +switch_destroy() +{ + tc qdisc del dev $swp2 clsact + + ip link set dev $swp2 down + ip link set dev $swp2 nomaster + ip link set dev $swp1 down + ip link set dev $swp1 nomaster + ip link del dev br1 +} + +test_l2_miss_unicast() +{ + local dmac=00:01:02:03:04:05 + local dip=192.0.2.2 + local sip=192.0.2.1 + + RET=0 + + # Unknown unicast. + tc filter add dev $swp2 egress protocol ipv4 handle 101 pref 1 \ + flower indev $swp1 l2_miss true dst_mac $dmac src_ip $sip \ + dst_ip $dip action pass + # Known unicast. + tc filter add dev $swp2 egress protocol ipv4 handle 102 pref 1 \ + flower indev $swp1 l2_miss false dst_mac $dmac src_ip $sip \ + dst_ip $dip action pass + + # Before adding FDB entry. + $MZ $h1 -a own -b $dmac -t ip -A $sip -B $dip -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 1 + check_err $? "Unknown unicast filter was not hit before adding FDB entry" + + tc_check_packets "dev $swp2 egress" 102 0 + check_err $? "Known unicast filter was hit before adding FDB entry" + + # Adding FDB entry. + bridge fdb replace $dmac dev $swp2 master static + + $MZ $h1 -a own -b $dmac -t ip -A $sip -B $dip -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 1 + check_err $? "Unknown unicast filter was hit after adding FDB entry" + + tc_check_packets "dev $swp2 egress" 102 1 + check_err $? "Known unicast filter was not hit after adding FDB entry" + + # Deleting FDB entry. + bridge fdb del $dmac dev $swp2 master static + + $MZ $h1 -a own -b $dmac -t ip -A $sip -B $dip -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 2 + check_err $? "Unknown unicast filter was not hit after deleting FDB entry" + + tc_check_packets "dev $swp2 egress" 102 1 + check_err $? "Known unicast filter was hit after deleting FDB entry" + + tc filter del dev $swp2 egress protocol ipv4 pref 1 handle 102 flower + tc filter del dev $swp2 egress protocol ipv4 pref 1 handle 101 flower + + log_test "L2 miss - Unicast" +} + +test_l2_miss_multicast_common() +{ + local proto=$1; shift + local sip=$1; shift + local dip=$1; shift + local mode=$1; shift + local name=$1; shift + + RET=0 + + # Unregistered multicast. + tc filter add dev $swp2 egress protocol $proto handle 101 pref 1 \ + flower indev $swp1 l2_miss true src_ip $sip dst_ip $dip \ + action pass + # Registered multicast. + tc filter add dev $swp2 egress protocol $proto handle 102 pref 1 \ + flower indev $swp1 l2_miss false src_ip $sip dst_ip $dip \ + action pass + + # Before adding MDB entry. + $MZ $mode $h1 -t ip -A $sip -B $dip -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 1 + check_err $? "Unregistered multicast filter was not hit before adding MDB entry" + + tc_check_packets "dev $swp2 egress" 102 0 + check_err $? "Registered multicast filter was hit before adding MDB entry" + + # Adding MDB entry. + bridge mdb replace dev br1 port $swp2 grp $dip permanent + + $MZ $mode $h1 -t ip -A $sip -B $dip -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 1 + check_err $? "Unregistered multicast filter was hit after adding MDB entry" + + tc_check_packets "dev $swp2 egress" 102 1 + check_err $? "Registered multicast filter was not hit after adding MDB entry" + + # Deleting MDB entry. + bridge mdb del dev br1 port $swp2 grp $dip + + $MZ $mode $h1 -t ip -A $sip -B $dip -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 2 + check_err $? "Unregistered multicast filter was not hit after deleting MDB entry" + + tc_check_packets "dev $swp2 egress" 102 1 + check_err $? "Registered multicast filter was hit after deleting MDB entry" + + tc filter del dev $swp2 egress protocol $proto pref 1 handle 102 flower + tc filter del dev $swp2 egress protocol $proto pref 1 handle 101 flower + + log_test "L2 miss - Multicast ($name)" +} + +test_l2_miss_multicast_ipv4() +{ + local proto="ipv4" + local sip=192.0.2.1 + local dip=239.1.1.1 + local mode="-4" + local name="IPv4" + + test_l2_miss_multicast_common $proto $sip $dip $mode $name +} + +test_l2_miss_multicast_ipv6() +{ + local proto="ipv6" + local sip=2001:db8:1::1 + local dip=ff0e::1 + local mode="-6" + local name="IPv6" + + test_l2_miss_multicast_common $proto $sip $dip $mode $name +} + +test_l2_miss_multicast() +{ + # Configure $swp2 as a multicast router port so that it will forward + # both registered and unregistered multicast traffic. + bridge link set dev $swp2 mcast_router 2 + + # Forwarding according to MDB entries only takes place when the bridge + # detects that there is a valid querier in the network. Set the bridge + # as the querier and assign it a valid IPv6 link-local address to be + # used as the source address for MLD queries. + ip link set dev br1 type bridge mcast_querier 1 + ip -6 address add fe80::1/64 nodad dev br1 + # Wait the default Query Response Interval (10 seconds) for the bridge + # to determine that there are no other queriers in the network. + sleep 10 + + test_l2_miss_multicast_ipv4 + test_l2_miss_multicast_ipv6 + + ip -6 address del fe80::1/64 dev br1 + ip link set dev br1 type bridge mcast_querier 0 + bridge link set dev $swp2 mcast_router 1 +} + +test_l2_miss_multicast_common2() +{ + local name=$1; shift + local dmac=$1; shift + local dip=224.0.0.1 + local sip=192.0.2.1 + +} + +test_l2_miss_ll_multicast_common() +{ + local proto=$1; shift + local dmac=$1; shift + local sip=$1; shift + local dip=$1; shift + local mode=$1; shift + local name=$1; shift + + RET=0 + + tc filter add dev $swp2 egress protocol $proto handle 101 pref 1 \ + flower indev $swp1 l2_miss true dst_mac $dmac src_ip $sip \ + dst_ip $dip action pass + + $MZ $mode $h1 -a own -b $dmac -t ip -A $sip -B $dip -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 1 + check_err $? "Filter was not hit" + + tc filter del dev $swp2 egress protocol $proto pref 1 handle 101 flower + + log_test "L2 miss - Link-local multicast ($name)" +} + +test_l2_miss_ll_multicast_ipv4() +{ + local proto=ipv4 + local dmac=01:00:5e:00:00:01 + local sip=192.0.2.1 + local dip=224.0.0.1 + local mode="-4" + local name="IPv4" + + test_l2_miss_ll_multicast_common $proto $dmac $sip $dip $mode $name +} + +test_l2_miss_ll_multicast_ipv6() +{ + local proto=ipv6 + local dmac=33:33:00:00:00:01 + local sip=2001:db8:1::1 + local dip=ff02::1 + local mode="-6" + local name="IPv6" + + test_l2_miss_ll_multicast_common $proto $dmac $sip $dip $mode $name +} + +test_l2_miss_ll_multicast() +{ + test_l2_miss_ll_multicast_ipv4 + test_l2_miss_ll_multicast_ipv6 +} + +test_l2_miss_broadcast() +{ + local dmac=ff:ff:ff:ff:ff:ff + local smac=00:01:02:03:04:05 + + RET=0 + + tc filter add dev $swp2 egress protocol all handle 101 pref 1 \ + flower l2_miss true dst_mac $dmac src_mac $smac \ + action pass + tc filter add dev $swp2 egress protocol all handle 102 pref 1 \ + flower l2_miss false dst_mac $dmac src_mac $smac \ + action pass + + $MZ $h1 -a $smac -b $dmac -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 0 + check_err $? "L2 miss filter was hit when should not" + + tc_check_packets "dev $swp2 egress" 102 1 + check_err $? "L2 no miss filter was not hit when should" + + tc filter del dev $swp2 egress protocol all pref 1 handle 102 flower + tc filter del dev $swp2 egress protocol all pref 1 handle 101 flower + + log_test "L2 miss - Broadcast" +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + h1_create + h2_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h2_destroy + h1_destroy + vrf_cleanup +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 29f0c99d9a46..85474e029784 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -37,6 +37,7 @@ evts_ns1="" evts_ns2="" evts_ns1_pid=0 evts_ns2_pid=0 +stats_dumped=0 declare -A all_tests declare -a only_tests_ids @@ -90,6 +91,7 @@ init_partial() fi done + stats_dumped=0 check_invert=0 validate_checksum=$checksum FAILING_LINKS="" @@ -353,6 +355,9 @@ fail_test() { ret=1 failed_tests[${TEST_COUNT}]="${TEST_NAME}" + + [ "${stats_dumped}" = 0 ] && dump_stats + stats_dumped=1 } get_failed_tests_ids() @@ -1142,7 +1147,6 @@ chk_csum_nr() local csum_ns1=${1:-0} local csum_ns2=${2:-0} local count - local dump_stats local extra_msg="" local allow_multi_errors_ns1=0 local allow_multi_errors_ns2=0 @@ -1166,7 +1170,6 @@ chk_csum_nr() { [ "$count" -lt $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 1 ]; }; then echo "[fail] got $count data checksum error[s] expected $csum_ns1" fail_test - dump_stats=1 else echo -n "[ ok ]" fi @@ -1180,11 +1183,9 @@ chk_csum_nr() { [ "$count" -lt $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 1 ]; }; then echo "[fail] got $count data checksum error[s] expected $csum_ns2" fail_test - dump_stats=1 else echo -n "[ ok ]" fi - [ "${dump_stats}" = 1 ] && dump_stats echo "$extra_msg" } @@ -1195,7 +1196,6 @@ chk_fail_nr() local fail_rx=$2 local ns_invert=${3:-""} local count - local dump_stats local ns_tx=$ns1 local ns_rx=$ns2 local extra_msg="" @@ -1227,7 +1227,6 @@ chk_fail_nr() { [ "$count" -gt "$fail_tx" ] && [ $allow_tx_lost -eq 1 ]; }; then echo "[fail] got $count MP_FAIL[s] TX expected $fail_tx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi @@ -1242,13 +1241,10 @@ chk_fail_nr() { [ "$count" -gt "$fail_rx" ] && [ $allow_rx_lost -eq 1 ]; }; then echo "[fail] got $count MP_FAIL[s] RX expected $fail_rx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi - [ "${dump_stats}" = 1 ] && dump_stats - echo "$extra_msg" } @@ -1258,7 +1254,6 @@ chk_fclose_nr() local fclose_rx=$2 local ns_invert=$3 local count - local dump_stats local ns_tx=$ns2 local ns_rx=$ns1 local extra_msg=" " @@ -1276,7 +1271,6 @@ chk_fclose_nr() if [ "$count" != "$fclose_tx" ]; then echo "[fail] got $count MP_FASTCLOSE[s] TX expected $fclose_tx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi @@ -1288,13 +1282,10 @@ chk_fclose_nr() if [ "$count" != "$fclose_rx" ]; then echo "[fail] got $count MP_FASTCLOSE[s] RX expected $fclose_rx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi - [ "${dump_stats}" = 1 ] && dump_stats - echo "$extra_msg" } @@ -1304,7 +1295,6 @@ chk_rst_nr() local rst_rx=$2 local ns_invert=${3:-""} local count - local dump_stats local ns_tx=$ns1 local ns_rx=$ns2 local extra_msg="" @@ -1321,7 +1311,6 @@ chk_rst_nr() if [ $count -lt $rst_tx ]; then echo "[fail] got $count MP_RST[s] TX expected $rst_tx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi @@ -1332,13 +1321,10 @@ chk_rst_nr() if [ "$count" -lt "$rst_rx" ]; then echo "[fail] got $count MP_RST[s] RX expected $rst_rx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi - [ "${dump_stats}" = 1 ] && dump_stats - echo "$extra_msg" } @@ -1347,7 +1333,6 @@ chk_infi_nr() local infi_tx=$1 local infi_rx=$2 local count - local dump_stats printf "%-${nr_blank}s %s" " " "itx" count=$(ip netns exec $ns2 nstat -as | grep InfiniteMapTx | awk '{print $2}') @@ -1355,7 +1340,6 @@ chk_infi_nr() if [ "$count" != "$infi_tx" ]; then echo "[fail] got $count infinite map[s] TX expected $infi_tx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi @@ -1366,12 +1350,9 @@ chk_infi_nr() if [ "$count" != "$infi_rx" ]; then echo "[fail] got $count infinite map[s] RX expected $infi_rx" fail_test - dump_stats=1 else echo "[ ok ]" fi - - [ "${dump_stats}" = 1 ] && dump_stats } chk_join_nr() @@ -1386,7 +1367,6 @@ chk_join_nr() local infi_nr=${8:-0} local corrupted_pkts=${9:-0} local count - local dump_stats local with_cookie local title="${TEST_NAME}" @@ -1400,7 +1380,6 @@ chk_join_nr() if [ "$count" != "$syn_nr" ]; then echo "[fail] got $count JOIN[s] syn expected $syn_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi @@ -1418,7 +1397,6 @@ chk_join_nr() else echo "[fail] got $count JOIN[s] synack expected $syn_ack_nr" fail_test - dump_stats=1 fi else echo -n "[ ok ]" @@ -1430,11 +1408,9 @@ chk_join_nr() if [ "$count" != "$ack_nr" ]; then echo "[fail] got $count JOIN[s] ack expected $ack_nr" fail_test - dump_stats=1 else echo "[ ok ]" fi - [ "${dump_stats}" = 1 ] && dump_stats if [ $validate_checksum -eq 1 ]; then chk_csum_nr $csum_ns1 $csum_ns2 chk_fail_nr $fail_nr $fail_nr @@ -1494,7 +1470,6 @@ chk_add_nr() local mis_syn_nr=${7:-0} local mis_ack_nr=${8:-0} local count - local dump_stats local timeout timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout) @@ -1508,18 +1483,16 @@ chk_add_nr() if [ "$count" != "$add_nr" ] && { [ "$timeout" -gt 1 ] || [ "$count" -lt "$add_nr" ]; }; then echo "[fail] got $count ADD_ADDR[s] expected $add_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi echo -n " - echo " - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtEchoAdd | awk '{print $2}') + count=$(ip netns exec $ns1 nstat -as MPTcpExtEchoAdd | grep MPTcpExtEchoAdd | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$echo_nr" ]; then echo "[fail] got $count ADD_ADDR echo[s] expected $echo_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi @@ -1531,7 +1504,6 @@ chk_add_nr() if [ "$count" != "$port_nr" ]; then echo "[fail] got $count ADD_ADDR[s] with a port-number expected $port_nr" fail_test - dump_stats=1 else echo "[ ok ]" fi @@ -1544,7 +1516,6 @@ chk_add_nr() echo "[fail] got $count JOIN[s] syn with a different \ port-number expected $syn_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi @@ -1557,7 +1528,6 @@ chk_add_nr() echo "[fail] got $count JOIN[s] synack with a different \ port-number expected $syn_ack_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi @@ -1570,7 +1540,6 @@ chk_add_nr() echo "[fail] got $count JOIN[s] ack with a different \ port-number expected $ack_nr" fail_test - dump_stats=1 else echo "[ ok ]" fi @@ -1583,7 +1552,6 @@ chk_add_nr() echo "[fail] got $count JOIN[s] syn with a mismatched \ port-number expected $mis_syn_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi @@ -1596,15 +1564,45 @@ chk_add_nr() echo "[fail] got $count JOIN[s] ack with a mismatched \ port-number expected $mis_ack_nr" fail_test - dump_stats=1 else echo "[ ok ]" fi else echo "" fi +} + +chk_add_tx_nr() +{ + local add_tx_nr=$1 + local echo_tx_nr=$2 + local timeout + local count + + timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout) + + printf "%-${nr_blank}s %s" " " "add TX" + count=$(ip netns exec $ns1 nstat -as MPTcpExtAddAddrTx | grep MPTcpExtAddAddrTx | awk '{print $2}') + [ -z "$count" ] && count=0 + + # if the test configured a short timeout tolerate greater then expected + # add addrs options, due to retransmissions + if [ "$count" != "$add_tx_nr" ] && { [ "$timeout" -gt 1 ] || [ "$count" -lt "$add_tx_nr" ]; }; then + echo "[fail] got $count ADD_ADDR[s] TX, expected $add_tx_nr" + fail_test + else + echo -n "[ ok ]" + fi - [ "${dump_stats}" = 1 ] && dump_stats + echo -n " - echo TX " + count=$(ip netns exec $ns2 nstat -as MPTcpExtEchoAddTx | grep MPTcpExtEchoAddTx | awk '{print $2}') + [ -z "$count" ] && count=0 + if [ "$count" != "$echo_tx_nr" ]; then + echo "[fail] got $count ADD_ADDR echo[s] TX, expected $echo_tx_nr" + fail_test + else + echo "[ ok ]" + fi } chk_rm_nr() @@ -1614,7 +1612,6 @@ chk_rm_nr() local invert local simult local count - local dump_stats local addr_ns=$ns1 local subflow_ns=$ns2 local extra_msg="" @@ -1636,12 +1633,11 @@ chk_rm_nr() fi printf "%-${nr_blank}s %s" " " "rm " - count=$(ip netns exec $addr_ns nstat -as | grep MPTcpExtRmAddr | awk '{print $2}') + count=$(ip netns exec $addr_ns nstat -as MPTcpExtRmAddr | grep MPTcpExtRmAddr | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$rm_addr_nr" ]; then echo "[fail] got $count RM_ADDR[s] expected $rm_addr_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi @@ -1665,19 +1661,32 @@ chk_rm_nr() else echo "[fail] got $count RM_SUBFLOW[s] expected in range [$rm_subflow_nr:$((rm_subflow_nr*2))]" fail_test - dump_stats=1 fi return fi if [ "$count" != "$rm_subflow_nr" ]; then echo "[fail] got $count RM_SUBFLOW[s] expected $rm_subflow_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi - [ "${dump_stats}" = 1 ] && dump_stats + echo "$extra_msg" +} + +chk_rm_tx_nr() +{ + local rm_addr_tx_nr=$1 + + printf "%-${nr_blank}s %s" " " "rm TX " + count=$(ip netns exec $ns2 nstat -as MPTcpExtRmAddrTx | grep MPTcpExtRmAddrTx | awk '{print $2}') + [ -z "$count" ] && count=0 + if [ "$count" != "$rm_addr_tx_nr" ]; then + echo "[fail] got $count RM_ADDR[s] expected $rm_addr_tx_nr" + fail_test + else + echo -n "[ ok ]" + fi echo "$extra_msg" } @@ -1687,7 +1696,6 @@ chk_prio_nr() local mp_prio_nr_tx=$1 local mp_prio_nr_rx=$2 local count - local dump_stats printf "%-${nr_blank}s %s" " " "ptx" count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPPrioTx | awk '{print $2}') @@ -1695,7 +1703,6 @@ chk_prio_nr() if [ "$count" != "$mp_prio_nr_tx" ]; then echo "[fail] got $count MP_PRIO[s] TX expected $mp_prio_nr_tx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi @@ -1706,12 +1713,9 @@ chk_prio_nr() if [ "$count" != "$mp_prio_nr_rx" ]; then echo "[fail] got $count MP_PRIO[s] RX expected $mp_prio_nr_rx" fail_test - dump_stats=1 else echo "[ ok ]" fi - - [ "${dump_stats}" = 1 ] && dump_stats } chk_subflow_nr() @@ -1743,7 +1747,6 @@ chk_subflow_nr() ss -N $ns1 -tOni ss -N $ns1 -tOni | grep token ip -n $ns1 mptcp endpoint - dump_stats fi } @@ -1783,7 +1786,6 @@ chk_mptcp_info() if [ "$dump_stats" = 1 ]; then ss -N $ns1 -inmHM ss -N $ns2 -inmHM - dump_stats fi } @@ -1961,6 +1963,7 @@ signal_address_tests() pm_nl_add_endpoint $ns1 10.0.2.1 flags signal run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 + chk_add_tx_nr 1 1 chk_add_nr 1 1 fi @@ -2142,6 +2145,7 @@ add_addr_timeout_tests() pm_nl_add_endpoint $ns1 10.0.2.1 flags signal run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow chk_join_nr 1 1 1 + chk_add_tx_nr 4 4 chk_add_nr 4 0 fi @@ -2187,6 +2191,7 @@ remove_tests() pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 0 -1 slow chk_join_nr 1 1 1 + chk_rm_tx_nr 1 chk_rm_nr 1 1 fi @@ -2285,6 +2290,7 @@ remove_tests() pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow chk_join_nr 3 3 3 + chk_rm_tx_nr 0 chk_rm_nr 0 3 simult fi diff --git a/tools/testing/selftests/net/nettest.c b/tools/testing/selftests/net/nettest.c index ee9a72982705..39a0e01f8554 100644 --- a/tools/testing/selftests/net/nettest.c +++ b/tools/testing/selftests/net/nettest.c @@ -76,7 +76,9 @@ struct sock_args { has_grp:1, has_expected_laddr:1, has_expected_raddr:1, - bind_test_only:1; + bind_test_only:1, + client_dontroute:1, + server_dontroute:1; unsigned short port; @@ -611,6 +613,18 @@ static int set_dsfield(int sd, int version, int dsfield) return 0; } +static int set_dontroute(int sd) +{ + unsigned int one = 1; + + if (setsockopt(sd, SOL_SOCKET, SO_DONTROUTE, &one, sizeof(one)) < 0) { + log_err_errno("setsockopt(SO_DONTROUTE)"); + return -1; + } + + return 0; +} + static int str_to_uint(const char *str, int min, int max, unsigned int *value) { int number; @@ -1351,6 +1365,14 @@ static int msock_init(struct sock_args *args, int server) if (set_dsfield(sd, AF_INET, args->dsfield) != 0) goto out_err; + if (server) { + if (args->server_dontroute && set_dontroute(sd) != 0) + goto out_err; + } else { + if (args->client_dontroute && set_dontroute(sd) != 0) + goto out_err; + } + if (args->dev && bind_to_device(sd, args->dev) != 0) goto out_err; else if (args->use_setsockopt && @@ -1482,6 +1504,9 @@ static int lsock_init(struct sock_args *args) if (set_dsfield(sd, args->version, args->dsfield) != 0) goto err; + if (args->server_dontroute && set_dontroute(sd) != 0) + goto err; + if (args->dev && bind_to_device(sd, args->dev) != 0) goto err; else if (args->use_setsockopt && @@ -1698,6 +1723,9 @@ static int connectsock(void *addr, socklen_t alen, struct sock_args *args) if (set_dsfield(sd, args->version, args->dsfield) != 0) goto err; + if (args->client_dontroute && set_dontroute(sd) != 0) + goto err; + if (args->dev && bind_to_device(sd, args->dev) != 0) goto err; else if (args->use_setsockopt && @@ -1905,10 +1933,14 @@ static int ipc_parent(int cpid, int fd, struct sock_args *args) #define GETOPT_STR "sr:l:c:Q:p:t:g:P:DRn:M:X:m:d:I:BN:O:SUCi6xL:0:1:2:3:Fbqf" #define OPT_FORCE_BIND_KEY_IFINDEX 1001 #define OPT_NO_BIND_KEY_IFINDEX 1002 +#define OPT_CLIENT_DONTROUTE 1003 +#define OPT_SERVER_DONTROUTE 1004 static struct option long_opts[] = { {"force-bind-key-ifindex", 0, 0, OPT_FORCE_BIND_KEY_IFINDEX}, {"no-bind-key-ifindex", 0, 0, OPT_NO_BIND_KEY_IFINDEX}, + {"client-dontroute", 0, 0, OPT_CLIENT_DONTROUTE}, + {"server-dontroute", 0, 0, OPT_SERVER_DONTROUTE}, {0, 0, 0, 0} }; @@ -1954,6 +1986,12 @@ static void print_usage(char *prog) " --no-bind-key-ifindex: Force TCP_MD5SIG_FLAG_IFINDEX off\n" " --force-bind-key-ifindex: Force TCP_MD5SIG_FLAG_IFINDEX on\n" " (default: only if -I is passed)\n" + " --client-dontroute: don't use gateways for client socket: send\n" + " packets only if destination is on link (see\n" + " SO_DONTROUTE in socket(7))\n" + " --server-dontroute: don't use gateways for server socket: send\n" + " packets only if destination is on link (see\n" + " SO_DONTROUTE in socket(7))\n" "\n" " -g grp multicast group (e.g., 239.1.1.1)\n" " -i interactive mode (default is echo and terminate)\n" @@ -2076,6 +2114,12 @@ int main(int argc, char *argv[]) case OPT_NO_BIND_KEY_IFINDEX: args.bind_key_ifindex = -1; break; + case OPT_CLIENT_DONTROUTE: + args.client_dontroute = 1; + break; + case OPT_SERVER_DONTROUTE: + args.server_dontroute = 1; + break; case 'X': args.client_pw = optarg; break; diff --git a/tools/testing/selftests/net/test_vxlan_nolocalbypass.sh b/tools/testing/selftests/net/test_vxlan_nolocalbypass.sh new file mode 100755 index 000000000000..46067db53068 --- /dev/null +++ b/tools/testing/selftests/net/test_vxlan_nolocalbypass.sh @@ -0,0 +1,240 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test is for checking the [no]localbypass VXLAN device option. The test +# configures two VXLAN devices in the same network namespace and a tc filter on +# the loopback device that drops encapsulated packets. The test sends packets +# from the first VXLAN device and verifies that by default these packets are +# received by the second VXLAN device. The test then enables the nolocalbypass +# option and verifies that packets are no longer received by the second VXLAN +# device. + +ret=0 +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +TESTS=" + nolocalbypass +" +VERBOSE=0 +PAUSE_ON_FAIL=no +PAUSE=no + +################################################################################ +# Utilities + +log_test() +{ + local rc=$1 + local expected=$2 + local msg="$3" + + if [ ${rc} -eq ${expected} ]; then + printf "TEST: %-60s [ OK ]\n" "${msg}" + nsuccess=$((nsuccess+1)) + else + ret=1 + nfail=$((nfail+1)) + printf "TEST: %-60s [FAIL]\n" "${msg}" + if [ "$VERBOSE" = "1" ]; then + echo " rc=$rc, expected $expected" + fi + + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi + + if [ "${PAUSE}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + + [ "$VERBOSE" = "1" ] && echo +} + +run_cmd() +{ + local cmd="$1" + local out + local stderr="2>/dev/null" + + if [ "$VERBOSE" = "1" ]; then + printf "COMMAND: $cmd\n" + stderr= + fi + + out=$(eval $cmd $stderr) + rc=$? + if [ "$VERBOSE" = "1" -a -n "$out" ]; then + echo " $out" + fi + + return $rc +} + +tc_check_packets() +{ + local ns=$1; shift + local id=$1; shift + local handle=$1; shift + local count=$1; shift + local pkts + + sleep 0.1 + pkts=$(tc -n $ns -j -s filter show $id \ + | jq ".[] | select(.options.handle == $handle) | \ + .options.actions[0].stats.packets") + [[ $pkts == $count ]] +} + +################################################################################ +# Setup + +setup() +{ + ip netns add ns1 + + ip -n ns1 link set dev lo up + ip -n ns1 address add 192.0.2.1/32 dev lo + ip -n ns1 address add 198.51.100.1/32 dev lo + + ip -n ns1 link add name vx0 up type vxlan id 100 local 198.51.100.1 \ + dstport 4789 nolearning + ip -n ns1 link add name vx1 up type vxlan id 100 dstport 4790 +} + +cleanup() +{ + ip netns del ns1 &> /dev/null +} + +################################################################################ +# Tests + +nolocalbypass() +{ + local smac=00:01:02:03:04:05 + local dmac=00:0a:0b:0c:0d:0e + + run_cmd "bridge -n ns1 fdb add $dmac dev vx0 self static dst 192.0.2.1 port 4790" + + run_cmd "tc -n ns1 qdisc add dev vx1 clsact" + run_cmd "tc -n ns1 filter add dev vx1 ingress pref 1 handle 101 proto all flower src_mac $smac dst_mac $dmac action pass" + + run_cmd "tc -n ns1 qdisc add dev lo clsact" + run_cmd "tc -n ns1 filter add dev lo ingress pref 1 handle 101 proto ip flower ip_proto udp dst_port 4790 action drop" + + run_cmd "ip -n ns1 -d link show dev vx0 | grep ' localbypass'" + log_test $? 0 "localbypass enabled" + + run_cmd "ip netns exec ns1 mausezahn vx0 -a $smac -b $dmac -c 1 -p 100 -q" + + tc_check_packets "ns1" "dev vx1 ingress" 101 1 + log_test $? 0 "Packet received by local VXLAN device - localbypass" + + run_cmd "ip -n ns1 link set dev vx0 type vxlan nolocalbypass" + + run_cmd "ip -n ns1 -d link show dev vx0 | grep 'nolocalbypass'" + log_test $? 0 "localbypass disabled" + + run_cmd "ip netns exec ns1 mausezahn vx0 -a $smac -b $dmac -c 1 -p 100 -q" + + tc_check_packets "ns1" "dev vx1 ingress" 101 1 + log_test $? 0 "Packet not received by local VXLAN device - nolocalbypass" + + run_cmd "ip -n ns1 link set dev vx0 type vxlan localbypass" + + run_cmd "ip -n ns1 -d link show dev vx0 | grep ' localbypass'" + log_test $? 0 "localbypass enabled" + + run_cmd "ip netns exec ns1 mausezahn vx0 -a $smac -b $dmac -c 1 -p 100 -q" + + tc_check_packets "ns1" "dev vx1 ingress" 101 2 + log_test $? 0 "Packet received by local VXLAN device - localbypass" +} + +################################################################################ +# Usage + +usage() +{ + cat <<EOF +usage: ${0##*/} OPTS + + -t <test> Test(s) to run (default: all) + (options: $TESTS) + -p Pause on fail + -P Pause after each test before cleanup + -v Verbose mode (show commands and output) +EOF +} + +################################################################################ +# Main + +trap cleanup EXIT + +while getopts ":t:pPvh" opt; do + case $opt in + t) TESTS=$OPTARG ;; + p) PAUSE_ON_FAIL=yes;; + P) PAUSE=yes;; + v) VERBOSE=$(($VERBOSE + 1));; + h) usage; exit 0;; + *) usage; exit 1;; + esac +done + +# Make sure we don't pause twice. +[ "${PAUSE}" = "yes" ] && PAUSE_ON_FAIL=no + +if [ "$(id -u)" -ne 0 ];then + echo "SKIP: Need root privileges" + exit $ksft_skip; +fi + +if [ ! -x "$(command -v ip)" ]; then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +if [ ! -x "$(command -v bridge)" ]; then + echo "SKIP: Could not run test without bridge tool" + exit $ksft_skip +fi + +if [ ! -x "$(command -v mausezahn)" ]; then + echo "SKIP: Could not run test without mausezahn tool" + exit $ksft_skip +fi + +if [ ! -x "$(command -v jq)" ]; then + echo "SKIP: Could not run test without jq tool" + exit $ksft_skip +fi + +ip link help vxlan 2>&1 | grep -q "localbypass" +if [ $? -ne 0 ]; then + echo "SKIP: iproute2 ip too old, missing VXLAN nolocalbypass support" + exit $ksft_skip +fi + +cleanup + +for t in $TESTS +do + setup; $t; cleanup; +done + +if [ "$TESTS" != "none" ]; then + printf "\nTests passed: %3d\n" ${nsuccess} + printf "Tests failed: %3d\n" ${nfail} +fi + +exit $ret diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index e699548d4247..eccea9845c65 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -15,6 +15,7 @@ #include <linux/tcp.h> #include <linux/socket.h> +#include <sys/epoll.h> #include <sys/types.h> #include <sys/sendfile.h> #include <sys/socket.h> @@ -1637,6 +1638,136 @@ TEST_F(tls_err, timeo) } } +TEST_F(tls_err, poll_partial_rec) +{ + struct pollfd pfd = { }; + ssize_t rec_len; + char rec[256]; + char buf[128]; + + if (self->notls) + SKIP(return, "no TLS support"); + + pfd.fd = self->cfd2; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 1), 0); + + memrnd(buf, sizeof(buf)); + EXPECT_EQ(send(self->fd, buf, sizeof(buf), 0), sizeof(buf)); + rec_len = recv(self->cfd, rec, sizeof(rec), 0); + EXPECT_GT(rec_len, sizeof(buf)); + + /* Write 100B, not the full record ... */ + EXPECT_EQ(send(self->fd2, rec, 100, 0), 100); + /* ... no full record should mean no POLLIN */ + pfd.fd = self->cfd2; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 1), 0); + /* Now write the rest, and it should all pop out of the other end. */ + EXPECT_EQ(send(self->fd2, rec + 100, rec_len - 100, 0), rec_len - 100); + pfd.fd = self->cfd2; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 1), 1); + EXPECT_EQ(recv(self->cfd2, rec, sizeof(rec), 0), sizeof(buf)); + EXPECT_EQ(memcmp(buf, rec, sizeof(buf)), 0); +} + +TEST_F(tls_err, epoll_partial_rec) +{ + struct epoll_event ev, events[10]; + ssize_t rec_len; + char rec[256]; + char buf[128]; + int epollfd; + + if (self->notls) + SKIP(return, "no TLS support"); + + epollfd = epoll_create1(0); + ASSERT_GE(epollfd, 0); + + memset(&ev, 0, sizeof(ev)); + ev.events = EPOLLIN; + ev.data.fd = self->cfd2; + ASSERT_GE(epoll_ctl(epollfd, EPOLL_CTL_ADD, self->cfd2, &ev), 0); + + EXPECT_EQ(epoll_wait(epollfd, events, 10, 0), 0); + + memrnd(buf, sizeof(buf)); + EXPECT_EQ(send(self->fd, buf, sizeof(buf), 0), sizeof(buf)); + rec_len = recv(self->cfd, rec, sizeof(rec), 0); + EXPECT_GT(rec_len, sizeof(buf)); + + /* Write 100B, not the full record ... */ + EXPECT_EQ(send(self->fd2, rec, 100, 0), 100); + /* ... no full record should mean no POLLIN */ + EXPECT_EQ(epoll_wait(epollfd, events, 10, 0), 0); + /* Now write the rest, and it should all pop out of the other end. */ + EXPECT_EQ(send(self->fd2, rec + 100, rec_len - 100, 0), rec_len - 100); + EXPECT_EQ(epoll_wait(epollfd, events, 10, 0), 1); + EXPECT_EQ(recv(self->cfd2, rec, sizeof(rec), 0), sizeof(buf)); + EXPECT_EQ(memcmp(buf, rec, sizeof(buf)), 0); + + close(epollfd); +} + +TEST_F(tls_err, poll_partial_rec_async) +{ + struct pollfd pfd = { }; + ssize_t rec_len; + char rec[256]; + char buf[128]; + char token; + int p[2]; + int ret; + + if (self->notls) + SKIP(return, "no TLS support"); + + ASSERT_GE(pipe(p), 0); + + memrnd(buf, sizeof(buf)); + EXPECT_EQ(send(self->fd, buf, sizeof(buf), 0), sizeof(buf)); + rec_len = recv(self->cfd, rec, sizeof(rec), 0); + EXPECT_GT(rec_len, sizeof(buf)); + + ret = fork(); + ASSERT_GE(ret, 0); + + if (ret) { + int status, pid2; + + close(p[1]); + usleep(1000); /* Give child a head start */ + + EXPECT_EQ(send(self->fd2, rec, 100, 0), 100); + + EXPECT_EQ(read(p[0], &token, 1), 1); /* Barrier #1 */ + + EXPECT_EQ(send(self->fd2, rec + 100, rec_len - 100, 0), + rec_len - 100); + + pid2 = wait(&status); + EXPECT_EQ(pid2, ret); + EXPECT_EQ(status, 0); + } else { + close(p[0]); + + /* Child should sleep in poll(), never get a wake */ + pfd.fd = self->cfd2; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 5), 0); + + EXPECT_EQ(write(p[1], &token, 1), 1); /* Barrier #1 */ + + pfd.fd = self->cfd2; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 5), 1); + + exit(!_metadata->passed); + } +} + TEST(non_established) { struct tls12_crypto_info_aes_gcm_256 tls12; struct sockaddr_in addr; diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json index 44fbfc6caec7..e3d2de5c184f 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json @@ -155,5 +155,28 @@ "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" ] - } + }, + { + "id": "0531", + "name": "Replace mq with invalid parent ID", + "category": [ + "qdisc", + "mq" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "echo \"1 1 16\" > /sys/bus/netdevsim/new_device", + "$TC qdisc add dev $ETH root handle ffff: mq" + ], + "cmdUnderTest": "$TC qdisc replace dev $ETH parent ffff:fff1 handle ffff: mq", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $ETH", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent ffff", + "matchCount": "16", + "teardown": [ + "echo \"1\" > /sys/bus/netdevsim/del_device" + ] + } ] |