diff options
Diffstat (limited to 'tools')
73 files changed, 2975 insertions, 526 deletions
diff --git a/tools/bpf/bpftool/Documentation/bpftool-btf.rst b/tools/bpf/bpftool/Documentation/bpftool-btf.rst index eaba24320fb2..3f6bca03ad2e 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-btf.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-btf.rst @@ -28,7 +28,7 @@ BTF COMMANDS | **bpftool** **btf help** | | *BTF_SRC* := { **id** *BTF_ID* | **prog** *PROG* | **map** *MAP* [{**key** | **value** | **kv** | **all**}] | **file** *FILE* } -| *FORMAT* := { **raw** | **c** } +| *FORMAT* := { **raw** | **c** [**unsorted**] } | *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } | *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* | **name** *PROG_NAME* } @@ -63,7 +63,9 @@ bpftool btf dump *BTF_SRC* pahole. **format** option can be used to override default (raw) output format. Raw - (**raw**) or C-syntax (**c**) output formats are supported. + (**raw**) or C-syntax (**c**) output formats are supported. With C-style + formatting, the output is sorted by default. Use the **unsorted** option + to avoid sorting the output. bpftool btf help Print short help message. diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index dfa4f1bebbb3..ba927379eb20 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -204,10 +204,11 @@ ifeq ($(feature-clang-bpf-co-re),1) BUILD_BPF_SKELS := 1 -$(OUTPUT)vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL_BOOTSTRAP) ifeq ($(VMLINUX_H),) +$(OUTPUT)vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL_BOOTSTRAP) $(QUIET_GEN)$(BPFTOOL_BOOTSTRAP) btf dump file $< format c > $@ else +$(OUTPUT)vmlinux.h: $(VMLINUX_H) $(Q)cp "$(VMLINUX_H)" $@ endif diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index 04afe2ac2228..be99d49b8714 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -930,6 +930,9 @@ _bpftool() format) COMPREPLY=( $( compgen -W "c raw" -- "$cur" ) ) ;; + c) + COMPREPLY=( $( compgen -W "unsorted" -- "$cur" ) ) + ;; *) # emit extra options case ${words[3]} in diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index 91fcb75babe3..af047dedde38 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -43,6 +43,13 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_ENUM64] = "ENUM64", }; +struct sort_datum { + int index; + int type_rank; + const char *sort_name; + const char *own_name; +}; + static const char *btf_int_enc_str(__u8 encoding) { switch (encoding) { @@ -460,9 +467,122 @@ static void __printf(2, 0) btf_dump_printf(void *ctx, vfprintf(stdout, fmt, args); } +static int btf_type_rank(const struct btf *btf, __u32 index, bool has_name) +{ + const struct btf_type *t = btf__type_by_id(btf, index); + const int kind = btf_kind(t); + const int max_rank = 10; + + if (t->name_off) + has_name = true; + + switch (kind) { + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + return has_name ? 1 : 0; + case BTF_KIND_INT: + case BTF_KIND_FLOAT: + return 2; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + return has_name ? 3 : max_rank; + case BTF_KIND_FUNC_PROTO: + return has_name ? 4 : max_rank; + case BTF_KIND_ARRAY: + if (has_name) + return btf_type_rank(btf, btf_array(t)->type, has_name); + return max_rank; + case BTF_KIND_TYPE_TAG: + case BTF_KIND_CONST: + case BTF_KIND_PTR: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_TYPEDEF: + case BTF_KIND_DECL_TAG: + if (has_name) + return btf_type_rank(btf, t->type, has_name); + return max_rank; + default: + return max_rank; + } +} + +static const char *btf_type_sort_name(const struct btf *btf, __u32 index, bool from_ref) +{ + const struct btf_type *t = btf__type_by_id(btf, index); + + switch (btf_kind(t)) { + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: { + int name_off = t->name_off; + + /* Use name of the first element for anonymous enums if allowed */ + if (!from_ref && !t->name_off && btf_vlen(t)) + name_off = btf_enum(t)->name_off; + + return btf__name_by_offset(btf, name_off); + } + case BTF_KIND_ARRAY: + return btf_type_sort_name(btf, btf_array(t)->type, true); + case BTF_KIND_TYPE_TAG: + case BTF_KIND_CONST: + case BTF_KIND_PTR: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_TYPEDEF: + case BTF_KIND_DECL_TAG: + return btf_type_sort_name(btf, t->type, true); + default: + return btf__name_by_offset(btf, t->name_off); + } + return NULL; +} + +static int btf_type_compare(const void *left, const void *right) +{ + const struct sort_datum *d1 = (const struct sort_datum *)left; + const struct sort_datum *d2 = (const struct sort_datum *)right; + int r; + + if (d1->type_rank != d2->type_rank) + return d1->type_rank < d2->type_rank ? -1 : 1; + + r = strcmp(d1->sort_name, d2->sort_name); + if (r) + return r; + + return strcmp(d1->own_name, d2->own_name); +} + +static struct sort_datum *sort_btf_c(const struct btf *btf) +{ + struct sort_datum *datums; + int n; + + n = btf__type_cnt(btf); + datums = malloc(sizeof(struct sort_datum) * n); + if (!datums) + return NULL; + + for (int i = 0; i < n; ++i) { + struct sort_datum *d = datums + i; + const struct btf_type *t = btf__type_by_id(btf, i); + + d->index = i; + d->type_rank = btf_type_rank(btf, i, false); + d->sort_name = btf_type_sort_name(btf, i, false); + d->own_name = btf__name_by_offset(btf, t->name_off); + } + + qsort(datums, n, sizeof(struct sort_datum), btf_type_compare); + + return datums; +} + static int dump_btf_c(const struct btf *btf, - __u32 *root_type_ids, int root_type_cnt) + __u32 *root_type_ids, int root_type_cnt, bool sort_dump) { + struct sort_datum *datums = NULL; struct btf_dump *d; int err = 0, i; @@ -486,8 +606,12 @@ static int dump_btf_c(const struct btf *btf, } else { int cnt = btf__type_cnt(btf); + if (sort_dump) + datums = sort_btf_c(btf); for (i = 1; i < cnt; i++) { - err = btf_dump__dump_type(d, i); + int idx = datums ? datums[i].index : i; + + err = btf_dump__dump_type(d, idx); if (err) goto done; } @@ -500,6 +624,7 @@ static int dump_btf_c(const struct btf *btf, printf("#endif /* __VMLINUX_H__ */\n"); done: + free(datums); btf_dump__free(d); return err; } @@ -549,10 +674,10 @@ static bool btf_is_kernel_module(__u32 btf_id) static int do_dump(int argc, char **argv) { + bool dump_c = false, sort_dump_c = true; struct btf *btf = NULL, *base = NULL; __u32 root_type_ids[2]; int root_type_cnt = 0; - bool dump_c = false; __u32 btf_id = -1; const char *src; int fd = -1; @@ -663,6 +788,9 @@ static int do_dump(int argc, char **argv) goto done; } NEXT_ARG(); + } else if (is_prefix(*argv, "unsorted")) { + sort_dump_c = false; + NEXT_ARG(); } else { p_err("unrecognized option: '%s'", *argv); err = -EINVAL; @@ -691,7 +819,7 @@ static int do_dump(int argc, char **argv) err = -ENOTSUP; goto done; } - err = dump_btf_c(btf, root_type_ids, root_type_cnt); + err = dump_btf_c(btf, root_type_ids, root_type_cnt, sort_dump_c); } else { err = dump_btf_raw(btf, root_type_ids, root_type_cnt); } @@ -1063,7 +1191,7 @@ static int do_help(int argc, char **argv) " %1$s %2$s help\n" "\n" " BTF_SRC := { id BTF_ID | prog PROG | map MAP [{key | value | kv | all}] | file FILE }\n" - " FORMAT := { raw | c }\n" + " FORMAT := { raw | c [unsorted] }\n" " " HELP_SPEC_MAP "\n" " " HELP_SPEC_PROGRAM "\n" " " HELP_SPEC_OPTIONS " |\n" diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 958e92acca8e..9b75639434b8 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -410,7 +410,7 @@ void get_prog_full_name(const struct bpf_prog_info *prog_info, int prog_fd, { const char *prog_name = prog_info->name; const struct btf_type *func_type; - const struct bpf_func_info finfo = {}; + struct bpf_func_info finfo = {}; struct bpf_prog_info info = {}; __u32 info_len = sizeof(info); struct btf *prog_btf = NULL; diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c index b3979ddc0189..4a4eedfcd479 100644 --- a/tools/bpf/bpftool/gen.c +++ b/tools/bpf/bpftool/gen.c @@ -848,7 +848,7 @@ out: } static void -codegen_maps_skeleton(struct bpf_object *obj, size_t map_cnt, bool mmaped) +codegen_maps_skeleton(struct bpf_object *obj, size_t map_cnt, bool mmaped, bool populate_links) { struct bpf_map *map; char ident[256]; @@ -888,6 +888,14 @@ codegen_maps_skeleton(struct bpf_object *obj, size_t map_cnt, bool mmaped) printf("\ts->maps[%zu].mmaped = (void **)&obj->%s;\n", i, ident); } + + if (populate_links && bpf_map__type(map) == BPF_MAP_TYPE_STRUCT_OPS) { + codegen("\ + \n\ + s->maps[%zu].link = &obj->links.%s;\n\ + ", + i, ident); + } i++; } } @@ -1141,7 +1149,7 @@ static void gen_st_ops_shadow_init(struct btf *btf, struct bpf_object *obj) static int do_skeleton(int argc, char **argv) { char header_guard[MAX_OBJ_NAME_LEN + sizeof("__SKEL_H__")]; - size_t map_cnt = 0, prog_cnt = 0, file_sz, mmap_sz; + size_t map_cnt = 0, prog_cnt = 0, attach_map_cnt = 0, file_sz, mmap_sz; DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts); char obj_name[MAX_OBJ_NAME_LEN] = "", *obj_data; struct bpf_object *obj = NULL; @@ -1225,6 +1233,10 @@ static int do_skeleton(int argc, char **argv) bpf_map__name(map)); continue; } + + if (bpf_map__type(map) == BPF_MAP_TYPE_STRUCT_OPS) + attach_map_cnt++; + map_cnt++; } bpf_object__for_each_program(prog, obj) { @@ -1297,6 +1309,9 @@ static int do_skeleton(int argc, char **argv) bpf_program__name(prog)); } printf("\t} progs;\n"); + } + + if (prog_cnt + attach_map_cnt) { printf("\tstruct {\n"); bpf_object__for_each_program(prog, obj) { if (use_loader) @@ -1306,6 +1321,19 @@ static int do_skeleton(int argc, char **argv) printf("\t\tstruct bpf_link *%s;\n", bpf_program__name(prog)); } + + bpf_object__for_each_map(map, obj) { + if (!get_map_ident(map, ident, sizeof(ident))) + continue; + if (bpf_map__type(map) != BPF_MAP_TYPE_STRUCT_OPS) + continue; + + if (use_loader) + printf("t\tint %s_fd;\n", ident); + else + printf("\t\tstruct bpf_link *%s;\n", ident); + } + printf("\t} links;\n"); } @@ -1448,7 +1476,7 @@ static int do_skeleton(int argc, char **argv) obj_name ); - codegen_maps_skeleton(obj, map_cnt, true /*mmaped*/); + codegen_maps_skeleton(obj, map_cnt, true /*mmaped*/, true /*links*/); codegen_progs_skeleton(obj, prog_cnt, true /*populate_links*/); codegen("\ @@ -1786,7 +1814,7 @@ static int do_subskeleton(int argc, char **argv) } } - codegen_maps_skeleton(obj, map_cnt, false /*mmaped*/); + codegen_maps_skeleton(obj, map_cnt, false /*mmaped*/, false /*links*/); codegen_progs_skeleton(obj, prog_cnt, false /*links*/); codegen("\ @@ -2379,15 +2407,6 @@ out: return err; } -static int btfgen_remap_id(__u32 *type_id, void *ctx) -{ - unsigned int *ids = ctx; - - *type_id = ids[*type_id]; - - return 0; -} - /* Generate BTF from relocation information previously recorded */ static struct btf *btfgen_get_btf(struct btfgen_info *info) { @@ -2467,10 +2486,15 @@ static struct btf *btfgen_get_btf(struct btfgen_info *info) /* second pass: fix up type ids */ for (i = 1; i < btf__type_cnt(btf_new); i++) { struct btf_type *btf_type = (struct btf_type *) btf__type_by_id(btf_new, i); + struct btf_field_iter it; + __u32 *type_id; - err = btf_type_visit_type_ids(btf_type, btfgen_remap_id, ids); + err = btf_field_iter_init(&it, btf_type, BTF_FIELD_ITER_IDS); if (err) goto err_out; + + while ((type_id = btf_field_iter_next(&it))) + *type_id = ids[*type_id]; } free(ids); diff --git a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c index 7bdbcac3cf62..948dde25034e 100644 --- a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c +++ b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c @@ -29,6 +29,7 @@ enum bpf_link_type___local { }; extern const void bpf_link_fops __ksym; +extern const void bpf_link_fops_poll __ksym __weak; extern const void bpf_map_fops __ksym; extern const void bpf_prog_fops __ksym; extern const void btf_fops __ksym; @@ -84,7 +85,11 @@ int iter(struct bpf_iter__task_file *ctx) fops = &btf_fops; break; case BPF_OBJ_LINK: - fops = &bpf_link_fops; + if (&bpf_link_fops_poll && + file->f_op == &bpf_link_fops_poll) + fops = &bpf_link_fops_poll; + else + fops = &bpf_link_fops; break; default: return 0; diff --git a/tools/bpf/bpftool/skeleton/profiler.bpf.c b/tools/bpf/bpftool/skeleton/profiler.bpf.c index 2f80edc682f1..f48c783cb9f7 100644 --- a/tools/bpf/bpftool/skeleton/profiler.bpf.c +++ b/tools/bpf/bpftool/skeleton/profiler.bpf.c @@ -40,17 +40,17 @@ struct { const volatile __u32 num_cpu = 1; const volatile __u32 num_metric = 1; -#define MAX_NUM_MATRICS 4 +#define MAX_NUM_METRICS 4 SEC("fentry/XXX") int BPF_PROG(fentry_XXX) { - struct bpf_perf_event_value___local *ptrs[MAX_NUM_MATRICS]; + struct bpf_perf_event_value___local *ptrs[MAX_NUM_METRICS]; u32 key = bpf_get_smp_processor_id(); u32 i; /* look up before reading, to reduce error */ - for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) { + for (i = 0; i < num_metric && i < MAX_NUM_METRICS; i++) { u32 flag = i; ptrs[i] = bpf_map_lookup_elem(&fentry_readings, &flag); @@ -58,7 +58,7 @@ int BPF_PROG(fentry_XXX) return 0; } - for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) { + for (i = 0; i < num_metric && i < MAX_NUM_METRICS; i++) { struct bpf_perf_event_value___local reading; int err; @@ -99,14 +99,14 @@ fexit_update_maps(u32 id, struct bpf_perf_event_value___local *after) SEC("fexit/XXX") int BPF_PROG(fexit_XXX) { - struct bpf_perf_event_value___local readings[MAX_NUM_MATRICS]; + struct bpf_perf_event_value___local readings[MAX_NUM_METRICS]; u32 cpu = bpf_get_smp_processor_id(); u32 i, zero = 0; int err; u64 *count; /* read all events before updating the maps, to reduce error */ - for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) { + for (i = 0; i < num_metric && i < MAX_NUM_METRICS; i++) { err = bpf_perf_event_read_value(&events, cpu + i * num_cpu, (void *)(readings + i), sizeof(*readings)); @@ -116,7 +116,7 @@ int BPF_PROG(fexit_XXX) count = bpf_map_lookup_elem(&counts, &zero); if (count) { *count += 1; - for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) + for (i = 0; i < num_metric && i < MAX_NUM_METRICS; i++) fexit_update_maps(i, &readings[i]); } return 0; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 90706a47f6ff..25ea393cf084 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -6207,12 +6207,17 @@ union { \ __u64 :64; \ } __attribute__((aligned(8))) +/* The enum used in skb->tstamp_type. It specifies the clock type + * of the time stored in the skb->tstamp. + */ enum { - BPF_SKB_TSTAMP_UNSPEC, - BPF_SKB_TSTAMP_DELIVERY_MONO, /* tstamp has mono delivery time */ - /* For any BPF_SKB_TSTAMP_* that the bpf prog cannot handle, - * the bpf prog should handle it like BPF_SKB_TSTAMP_UNSPEC - * and try to deduce it by ingress, egress or skb->sk->sk_clockid. + BPF_SKB_TSTAMP_UNSPEC = 0, /* DEPRECATED */ + BPF_SKB_TSTAMP_DELIVERY_MONO = 1, /* DEPRECATED */ + BPF_SKB_CLOCK_REALTIME = 0, + BPF_SKB_CLOCK_MONOTONIC = 1, + BPF_SKB_CLOCK_TAI = 2, + /* For any future BPF_SKB_CLOCK_* that the bpf prog cannot handle, + * the bpf prog can try to deduce it by ingress/egress/skb->sk->sk_clockid. */ }; diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 2d0840ef599a..775ca55a541c 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -1739,9 +1739,8 @@ struct btf_pipe { struct hashmap *str_off_map; /* map string offsets from src to dst */ }; -static int btf_rewrite_str(__u32 *str_off, void *ctx) +static int btf_rewrite_str(struct btf_pipe *p, __u32 *str_off) { - struct btf_pipe *p = ctx; long mapped_off; int off, err; @@ -1774,7 +1773,9 @@ static int btf_rewrite_str(__u32 *str_off, void *ctx) int btf__add_type(struct btf *btf, const struct btf *src_btf, const struct btf_type *src_type) { struct btf_pipe p = { .src = src_btf, .dst = btf }; + struct btf_field_iter it; struct btf_type *t; + __u32 *str_off; int sz, err; sz = btf_type_size(src_type); @@ -1791,26 +1792,17 @@ int btf__add_type(struct btf *btf, const struct btf *src_btf, const struct btf_t memcpy(t, src_type, sz); - err = btf_type_visit_str_offs(t, btf_rewrite_str, &p); + err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_STRS); if (err) return libbpf_err(err); - return btf_commit_type(btf, sz); -} - -static int btf_rewrite_type_ids(__u32 *type_id, void *ctx) -{ - struct btf *btf = ctx; - - if (!*type_id) /* nothing to do for VOID references */ - return 0; + while ((str_off = btf_field_iter_next(&it))) { + err = btf_rewrite_str(&p, str_off); + if (err) + return libbpf_err(err); + } - /* we haven't updated btf's type count yet, so - * btf->start_id + btf->nr_types - 1 is the type ID offset we should - * add to all newly added BTF types - */ - *type_id += btf->start_id + btf->nr_types - 1; - return 0; + return btf_commit_type(btf, sz); } static size_t btf_dedup_identity_hash_fn(long key, void *ctx); @@ -1858,6 +1850,9 @@ int btf__add_btf(struct btf *btf, const struct btf *src_btf) memcpy(t, src_btf->types_data, data_sz); for (i = 0; i < cnt; i++) { + struct btf_field_iter it; + __u32 *type_id, *str_off; + sz = btf_type_size(t); if (sz < 0) { /* unlikely, has to be corrupted src_btf */ @@ -1869,15 +1864,31 @@ int btf__add_btf(struct btf *btf, const struct btf *src_btf) *off = t - btf->types_data; /* add, dedup, and remap strings referenced by this BTF type */ - err = btf_type_visit_str_offs(t, btf_rewrite_str, &p); + err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_STRS); if (err) goto err_out; + while ((str_off = btf_field_iter_next(&it))) { + err = btf_rewrite_str(&p, str_off); + if (err) + goto err_out; + } /* remap all type IDs referenced from this BTF type */ - err = btf_type_visit_type_ids(t, btf_rewrite_type_ids, btf); + err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_IDS); if (err) goto err_out; + while ((type_id = btf_field_iter_next(&it))) { + if (!*type_id) /* nothing to do for VOID references */ + continue; + + /* we haven't updated btf's type count yet, so + * btf->start_id + btf->nr_types - 1 is the type ID offset we should + * add to all newly added BTF types + */ + *type_id += btf->start_id + btf->nr_types - 1; + } + /* go to next type data and type offset index entry */ t += sz; off++; @@ -3453,11 +3464,19 @@ static int btf_for_each_str_off(struct btf_dedup *d, str_off_visit_fn fn, void * int i, r; for (i = 0; i < d->btf->nr_types; i++) { + struct btf_field_iter it; struct btf_type *t = btf_type_by_id(d->btf, d->btf->start_id + i); + __u32 *str_off; - r = btf_type_visit_str_offs(t, fn, ctx); + r = btf_field_iter_init(&it, t, BTF_FIELD_ITER_STRS); if (r) return r; + + while ((str_off = btf_field_iter_next(&it))) { + r = fn(str_off, ctx); + if (r) + return r; + } } if (!d->btf_ext) @@ -4919,10 +4938,23 @@ static int btf_dedup_remap_types(struct btf_dedup *d) for (i = 0; i < d->btf->nr_types; i++) { struct btf_type *t = btf_type_by_id(d->btf, d->btf->start_id + i); + struct btf_field_iter it; + __u32 *type_id; - r = btf_type_visit_type_ids(t, btf_dedup_remap_type_id, d); + r = btf_field_iter_init(&it, t, BTF_FIELD_ITER_IDS); if (r) return r; + + while ((type_id = btf_field_iter_next(&it))) { + __u32 resolved_id, new_id; + + resolved_id = resolve_type_id(d, *type_id); + new_id = d->hypot_map[resolved_id]; + if (new_id > BTF_MAX_NR_TYPES) + return -EINVAL; + + *type_id = new_id; + } } if (!d->btf_ext) @@ -5003,134 +5035,166 @@ struct btf *btf__load_module_btf(const char *module_name, struct btf *vmlinux_bt return btf__parse_split(path, vmlinux_btf); } -int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ctx) +int btf_field_iter_init(struct btf_field_iter *it, struct btf_type *t, enum btf_field_iter_kind iter_kind) { - int i, n, err; - - switch (btf_kind(t)) { - case BTF_KIND_INT: - case BTF_KIND_FLOAT: - case BTF_KIND_ENUM: - case BTF_KIND_ENUM64: - return 0; - - case BTF_KIND_FWD: - case BTF_KIND_CONST: - case BTF_KIND_VOLATILE: - case BTF_KIND_RESTRICT: - case BTF_KIND_PTR: - case BTF_KIND_TYPEDEF: - case BTF_KIND_FUNC: - case BTF_KIND_VAR: - case BTF_KIND_DECL_TAG: - case BTF_KIND_TYPE_TAG: - return visit(&t->type, ctx); - - case BTF_KIND_ARRAY: { - struct btf_array *a = btf_array(t); - - err = visit(&a->type, ctx); - err = err ?: visit(&a->index_type, ctx); - return err; - } + it->p = NULL; + it->m_idx = -1; + it->off_idx = 0; + it->vlen = 0; - case BTF_KIND_STRUCT: - case BTF_KIND_UNION: { - struct btf_member *m = btf_members(t); - - for (i = 0, n = btf_vlen(t); i < n; i++, m++) { - err = visit(&m->type, ctx); - if (err) - return err; - } - return 0; - } - - case BTF_KIND_FUNC_PROTO: { - struct btf_param *m = btf_params(t); - - err = visit(&t->type, ctx); - if (err) - return err; - for (i = 0, n = btf_vlen(t); i < n; i++, m++) { - err = visit(&m->type, ctx); - if (err) - return err; + switch (iter_kind) { + case BTF_FIELD_ITER_IDS: + switch (btf_kind(t)) { + case BTF_KIND_UNKN: + case BTF_KIND_INT: + case BTF_KIND_FLOAT: + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + it->desc = (struct btf_field_desc) {}; + break; + case BTF_KIND_FWD: + case BTF_KIND_CONST: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_PTR: + case BTF_KIND_TYPEDEF: + case BTF_KIND_FUNC: + case BTF_KIND_VAR: + case BTF_KIND_DECL_TAG: + case BTF_KIND_TYPE_TAG: + it->desc = (struct btf_field_desc) { 1, {offsetof(struct btf_type, type)} }; + break; + case BTF_KIND_ARRAY: + it->desc = (struct btf_field_desc) { + 2, {sizeof(struct btf_type) + offsetof(struct btf_array, type), + sizeof(struct btf_type) + offsetof(struct btf_array, index_type)} + }; + break; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + it->desc = (struct btf_field_desc) { + 0, {}, + sizeof(struct btf_member), + 1, {offsetof(struct btf_member, type)} + }; + break; + case BTF_KIND_FUNC_PROTO: + it->desc = (struct btf_field_desc) { + 1, {offsetof(struct btf_type, type)}, + sizeof(struct btf_param), + 1, {offsetof(struct btf_param, type)} + }; + break; + case BTF_KIND_DATASEC: + it->desc = (struct btf_field_desc) { + 0, {}, + sizeof(struct btf_var_secinfo), + 1, {offsetof(struct btf_var_secinfo, type)} + }; + break; + default: + return -EINVAL; } - return 0; - } - - case BTF_KIND_DATASEC: { - struct btf_var_secinfo *m = btf_var_secinfos(t); - - for (i = 0, n = btf_vlen(t); i < n; i++, m++) { - err = visit(&m->type, ctx); - if (err) - return err; + break; + case BTF_FIELD_ITER_STRS: + switch (btf_kind(t)) { + case BTF_KIND_UNKN: + it->desc = (struct btf_field_desc) {}; + break; + case BTF_KIND_INT: + case BTF_KIND_FLOAT: + case BTF_KIND_FWD: + case BTF_KIND_ARRAY: + case BTF_KIND_CONST: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_PTR: + case BTF_KIND_TYPEDEF: + case BTF_KIND_FUNC: + case BTF_KIND_VAR: + case BTF_KIND_DECL_TAG: + case BTF_KIND_TYPE_TAG: + case BTF_KIND_DATASEC: + it->desc = (struct btf_field_desc) { + 1, {offsetof(struct btf_type, name_off)} + }; + break; + case BTF_KIND_ENUM: + it->desc = (struct btf_field_desc) { + 1, {offsetof(struct btf_type, name_off)}, + sizeof(struct btf_enum), + 1, {offsetof(struct btf_enum, name_off)} + }; + break; + case BTF_KIND_ENUM64: + it->desc = (struct btf_field_desc) { + 1, {offsetof(struct btf_type, name_off)}, + sizeof(struct btf_enum64), + 1, {offsetof(struct btf_enum64, name_off)} + }; + break; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + it->desc = (struct btf_field_desc) { + 1, {offsetof(struct btf_type, name_off)}, + sizeof(struct btf_member), + 1, {offsetof(struct btf_member, name_off)} + }; + break; + case BTF_KIND_FUNC_PROTO: + it->desc = (struct btf_field_desc) { + 1, {offsetof(struct btf_type, name_off)}, + sizeof(struct btf_param), + 1, {offsetof(struct btf_param, name_off)} + }; + break; + default: + return -EINVAL; } - return 0; - } - + break; default: return -EINVAL; } -} -int btf_type_visit_str_offs(struct btf_type *t, str_off_visit_fn visit, void *ctx) -{ - int i, n, err; + if (it->desc.m_sz) + it->vlen = btf_vlen(t); - err = visit(&t->name_off, ctx); - if (err) - return err; + it->p = t; + return 0; +} - switch (btf_kind(t)) { - case BTF_KIND_STRUCT: - case BTF_KIND_UNION: { - struct btf_member *m = btf_members(t); +__u32 *btf_field_iter_next(struct btf_field_iter *it) +{ + if (!it->p) + return NULL; - for (i = 0, n = btf_vlen(t); i < n; i++, m++) { - err = visit(&m->name_off, ctx); - if (err) - return err; - } - break; + if (it->m_idx < 0) { + if (it->off_idx < it->desc.t_off_cnt) + return it->p + it->desc.t_offs[it->off_idx++]; + /* move to per-member iteration */ + it->m_idx = 0; + it->p += sizeof(struct btf_type); + it->off_idx = 0; } - case BTF_KIND_ENUM: { - struct btf_enum *m = btf_enum(t); - for (i = 0, n = btf_vlen(t); i < n; i++, m++) { - err = visit(&m->name_off, ctx); - if (err) - return err; - } - break; + /* if type doesn't have members, stop */ + if (it->desc.m_sz == 0) { + it->p = NULL; + return NULL; } - case BTF_KIND_ENUM64: { - struct btf_enum64 *m = btf_enum64(t); - for (i = 0, n = btf_vlen(t); i < n; i++, m++) { - err = visit(&m->name_off, ctx); - if (err) - return err; - } - break; + if (it->off_idx >= it->desc.m_off_cnt) { + /* exhausted this member's fields, go to the next member */ + it->m_idx++; + it->p += it->desc.m_sz; + it->off_idx = 0; } - case BTF_KIND_FUNC_PROTO: { - struct btf_param *m = btf_params(t); - for (i = 0, n = btf_vlen(t); i < n; i++, m++) { - err = visit(&m->name_off, ctx); - if (err) - return err; - } - break; - } - default: - break; - } + if (it->m_idx < it->vlen) + return it->p + it->desc.m_offs[it->off_idx++]; - return 0; + it->p = NULL; + return NULL; } int btf_ext_visit_type_ids(struct btf_ext *btf_ext, type_id_visit_fn visit, void *ctx) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 5401f2df463d..4a28fac4908a 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -229,7 +229,30 @@ static const char * const prog_type_name[] = { static int __base_pr(enum libbpf_print_level level, const char *format, va_list args) { - if (level == LIBBPF_DEBUG) + const char *env_var = "LIBBPF_LOG_LEVEL"; + static enum libbpf_print_level min_level = LIBBPF_INFO; + static bool initialized; + + if (!initialized) { + char *verbosity; + + initialized = true; + verbosity = getenv(env_var); + if (verbosity) { + if (strcasecmp(verbosity, "warn") == 0) + min_level = LIBBPF_WARN; + else if (strcasecmp(verbosity, "debug") == 0) + min_level = LIBBPF_DEBUG; + else if (strcasecmp(verbosity, "info") == 0) + min_level = LIBBPF_INFO; + else + fprintf(stderr, "libbpf: unrecognized '%s' envvar value: '%s', should be one of 'warn', 'debug', or 'info'.\n", + env_var, verbosity); + } + } + + /* if too verbose, skip logging */ + if (level > min_level) return 0; return vfprintf(stderr, format, args); @@ -549,6 +572,7 @@ struct bpf_map { bool pinned; bool reused; bool autocreate; + bool autoattach; __u64 map_extra; }; @@ -1377,6 +1401,7 @@ static int init_struct_ops_maps(struct bpf_object *obj, const char *sec_name, map->def.value_size = type->size; map->def.max_entries = 1; map->def.map_flags = strcmp(sec_name, STRUCT_OPS_LINK_SEC) == 0 ? BPF_F_LINK : 0; + map->autoattach = true; map->st_ops = calloc(1, sizeof(*map->st_ops)); if (!map->st_ops) @@ -4796,6 +4821,20 @@ int bpf_map__set_autocreate(struct bpf_map *map, bool autocreate) return 0; } +int bpf_map__set_autoattach(struct bpf_map *map, bool autoattach) +{ + if (!bpf_map__is_struct_ops(map)) + return libbpf_err(-EINVAL); + + map->autoattach = autoattach; + return 0; +} + +bool bpf_map__autoattach(const struct bpf_map *map) +{ + return map->autoattach; +} + int bpf_map__reuse_fd(struct bpf_map *map, int fd) { struct bpf_map_info info; @@ -12877,8 +12916,10 @@ struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map) __u32 zero = 0; int err, fd; - if (!bpf_map__is_struct_ops(map)) + if (!bpf_map__is_struct_ops(map)) { + pr_warn("map '%s': can't attach non-struct_ops map\n", map->name); return libbpf_err_ptr(-EINVAL); + } if (map->fd < 0) { pr_warn("map '%s': can't attach BPF map without FD (was it created?)\n", map->name); @@ -13922,6 +13963,35 @@ int bpf_object__attach_skeleton(struct bpf_object_skeleton *s) */ } + /* Skeleton is created with earlier version of bpftool + * which does not support auto-attachment + */ + if (s->map_skel_sz < sizeof(struct bpf_map_skeleton)) + return 0; + + for (i = 0; i < s->map_cnt; i++) { + struct bpf_map *map = *s->maps[i].map; + struct bpf_link **link = s->maps[i].link; + + if (!map->autocreate || !map->autoattach) + continue; + + if (*link) + continue; + + /* only struct_ops maps can be attached */ + if (!bpf_map__is_struct_ops(map)) + continue; + *link = bpf_map__attach_struct_ops(map); + + if (!*link) { + err = -errno; + pr_warn("map '%s': failed to auto-attach: %d\n", + bpf_map__name(map), err); + return libbpf_err(err); + } + } + return 0; } @@ -13935,6 +14005,18 @@ void bpf_object__detach_skeleton(struct bpf_object_skeleton *s) bpf_link__destroy(*link); *link = NULL; } + + if (s->map_skel_sz < sizeof(struct bpf_map_skeleton)) + return; + + for (i = 0; i < s->map_cnt; i++) { + struct bpf_link **link = s->maps[i].link; + + if (link) { + bpf_link__destroy(*link); + *link = NULL; + } + } } void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s) @@ -13942,8 +14024,7 @@ void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s) if (!s) return; - if (s->progs) - bpf_object__detach_skeleton(s); + bpf_object__detach_skeleton(s); if (s->obj) bpf_object__close(*s->obj); free(s->maps); diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index c3f77d9260fe..64a6a3d323e3 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -98,7 +98,10 @@ typedef int (*libbpf_print_fn_t)(enum libbpf_print_level level, /** * @brief **libbpf_set_print()** sets user-provided log callback function to - * be used for libbpf warnings and informational messages. + * be used for libbpf warnings and informational messages. If the user callback + * is not set, messages are logged to stderr by default. The verbosity of these + * messages can be controlled by setting the environment variable + * LIBBPF_LOG_LEVEL to either warn, info, or debug. * @param fn The log print function. If NULL, libbpf won't print anything. * @return Pointer to old print function. * @@ -976,6 +979,23 @@ LIBBPF_API int bpf_map__set_autocreate(struct bpf_map *map, bool autocreate); LIBBPF_API bool bpf_map__autocreate(const struct bpf_map *map); /** + * @brief **bpf_map__set_autoattach()** sets whether libbpf has to auto-attach + * map during BPF skeleton attach phase. + * @param map the BPF map instance + * @param autoattach whether to attach map during BPF skeleton attach phase + * @return 0 on success; negative error code, otherwise + */ +LIBBPF_API int bpf_map__set_autoattach(struct bpf_map *map, bool autoattach); + +/** + * @brief **bpf_map__autoattach()** returns whether BPF map is configured to + * auto-attach during BPF skeleton attach phase. + * @param map the BPF map instance + * @return true if map is set to auto-attach during skeleton attach phase; false, otherwise + */ +LIBBPF_API bool bpf_map__autoattach(const struct bpf_map *map); + +/** * @brief **bpf_map__fd()** gets the file descriptor of the passed * BPF map * @param map the BPF map instance @@ -1669,6 +1689,7 @@ struct bpf_map_skeleton { const char *name; struct bpf_map **map; void **mmaped; + struct bpf_link **link; }; struct bpf_prog_skeleton { diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index c1ce8aa3520b..40595233dc7f 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -419,6 +419,8 @@ LIBBPF_1.4.0 { LIBBPF_1.5.0 { global: + bpf_map__autoattach; + bpf_map__set_autoattach; bpf_program__attach_sockmap; ring__consume_n; ring_buffer__consume_n; diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index a0dcfb82e455..e2f06609c624 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -508,11 +508,33 @@ struct bpf_line_info_min { __u32 line_col; }; +enum btf_field_iter_kind { + BTF_FIELD_ITER_IDS, + BTF_FIELD_ITER_STRS, +}; + +struct btf_field_desc { + /* once-per-type offsets */ + int t_off_cnt, t_offs[2]; + /* member struct size, or zero, if no members */ + int m_sz; + /* repeated per-member offsets */ + int m_off_cnt, m_offs[1]; +}; + +struct btf_field_iter { + struct btf_field_desc desc; + void *p; + int m_idx; + int off_idx; + int vlen; +}; + +int btf_field_iter_init(struct btf_field_iter *it, struct btf_type *t, enum btf_field_iter_kind iter_kind); +__u32 *btf_field_iter_next(struct btf_field_iter *it); typedef int (*type_id_visit_fn)(__u32 *type_id, void *ctx); typedef int (*str_off_visit_fn)(__u32 *str_off, void *ctx); -int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ctx); -int btf_type_visit_str_offs(struct btf_type *t, str_off_visit_fn visit, void *ctx); int btf_ext_visit_type_ids(struct btf_ext *btf_ext, type_id_visit_fn visit, void *ctx); int btf_ext_visit_str_offs(struct btf_ext *btf_ext, str_off_visit_fn visit, void *ctx); __s32 btf__find_by_name_kind_own(const struct btf *btf, const char *type_name, @@ -597,13 +619,9 @@ static inline int ensure_good_fd(int fd) return fd; } -static inline int sys_dup2(int oldfd, int newfd) +static inline int sys_dup3(int oldfd, int newfd, int flags) { -#ifdef __NR_dup2 - return syscall(__NR_dup2, oldfd, newfd); -#else - return syscall(__NR_dup3, oldfd, newfd, 0); -#endif + return syscall(__NR_dup3, oldfd, newfd, flags); } /* Point *fixed_fd* to the same file that *tmp_fd* points to. @@ -614,7 +632,7 @@ static inline int reuse_fd(int fixed_fd, int tmp_fd) { int err; - err = sys_dup2(tmp_fd, fixed_fd); + err = sys_dup3(tmp_fd, fixed_fd, O_CLOEXEC); err = err < 0 ? -errno : 0; close(tmp_fd); /* clean up temporary FD */ return err; diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c index 0d4be829551b..fa11a671da3e 100644 --- a/tools/lib/bpf/linker.c +++ b/tools/lib/bpf/linker.c @@ -957,19 +957,33 @@ static int check_btf_str_off(__u32 *str_off, void *ctx) static int linker_sanity_check_btf(struct src_obj *obj) { struct btf_type *t; - int i, n, err = 0; + int i, n, err; if (!obj->btf) return 0; n = btf__type_cnt(obj->btf); for (i = 1; i < n; i++) { + struct btf_field_iter it; + __u32 *type_id, *str_off; + t = btf_type_by_id(obj->btf, i); - err = err ?: btf_type_visit_type_ids(t, check_btf_type_id, obj->btf); - err = err ?: btf_type_visit_str_offs(t, check_btf_str_off, obj->btf); + err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_IDS); if (err) return err; + while ((type_id = btf_field_iter_next(&it))) { + if (*type_id >= n) + return -EINVAL; + } + + err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_STRS); + if (err) + return err; + while ((str_off = btf_field_iter_next(&it))) { + if (!btf__str_by_offset(obj->btf, *str_off)) + return -EINVAL; + } } return 0; @@ -2234,26 +2248,10 @@ static int linker_fixup_btf(struct src_obj *obj) return 0; } -static int remap_type_id(__u32 *type_id, void *ctx) -{ - int *id_map = ctx; - int new_id = id_map[*type_id]; - - /* Error out if the type wasn't remapped. Ignore VOID which stays VOID. */ - if (new_id == 0 && *type_id != 0) { - pr_warn("failed to find new ID mapping for original BTF type ID %u\n", *type_id); - return -EINVAL; - } - - *type_id = id_map[*type_id]; - - return 0; -} - static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj) { const struct btf_type *t; - int i, j, n, start_id, id; + int i, j, n, start_id, id, err; const char *name; if (!obj->btf) @@ -2324,9 +2322,25 @@ static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj) n = btf__type_cnt(linker->btf); for (i = start_id; i < n; i++) { struct btf_type *dst_t = btf_type_by_id(linker->btf, i); + struct btf_field_iter it; + __u32 *type_id; - if (btf_type_visit_type_ids(dst_t, remap_type_id, obj->btf_type_map)) - return -EINVAL; + err = btf_field_iter_init(&it, dst_t, BTF_FIELD_ITER_IDS); + if (err) + return err; + + while ((type_id = btf_field_iter_next(&it))) { + int new_id = obj->btf_type_map[*type_id]; + + /* Error out if the type wasn't remapped. Ignore VOID which stays VOID. */ + if (new_id == 0 && *type_id != 0) { + pr_warn("failed to find new ID mapping for original BTF type ID %u\n", + *type_id); + return -EINVAL; + } + + *type_id = obj->btf_type_map[*type_id]; + } } /* Rewrite VAR/FUNC underlying types (i.e., FUNC's FUNC_PROTO and VAR's diff --git a/tools/net/ynl/lib/ynl-priv.h b/tools/net/ynl/lib/ynl-priv.h index 6cf890080dc0..3c09a7bbfba5 100644 --- a/tools/net/ynl/lib/ynl-priv.h +++ b/tools/net/ynl/lib/ynl-priv.h @@ -45,17 +45,17 @@ struct ynl_policy_attr { enum ynl_policy_type type; unsigned int len; const char *name; - struct ynl_policy_nest *nest; + const struct ynl_policy_nest *nest; }; struct ynl_policy_nest { unsigned int max_attr; - struct ynl_policy_attr *table; + const struct ynl_policy_attr *table; }; struct ynl_parse_arg { struct ynl_sock *ys; - struct ynl_policy_nest *rsp_policy; + const struct ynl_policy_nest *rsp_policy; void *data; }; @@ -79,7 +79,7 @@ static inline void *ynl_dump_obj_next(void *obj) struct ynl_dump_list_type *list; uptr -= offsetof(struct ynl_dump_list_type, data); - list = (void *)uptr; + list = (struct ynl_dump_list_type *)uptr; uptr = (unsigned long)list->next; uptr += offsetof(struct ynl_dump_list_type, data); @@ -119,7 +119,7 @@ struct ynl_dump_state { }; struct ynl_ntf_info { - struct ynl_policy_nest *policy; + const struct ynl_policy_nest *policy; ynl_parse_cb_t cb; size_t alloc_sz; void (*free)(struct ynl_ntf_base_type *ntf); @@ -139,7 +139,7 @@ int ynl_error_parse(struct ynl_parse_arg *yarg, const char *msg); static inline struct nlmsghdr *ynl_nlmsg_put_header(void *buf) { - struct nlmsghdr *nlh = buf; + struct nlmsghdr *nlh = (struct nlmsghdr *)buf; memset(nlh, 0, sizeof(*nlh)); nlh->nlmsg_len = NLMSG_HDRLEN; @@ -196,7 +196,7 @@ static inline void *ynl_attr_data(const struct nlattr *attr) static inline void *ynl_attr_data_end(const struct nlattr *attr) { - return ynl_attr_data(attr) + ynl_attr_data_len(attr); + return (char *)ynl_attr_data(attr) + ynl_attr_data_len(attr); } #define ynl_attr_for_each(attr, nlh, fixed_hdr_sz) \ @@ -228,7 +228,7 @@ ynl_attr_next(const void *end, const struct nlattr *prev) { struct nlattr *attr; - attr = (void *)((char *)prev + NLA_ALIGN(prev->nla_len)); + attr = (struct nlattr *)((char *)prev + NLA_ALIGN(prev->nla_len)); return ynl_attr_if_good(end, attr); } @@ -237,8 +237,8 @@ ynl_attr_first(const void *start, size_t len, size_t skip) { struct nlattr *attr; - attr = (void *)((char *)start + NLMSG_ALIGN(skip)); - return ynl_attr_if_good(start + len, attr); + attr = (struct nlattr *)((char *)start + NLMSG_ALIGN(skip)); + return ynl_attr_if_good((char *)start + len, attr); } static inline bool @@ -262,9 +262,9 @@ ynl_attr_nest_start(struct nlmsghdr *nlh, unsigned int attr_type) struct nlattr *attr; if (__ynl_attr_put_overflow(nlh, 0)) - return ynl_nlmsg_end_addr(nlh) - NLA_HDRLEN; + return (struct nlattr *)ynl_nlmsg_end_addr(nlh) - 1; - attr = ynl_nlmsg_end_addr(nlh); + attr = (struct nlattr *)ynl_nlmsg_end_addr(nlh); attr->nla_type = attr_type | NLA_F_NESTED; nlh->nlmsg_len += NLA_HDRLEN; @@ -286,7 +286,7 @@ ynl_attr_put(struct nlmsghdr *nlh, unsigned int attr_type, if (__ynl_attr_put_overflow(nlh, size)) return; - attr = ynl_nlmsg_end_addr(nlh); + attr = (struct nlattr *)ynl_nlmsg_end_addr(nlh); attr->nla_type = attr_type; attr->nla_len = NLA_HDRLEN + size; @@ -305,10 +305,10 @@ ynl_attr_put_str(struct nlmsghdr *nlh, unsigned int attr_type, const char *str) if (__ynl_attr_put_overflow(nlh, len)) return; - attr = ynl_nlmsg_end_addr(nlh); + attr = (struct nlattr *)ynl_nlmsg_end_addr(nlh); attr->nla_type = attr_type; - strcpy(ynl_attr_data(attr), str); + strcpy((char *)ynl_attr_data(attr), str); attr->nla_len = NLA_HDRLEN + NLA_ALIGN(len); nlh->nlmsg_len += NLMSG_ALIGN(attr->nla_len); diff --git a/tools/net/ynl/lib/ynl.c b/tools/net/ynl/lib/ynl.c index 4b9c091fc86b..fcb18a5a6d70 100644 --- a/tools/net/ynl/lib/ynl.c +++ b/tools/net/ynl/lib/ynl.c @@ -46,7 +46,7 @@ /* -- Netlink boiler plate */ static int -ynl_err_walk_report_one(struct ynl_policy_nest *policy, unsigned int type, +ynl_err_walk_report_one(const struct ynl_policy_nest *policy, unsigned int type, char *str, int str_sz, int *n) { if (!policy) { @@ -75,8 +75,8 @@ ynl_err_walk_report_one(struct ynl_policy_nest *policy, unsigned int type, 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) + const struct ynl_policy_nest *policy, char *str, int str_sz, + const struct ynl_policy_nest **nest_pol) { unsigned int astart_off, aend_off; const struct nlattr *attr; @@ -206,7 +206,7 @@ ynl_ext_ack_check(struct ynl_sock *ys, const struct nlmsghdr *nlh, bad_attr[n] = '\0'; } if (tb[NLMSGERR_ATTR_MISS_TYPE]) { - struct ynl_policy_nest *nest_pol = NULL; + const struct ynl_policy_nest *nest_pol = NULL; unsigned int n, off, type; void *start, *end; int n2; @@ -296,7 +296,7 @@ static int ynl_cb_done(const struct nlmsghdr *nlh, struct ynl_parse_arg *yarg) int ynl_attr_validate(struct ynl_parse_arg *yarg, const struct nlattr *attr) { - struct ynl_policy_attr *policy; + const struct ynl_policy_attr *policy; unsigned int type, len; unsigned char *data; diff --git a/tools/net/ynl/lib/ynl.h b/tools/net/ynl/lib/ynl.h index eef7c6324ed4..6cd570b283ea 100644 --- a/tools/net/ynl/lib/ynl.h +++ b/tools/net/ynl/lib/ynl.h @@ -76,7 +76,7 @@ struct ynl_sock { struct ynl_ntf_base_type **ntf_last_next; struct nlmsghdr *nlh; - struct ynl_policy_nest *req_policy; + const struct ynl_policy_nest *req_policy; unsigned char *tx_buf; unsigned char *rx_buf; unsigned char raw_buf[]; diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py index a42d62b23ee0..374ca5e86e24 100755 --- a/tools/net/ynl/ynl-gen-c.py +++ b/tools/net/ynl/ynl-gen-c.py @@ -1507,12 +1507,12 @@ def print_dump_prototype(ri): def put_typol_fwd(cw, struct): - cw.p(f'extern struct ynl_policy_nest {struct.render_name}_nest;') + cw.p(f'extern const struct ynl_policy_nest {struct.render_name}_nest;') def put_typol(cw, struct): type_max = struct.attr_set.max_name - cw.block_start(line=f'struct ynl_policy_attr {struct.render_name}_policy[{type_max} + 1] =') + cw.block_start(line=f'const struct ynl_policy_attr {struct.render_name}_policy[{type_max} + 1] =') for _, arg in struct.member_list(): arg.attr_typol(cw) @@ -1520,7 +1520,7 @@ def put_typol(cw, struct): cw.block_end(line=';') cw.nl() - cw.block_start(line=f'struct ynl_policy_nest {struct.render_name}_nest =') + cw.block_start(line=f'const struct ynl_policy_nest {struct.render_name}_nest =') cw.p(f'.max_attr = {type_max},') cw.p(f'.table = {struct.render_name}_policy,') cw.block_end(line=';') diff --git a/tools/net/ynl/ynl-gen-rst.py b/tools/net/ynl/ynl-gen-rst.py index 657e881d2ea4..6c56d0d726b4 100755 --- a/tools/net/ynl/ynl-gen-rst.py +++ b/tools/net/ynl/ynl-gen-rst.py @@ -49,7 +49,7 @@ def inline(text: str) -> str: def sanitize(text: str) -> str: """Remove newlines and multiple spaces""" # This is useful for some fields that are spread across multiple lines - return str(text).replace("\n", "").strip() + return str(text).replace("\n", " ").strip() def rst_fields(key: str, value: str, level: int = 0) -> str: @@ -156,7 +156,10 @@ def parse_do(do_dict: Dict[str, Any], level: int = 0) -> str: lines = [] for key in do_dict.keys(): lines.append(rst_paragraph(bold(key), level + 1)) - lines.append(parse_do_attributes(do_dict[key], level + 1) + "\n") + if key in ['request', 'reply']: + lines.append(parse_do_attributes(do_dict[key], level + 1) + "\n") + else: + lines.append(headroom(level + 2) + do_dict[key] + "\n") return "\n".join(lines) @@ -172,13 +175,13 @@ def parse_do_attributes(attrs: Dict[str, Any], level: int = 0) -> str: def parse_operations(operations: List[Dict[str, Any]], namespace: str) -> str: """Parse operations block""" - preprocessed = ["name", "doc", "title", "do", "dump"] + preprocessed = ["name", "doc", "title", "do", "dump", "flags"] linkable = ["fixed-header", "attribute-set"] lines = [] for operation in operations: lines.append(rst_section(namespace, 'operation', operation["name"])) - lines.append(rst_paragraph(sanitize(operation["doc"])) + "\n") + lines.append(rst_paragraph(operation["doc"]) + "\n") for key in operation.keys(): if key in preprocessed: @@ -188,6 +191,8 @@ def parse_operations(operations: List[Dict[str, Any]], namespace: str) -> str: if key in linkable: value = rst_ref(namespace, key, value) lines.append(rst_fields(key, value, 0)) + if 'flags' in operation: + lines.append(rst_fields('flags', rst_list_inline(operation['flags']))) if "do" in operation: lines.append(rst_paragraph(":do:", 0)) diff --git a/tools/testing/selftests/bpf/bpf_test_no_cfi/bpf_test_no_cfi.c b/tools/testing/selftests/bpf/bpf_test_no_cfi/bpf_test_no_cfi.c index b1dd889d5d7d..948eb3962732 100644 --- a/tools/testing/selftests/bpf/bpf_test_no_cfi/bpf_test_no_cfi.c +++ b/tools/testing/selftests/bpf/bpf_test_no_cfi/bpf_test_no_cfi.c @@ -22,12 +22,12 @@ static int dummy_init_member(const struct btf_type *t, return 0; } -static int dummy_reg(void *kdata) +static int dummy_reg(void *kdata, struct bpf_link *link) { return 0; } -static void dummy_unreg(void *kdata) +static void dummy_unreg(void *kdata, struct bpf_link *link) { } diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index 2a18bd320e92..0a09732cde4b 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -820,7 +820,7 @@ static const struct bpf_verifier_ops bpf_testmod_verifier_ops = { .is_valid_access = bpf_testmod_ops_is_valid_access, }; -static int bpf_dummy_reg(void *kdata) +static int bpf_dummy_reg(void *kdata, struct bpf_link *link) { struct bpf_testmod_ops *ops = kdata; @@ -835,7 +835,7 @@ static int bpf_dummy_reg(void *kdata) return 0; } -static void bpf_dummy_unreg(void *kdata) +static void bpf_dummy_unreg(void *kdata, struct bpf_link *link) { } @@ -871,7 +871,7 @@ struct bpf_struct_ops bpf_bpf_testmod_ops = { .owner = THIS_MODULE, }; -static int bpf_dummy_reg2(void *kdata) +static int bpf_dummy_reg2(void *kdata, struct bpf_link *link) { struct bpf_testmod_ops2 *ops = kdata; diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index eeabd798bc3a..2fb16da78dce 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -80,6 +80,7 @@ CONFIG_NETFILTER_XT_TARGET_CT=y CONFIG_NETKIT=y CONFIG_NF_CONNTRACK=y CONFIG_NF_CONNTRACK_MARK=y +CONFIG_NF_CONNTRACK_ZONES=y CONFIG_NF_DEFRAG_IPV4=y CONFIG_NF_DEFRAG_IPV6=y CONFIG_NF_NAT=y diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index 35250e6cde7f..e20caef06aae 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -94,7 +94,8 @@ static int __start_server(int type, const struct sockaddr *addr, socklen_t addrl if (settimeo(fd, opts->timeout_ms)) goto error_close; - if (opts->post_socket_cb && opts->post_socket_cb(fd, NULL)) { + if (opts->post_socket_cb && + opts->post_socket_cb(fd, opts->cb_opts)) { log_err("Failed to call post_socket_cb"); goto error_close; } @@ -118,22 +119,32 @@ error_close: return -1; } -int start_server(int family, int type, const char *addr_str, __u16 port, - int timeout_ms) +int start_server_str(int family, int type, const char *addr_str, __u16 port, + const struct network_helper_opts *opts) { - struct network_helper_opts opts = { - .timeout_ms = timeout_ms, - }; struct sockaddr_storage addr; socklen_t addrlen; + if (!opts) + opts = &default_opts; + if (make_sockaddr(family, addr_str, port, &addr, &addrlen)) return -1; - return __start_server(type, (struct sockaddr *)&addr, addrlen, &opts); + return __start_server(type, (struct sockaddr *)&addr, addrlen, opts); +} + +int start_server(int family, int type, const char *addr_str, __u16 port, + int timeout_ms) +{ + struct network_helper_opts opts = { + .timeout_ms = timeout_ms, + }; + + return start_server_str(family, type, addr_str, port, &opts); } -static int reuseport_cb(int fd, const struct post_socket_opts *opts) +static int reuseport_cb(int fd, void *opts) { int on = 1; @@ -338,9 +349,8 @@ int connect_to_fd_opts(int server_fd, const struct network_helper_opts *opts) if (settimeo(fd, opts->timeout_ms)) goto error_close; - if (opts->cc && opts->cc[0] && - setsockopt(fd, SOL_TCP, TCP_CONGESTION, opts->cc, - strlen(opts->cc) + 1)) + if (opts->post_socket_cb && + opts->post_socket_cb(fd, opts->cb_opts)) goto error_close; if (!opts->noconnect) diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h index 883c7ea9d8d5..11eea8e2e4f1 100644 --- a/tools/testing/selftests/bpf/network_helpers.h +++ b/tools/testing/selftests/bpf/network_helpers.h @@ -21,16 +21,14 @@ typedef __u16 __sum16; #define VIP_NUM 5 #define MAGIC_BYTES 123 -struct post_socket_opts {}; - struct network_helper_opts { - const char *cc; int timeout_ms; bool must_fail; bool noconnect; int type; int proto; - int (*post_socket_cb)(int fd, const struct post_socket_opts *opts); + int (*post_socket_cb)(int fd, void *opts); + void *cb_opts; }; /* ipv4 test vector */ @@ -50,6 +48,8 @@ struct ipv6_packet { extern struct ipv6_packet pkt_v6; int settimeo(int fd, int timeout_ms); +int start_server_str(int family, int type, const char *addr_str, __u16 port, + const struct network_helper_opts *opts); int start_server(int family, int type, const char *addr, __u16 port, int timeout_ms); int *start_reuseport_server(int family, int type, const char *addr_str, diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c index 4407ea428e77..070c52c312e5 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c @@ -451,7 +451,7 @@ static void pe_subtest(struct test_bpf_cookie *skel) attr.type = PERF_TYPE_SOFTWARE; attr.config = PERF_COUNT_SW_CPU_CLOCK; attr.freq = 1; - attr.sample_freq = 1000; + attr.sample_freq = 10000; pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC); if (!ASSERT_GE(pfd, 0, "perf_fd")) goto cleanup; diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c index b30ff6b3b81a..a4a1f93878d4 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c @@ -104,6 +104,7 @@ static void test_bpf_nf_ct(int mode) ASSERT_EQ(skel->bss->test_einval_bpf_tuple, -EINVAL, "Test EINVAL for NULL bpf_tuple"); ASSERT_EQ(skel->bss->test_einval_reserved, -EINVAL, "Test EINVAL for reserved not set to 0"); + ASSERT_EQ(skel->bss->test_einval_reserved_new, -EINVAL, "Test EINVAL for reserved in new struct not set to 0"); ASSERT_EQ(skel->bss->test_einval_netns_id, -EINVAL, "Test EINVAL for netns_id < -1"); ASSERT_EQ(skel->bss->test_einval_len_opts, -EINVAL, "Test EINVAL for len__opts != NF_BPF_CT_OPTS_SZ"); ASSERT_EQ(skel->bss->test_eproto_l4proto, -EPROTO, "Test EPROTO for l4proto != TCP or UDP"); @@ -122,6 +123,12 @@ static void test_bpf_nf_ct(int mode) ASSERT_EQ(skel->bss->test_exist_lookup_mark, 43, "Test existing connection lookup ctmark"); ASSERT_EQ(skel->data->test_snat_addr, 0, "Test for source natting"); ASSERT_EQ(skel->data->test_dnat_addr, 0, "Test for destination natting"); + ASSERT_EQ(skel->data->test_ct_zone_id_alloc_entry, 0, "Test for alloc new entry in specified ct zone"); + ASSERT_EQ(skel->data->test_ct_zone_id_insert_entry, 0, "Test for insert new entry in specified ct zone"); + ASSERT_EQ(skel->data->test_ct_zone_id_succ_lookup, 0, "Test for successful lookup in specified ct_zone"); + ASSERT_EQ(skel->bss->test_ct_zone_dir_enoent_lookup, -ENOENT, "Test ENOENT for lookup with wrong ct zone dir"); + ASSERT_EQ(skel->bss->test_ct_zone_id_enoent_lookup, -ENOENT, "Test ENOENT for lookup in wrong ct zone"); + end: if (client_fd != -1) close(client_fd); diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c index 0aca02532794..67358adf5db3 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c @@ -23,6 +23,11 @@ static const unsigned int total_bytes = 10 * 1024 * 1024; static int expected_stg = 0xeB9F; +struct cb_opts { + const char *cc; + int map_fd; +}; + static int settcpca(int fd, const char *tcp_ca) { int err; @@ -34,55 +39,66 @@ static int settcpca(int fd, const char *tcp_ca) return 0; } -static void do_test(const char *tcp_ca, const struct bpf_map *sk_stg_map) +static bool start_test(char *addr_str, + const struct network_helper_opts *srv_opts, + const struct network_helper_opts *cli_opts, + int *srv_fd, int *cli_fd) { - int lfd = -1, fd = -1; - int err; - - lfd = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0); - if (!ASSERT_NEQ(lfd, -1, "socket")) - return; + *srv_fd = start_server_str(AF_INET6, SOCK_STREAM, addr_str, 0, srv_opts); + if (!ASSERT_NEQ(*srv_fd, -1, "start_server_str")) + goto err; - fd = socket(AF_INET6, SOCK_STREAM, 0); - if (!ASSERT_NEQ(fd, -1, "socket")) { - close(lfd); - return; - } + /* connect to server */ + *cli_fd = connect_to_fd_opts(*srv_fd, cli_opts); + if (!ASSERT_NEQ(*cli_fd, -1, "connect_to_fd_opts")) + goto err; - if (settcpca(lfd, tcp_ca) || settcpca(fd, tcp_ca)) - goto done; + return true; - if (sk_stg_map) { - err = bpf_map_update_elem(bpf_map__fd(sk_stg_map), &fd, - &expected_stg, BPF_NOEXIST); - if (!ASSERT_OK(err, "bpf_map_update_elem(sk_stg_map)")) - goto done; +err: + if (*srv_fd != -1) { + close(*srv_fd); + *srv_fd = -1; } + if (*cli_fd != -1) { + close(*cli_fd); + *cli_fd = -1; + } + return false; +} - /* connect to server */ - err = connect_fd_to_fd(fd, lfd, 0); - if (!ASSERT_NEQ(err, -1, "connect")) - goto done; - - if (sk_stg_map) { - int tmp_stg; +static void do_test(const struct network_helper_opts *opts) +{ + int lfd = -1, fd = -1; - err = bpf_map_lookup_elem(bpf_map__fd(sk_stg_map), &fd, - &tmp_stg); - if (!ASSERT_ERR(err, "bpf_map_lookup_elem(sk_stg_map)") || - !ASSERT_EQ(errno, ENOENT, "bpf_map_lookup_elem(sk_stg_map)")) - goto done; - } + if (!start_test(NULL, opts, opts, &lfd, &fd)) + goto done; ASSERT_OK(send_recv_data(lfd, fd, total_bytes), "send_recv_data"); done: - close(lfd); - close(fd); + if (lfd != -1) + close(lfd); + if (fd != -1) + close(fd); +} + +static int cc_cb(int fd, void *opts) +{ + struct cb_opts *cb_opts = (struct cb_opts *)opts; + + return settcpca(fd, cb_opts->cc); } static void test_cubic(void) { + struct cb_opts cb_opts = { + .cc = "bpf_cubic", + }; + struct network_helper_opts opts = { + .post_socket_cb = cc_cb, + .cb_opts = &cb_opts, + }; struct bpf_cubic *cubic_skel; struct bpf_link *link; @@ -96,7 +112,7 @@ static void test_cubic(void) return; } - do_test("bpf_cubic", NULL); + do_test(&opts); ASSERT_EQ(cubic_skel->bss->bpf_cubic_acked_called, 1, "pkts_acked called"); @@ -104,8 +120,37 @@ static void test_cubic(void) bpf_cubic__destroy(cubic_skel); } +static int stg_post_socket_cb(int fd, void *opts) +{ + struct cb_opts *cb_opts = (struct cb_opts *)opts; + int err; + + err = settcpca(fd, cb_opts->cc); + if (err) + return err; + + err = bpf_map_update_elem(cb_opts->map_fd, &fd, + &expected_stg, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(sk_stg_map)")) + return err; + + return 0; +} + static void test_dctcp(void) { + struct cb_opts cb_opts = { + .cc = "bpf_dctcp", + }; + struct network_helper_opts opts = { + .post_socket_cb = cc_cb, + .cb_opts = &cb_opts, + }; + struct network_helper_opts cli_opts = { + .post_socket_cb = stg_post_socket_cb, + .cb_opts = &cb_opts, + }; + int lfd = -1, fd = -1, tmp_stg, err; struct bpf_dctcp *dctcp_skel; struct bpf_link *link; @@ -119,11 +164,25 @@ static void test_dctcp(void) return; } - do_test("bpf_dctcp", dctcp_skel->maps.sk_stg_map); + cb_opts.map_fd = bpf_map__fd(dctcp_skel->maps.sk_stg_map); + if (!start_test(NULL, &opts, &cli_opts, &lfd, &fd)) + goto done; + + err = bpf_map_lookup_elem(cb_opts.map_fd, &fd, &tmp_stg); + if (!ASSERT_ERR(err, "bpf_map_lookup_elem(sk_stg_map)") || + !ASSERT_EQ(errno, ENOENT, "bpf_map_lookup_elem(sk_stg_map)")) + goto done; + + ASSERT_OK(send_recv_data(lfd, fd, total_bytes), "send_recv_data"); ASSERT_EQ(dctcp_skel->bss->stg_result, expected_stg, "stg_result"); +done: bpf_link__destroy(link); bpf_dctcp__destroy(dctcp_skel); + if (lfd != -1) + close(lfd); + if (fd != -1) + close(fd); } static char *err_str; @@ -171,11 +230,22 @@ static void test_invalid_license(void) static void test_dctcp_fallback(void) { int err, lfd = -1, cli_fd = -1, srv_fd = -1; - struct network_helper_opts opts = { - .cc = "cubic", - }; struct bpf_dctcp *dctcp_skel; struct bpf_link *link = NULL; + struct cb_opts dctcp = { + .cc = "bpf_dctcp", + }; + struct network_helper_opts srv_opts = { + .post_socket_cb = cc_cb, + .cb_opts = &dctcp, + }; + struct cb_opts cubic = { + .cc = "cubic", + }; + struct network_helper_opts cli_opts = { + .post_socket_cb = cc_cb, + .cb_opts = &cubic, + }; char srv_cc[16]; socklen_t cc_len = sizeof(srv_cc); @@ -190,13 +260,7 @@ static void test_dctcp_fallback(void) if (!ASSERT_OK_PTR(link, "dctcp link")) goto done; - lfd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0); - if (!ASSERT_GE(lfd, 0, "lfd") || - !ASSERT_OK(settcpca(lfd, "bpf_dctcp"), "lfd=>bpf_dctcp")) - goto done; - - cli_fd = connect_to_fd_opts(lfd, &opts); - if (!ASSERT_GE(cli_fd, 0, "cli_fd")) + if (!start_test("::1", &srv_opts, &cli_opts, &lfd, &cli_fd)) goto done; srv_fd = accept(lfd, NULL, 0); @@ -297,6 +361,13 @@ static void test_unsupp_cong_op(void) static void test_update_ca(void) { + struct cb_opts cb_opts = { + .cc = "tcp_ca_update", + }; + struct network_helper_opts opts = { + .post_socket_cb = cc_cb, + .cb_opts = &cb_opts, + }; struct tcp_ca_update *skel; struct bpf_link *link; int saved_ca1_cnt; @@ -309,14 +380,14 @@ static void test_update_ca(void) link = bpf_map__attach_struct_ops(skel->maps.ca_update_1); ASSERT_OK_PTR(link, "attach_struct_ops"); - do_test("tcp_ca_update", NULL); + do_test(&opts); saved_ca1_cnt = skel->bss->ca1_cnt; ASSERT_GT(saved_ca1_cnt, 0, "ca1_ca1_cnt"); err = bpf_link__update_map(link, skel->maps.ca_update_2); ASSERT_OK(err, "update_map"); - do_test("tcp_ca_update", NULL); + do_test(&opts); ASSERT_EQ(skel->bss->ca1_cnt, saved_ca1_cnt, "ca2_ca1_cnt"); ASSERT_GT(skel->bss->ca2_cnt, 0, "ca2_ca2_cnt"); @@ -326,6 +397,13 @@ static void test_update_ca(void) static void test_update_wrong(void) { + struct cb_opts cb_opts = { + .cc = "tcp_ca_update", + }; + struct network_helper_opts opts = { + .post_socket_cb = cc_cb, + .cb_opts = &cb_opts, + }; struct tcp_ca_update *skel; struct bpf_link *link; int saved_ca1_cnt; @@ -338,14 +416,14 @@ static void test_update_wrong(void) link = bpf_map__attach_struct_ops(skel->maps.ca_update_1); ASSERT_OK_PTR(link, "attach_struct_ops"); - do_test("tcp_ca_update", NULL); + do_test(&opts); saved_ca1_cnt = skel->bss->ca1_cnt; ASSERT_GT(saved_ca1_cnt, 0, "ca1_ca1_cnt"); err = bpf_link__update_map(link, skel->maps.ca_wrong); ASSERT_ERR(err, "update_map"); - do_test("tcp_ca_update", NULL); + do_test(&opts); ASSERT_GT(skel->bss->ca1_cnt, saved_ca1_cnt, "ca2_ca1_cnt"); bpf_link__destroy(link); @@ -354,6 +432,13 @@ static void test_update_wrong(void) static void test_mixed_links(void) { + struct cb_opts cb_opts = { + .cc = "tcp_ca_update", + }; + struct network_helper_opts opts = { + .post_socket_cb = cc_cb, + .cb_opts = &cb_opts, + }; struct tcp_ca_update *skel; struct bpf_link *link, *link_nl; int err; @@ -368,7 +453,7 @@ static void test_mixed_links(void) link = bpf_map__attach_struct_ops(skel->maps.ca_update_1); ASSERT_OK_PTR(link, "attach_struct_ops"); - do_test("tcp_ca_update", NULL); + do_test(&opts); ASSERT_GT(skel->bss->ca1_cnt, 0, "ca1_ca1_cnt"); err = bpf_link__update_map(link, skel->maps.ca_no_link); @@ -455,6 +540,13 @@ static void test_tcp_ca_kfunc(void) static void test_cc_cubic(void) { + struct cb_opts cb_opts = { + .cc = "bpf_cc_cubic", + }; + struct network_helper_opts opts = { + .post_socket_cb = cc_cb, + .cb_opts = &cb_opts, + }; struct bpf_cc_cubic *cc_cubic_skel; struct bpf_link *link; @@ -468,7 +560,7 @@ static void test_cc_cubic(void) return; } - do_test("bpf_cc_cubic", NULL); + do_test(&opts); bpf_link__destroy(link); bpf_cc_cubic__destroy(cc_cubic_skel); diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c index 4c6ada5b270b..73f669014b69 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c @@ -45,12 +45,6 @@ err_out: return err; } -struct scale_test_def { - const char *file; - enum bpf_prog_type attach_type; - bool fails; -}; - static void scale_test(const char *file, enum bpf_prog_type attach_type, bool should_fail) diff --git a/tools/testing/selftests/bpf/prog_tests/btf_field_iter.c b/tools/testing/selftests/bpf/prog_tests/btf_field_iter.c new file mode 100644 index 000000000000..32159d3eb281 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/btf_field_iter.c @@ -0,0 +1,161 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024, Oracle and/or its affiliates. */ + +#include <test_progs.h> +#include <bpf/btf.h> +#include "btf_helpers.h" +#include "bpf/libbpf_internal.h" + +struct field_data { + __u32 ids[5]; + const char *strs[5]; +} fields[] = { + { .ids = {}, .strs = {} }, + { .ids = {}, .strs = { "int" } }, + { .ids = {}, .strs = { "int64" } }, + { .ids = { 1 }, .strs = { "" } }, + { .ids = { 2, 1 }, .strs = { "" } }, + { .ids = { 3, 1 }, .strs = { "s1", "f1", "f2" } }, + { .ids = { 1, 5 }, .strs = { "u1", "f1", "f2" } }, + { .ids = {}, .strs = { "e1", "v1", "v2" } }, + { .ids = {}, .strs = { "fw1" } }, + { .ids = { 1 }, .strs = { "t" } }, + { .ids = { 2 }, .strs = { "" } }, + { .ids = { 1 }, .strs = { "" } }, + { .ids = { 3 }, .strs = { "" } }, + { .ids = { 1, 1, 3 }, .strs = { "", "p1", "p2" } }, + { .ids = { 13 }, .strs = { "func" } }, + { .ids = { 1 }, .strs = { "var1" } }, + { .ids = { 3 }, .strs = { "var2" } }, + { .ids = {}, .strs = { "float" } }, + { .ids = { 11 }, .strs = { "decltag" } }, + { .ids = { 6 }, .strs = { "typetag" } }, + { .ids = {}, .strs = { "e64", "eval1", "eval2", "eval3" } }, + { .ids = { 15, 16 }, .strs = { "datasec1" } } + +}; + +/* Fabricate BTF with various types and check BTF field iteration finds types, + * strings expected. + */ +void test_btf_field_iter(void) +{ + struct btf *btf = NULL; + int id; + + btf = btf__new_empty(); + if (!ASSERT_OK_PTR(btf, "empty_btf")) + return; + + btf__add_int(btf, "int", 4, BTF_INT_SIGNED); /* [1] int */ + btf__add_int(btf, "int64", 8, BTF_INT_SIGNED); /* [2] int64 */ + btf__add_ptr(btf, 1); /* [3] int * */ + btf__add_array(btf, 1, 2, 3); /* [4] int64[3] */ + btf__add_struct(btf, "s1", 12); /* [5] struct s1 { */ + btf__add_field(btf, "f1", 3, 0, 0); /* int *f1; */ + btf__add_field(btf, "f2", 1, 0, 0); /* int f2; */ + /* } */ + btf__add_union(btf, "u1", 12); /* [6] union u1 { */ + btf__add_field(btf, "f1", 1, 0, 0); /* int f1; */ + btf__add_field(btf, "f2", 5, 0, 0); /* struct s1 f2; */ + /* } */ + btf__add_enum(btf, "e1", 4); /* [7] enum e1 { */ + btf__add_enum_value(btf, "v1", 1); /* v1 = 1; */ + btf__add_enum_value(btf, "v2", 2); /* v2 = 2; */ + /* } */ + + btf__add_fwd(btf, "fw1", BTF_FWD_STRUCT); /* [8] struct fw1; */ + btf__add_typedef(btf, "t", 1); /* [9] typedef int t; */ + btf__add_volatile(btf, 2); /* [10] volatile int64; */ + btf__add_const(btf, 1); /* [11] const int; */ + btf__add_restrict(btf, 3); /* [12] restrict int *; */ + btf__add_func_proto(btf, 1); /* [13] int (*)(int p1, int *p2); */ + btf__add_func_param(btf, "p1", 1); + btf__add_func_param(btf, "p2", 3); + + btf__add_func(btf, "func", BTF_FUNC_GLOBAL, 13);/* [14] int func(int p1, int *p2); */ + btf__add_var(btf, "var1", BTF_VAR_STATIC, 1); /* [15] static int var1; */ + btf__add_var(btf, "var2", BTF_VAR_STATIC, 3); /* [16] static int *var2; */ + btf__add_float(btf, "float", 4); /* [17] float; */ + btf__add_decl_tag(btf, "decltag", 11, -1); /* [18] decltag const int; */ + btf__add_type_tag(btf, "typetag", 6); /* [19] typetag union u1; */ + btf__add_enum64(btf, "e64", 8, true); /* [20] enum { */ + btf__add_enum64_value(btf, "eval1", 1000); /* eval1 = 1000, */ + btf__add_enum64_value(btf, "eval2", 2000); /* eval2 = 2000, */ + btf__add_enum64_value(btf, "eval3", 3000); /* eval3 = 3000 */ + /* } */ + btf__add_datasec(btf, "datasec1", 12); /* [21] datasec datasec1 */ + btf__add_datasec_var_info(btf, 15, 0, 4); + btf__add_datasec_var_info(btf, 16, 4, 8); + + VALIDATE_RAW_BTF( + btf, + "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED", + "[2] INT 'int64' size=8 bits_offset=0 nr_bits=64 encoding=SIGNED", + "[3] PTR '(anon)' type_id=1", + "[4] ARRAY '(anon)' type_id=2 index_type_id=1 nr_elems=3", + "[5] STRUCT 's1' size=12 vlen=2\n" + "\t'f1' type_id=3 bits_offset=0\n" + "\t'f2' type_id=1 bits_offset=0", + "[6] UNION 'u1' size=12 vlen=2\n" + "\t'f1' type_id=1 bits_offset=0\n" + "\t'f2' type_id=5 bits_offset=0", + "[7] ENUM 'e1' encoding=UNSIGNED size=4 vlen=2\n" + "\t'v1' val=1\n" + "\t'v2' val=2", + "[8] FWD 'fw1' fwd_kind=struct", + "[9] TYPEDEF 't' type_id=1", + "[10] VOLATILE '(anon)' type_id=2", + "[11] CONST '(anon)' type_id=1", + "[12] RESTRICT '(anon)' type_id=3", + "[13] FUNC_PROTO '(anon)' ret_type_id=1 vlen=2\n" + "\t'p1' type_id=1\n" + "\t'p2' type_id=3", + "[14] FUNC 'func' type_id=13 linkage=global", + "[15] VAR 'var1' type_id=1, linkage=static", + "[16] VAR 'var2' type_id=3, linkage=static", + "[17] FLOAT 'float' size=4", + "[18] DECL_TAG 'decltag' type_id=11 component_idx=-1", + "[19] TYPE_TAG 'typetag' type_id=6", + "[20] ENUM64 'e64' encoding=SIGNED size=8 vlen=3\n" + "\t'eval1' val=1000\n" + "\t'eval2' val=2000\n" + "\t'eval3' val=3000", + "[21] DATASEC 'datasec1' size=12 vlen=2\n" + "\ttype_id=15 offset=0 size=4\n" + "\ttype_id=16 offset=4 size=8"); + + for (id = 1; id < btf__type_cnt(btf); id++) { + struct btf_type *t = btf_type_by_id(btf, id); + struct btf_field_iter it_strs, it_ids; + int str_idx = 0, id_idx = 0; + __u32 *next_str, *next_id; + + if (!ASSERT_OK_PTR(t, "btf_type_by_id")) + break; + if (!ASSERT_OK(btf_field_iter_init(&it_strs, t, BTF_FIELD_ITER_STRS), + "iter_init_strs")) + break; + if (!ASSERT_OK(btf_field_iter_init(&it_ids, t, BTF_FIELD_ITER_IDS), + "iter_init_ids")) + break; + while ((next_str = btf_field_iter_next(&it_strs))) { + const char *str = btf__str_by_offset(btf, *next_str); + + if (!ASSERT_OK(strcmp(fields[id].strs[str_idx], str), "field_str_match")) + break; + str_idx++; + } + /* ensure no more strings are expected */ + ASSERT_EQ(fields[id].strs[str_idx], NULL, "field_str_cnt"); + + while ((next_id = btf_field_iter_next(&it_ids))) { + if (!ASSERT_EQ(*next_id, fields[id].ids[id_idx], "field_id_match")) + break; + id_idx++; + } + /* ensure no more ids are expected */ + ASSERT_EQ(fields[id].ids[id_idx], 0, "field_id_cnt"); + } + btf__free(btf); +} diff --git a/tools/testing/selftests/bpf/prog_tests/cpumask.c b/tools/testing/selftests/bpf/prog_tests/cpumask.c index ecf89df78109..2570bd4b0cb2 100644 --- a/tools/testing/selftests/bpf/prog_tests/cpumask.c +++ b/tools/testing/selftests/bpf/prog_tests/cpumask.c @@ -18,6 +18,11 @@ static const char * const cpumask_success_testcases[] = { "test_insert_leave", "test_insert_remove_release", "test_global_mask_rcu", + "test_global_mask_array_one_rcu", + "test_global_mask_array_rcu", + "test_global_mask_array_l2_rcu", + "test_global_mask_nested_rcu", + "test_global_mask_nested_deep_rcu", "test_cpumask_weight", }; diff --git a/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c b/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c index 3b7c57fe55a5..08b6391f2f56 100644 --- a/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c +++ b/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c @@ -69,15 +69,17 @@ static struct test_case test_cases[] = { { N(SCHED_CLS, struct __sk_buff, tstamp), .read = "r11 = *(u8 *)($ctx + sk_buff::__mono_tc_offset);" - "w11 &= 3;" - "if w11 != 0x3 goto pc+2;" + "if w11 & 0x4 goto pc+1;" + "goto pc+4;" + "if w11 & 0x3 goto pc+1;" + "goto pc+2;" "$dst = 0;" "goto pc+1;" "$dst = *(u64 *)($ctx + sk_buff::tstamp);", .write = "r11 = *(u8 *)($ctx + sk_buff::__mono_tc_offset);" - "if w11 & 0x2 goto pc+1;" + "if w11 & 0x4 goto pc+1;" "goto pc+2;" - "w11 &= -2;" + "w11 &= -4;" "*(u8 *)($ctx + sk_buff::__mono_tc_offset) = r11;" "*(u64 *)($ctx + sk_buff::tstamp) = $src;", }, diff --git a/tools/testing/selftests/bpf/prog_tests/find_vma.c b/tools/testing/selftests/bpf/prog_tests/find_vma.c index 5165b38f0e59..f7619e0ade10 100644 --- a/tools/testing/selftests/bpf/prog_tests/find_vma.c +++ b/tools/testing/selftests/bpf/prog_tests/find_vma.c @@ -29,8 +29,8 @@ static int open_pe(void) /* create perf event */ attr.size = sizeof(attr); - attr.type = PERF_TYPE_HARDWARE; - attr.config = PERF_COUNT_HW_CPU_CYCLES; + attr.type = PERF_TYPE_SOFTWARE; + attr.config = PERF_COUNT_SW_CPU_CLOCK; attr.freq = 1; attr.sample_freq = 1000; pfd = syscall(__NR_perf_event_open, &attr, 0, -1, -1, PERF_FLAG_FD_CLOEXEC); diff --git a/tools/testing/selftests/bpf/prog_tests/linked_list.c b/tools/testing/selftests/bpf/prog_tests/linked_list.c index 2fb89de63bd2..77d07e0a4a55 100644 --- a/tools/testing/selftests/bpf/prog_tests/linked_list.c +++ b/tools/testing/selftests/bpf/prog_tests/linked_list.c @@ -183,6 +183,18 @@ static void test_linked_list_success(int mode, bool leave_in_map) if (!leave_in_map) clear_fields(skel->maps.bss_A); + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.global_list_push_pop_nested), &opts); + ASSERT_OK(ret, "global_list_push_pop_nested"); + ASSERT_OK(opts.retval, "global_list_push_pop_nested retval"); + if (!leave_in_map) + clear_fields(skel->maps.bss_A); + + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.global_list_array_push_pop), &opts); + ASSERT_OK(ret, "global_list_array_push_pop"); + ASSERT_OK(opts.retval, "global_list_array_push_pop retval"); + if (!leave_in_map) + clear_fields(skel->maps.bss_A); + if (mode == PUSH_POP) goto end; diff --git a/tools/testing/selftests/bpf/prog_tests/rbtree.c b/tools/testing/selftests/bpf/prog_tests/rbtree.c index e9300c96607d..9818f06c97c5 100644 --- a/tools/testing/selftests/bpf/prog_tests/rbtree.c +++ b/tools/testing/selftests/bpf/prog_tests/rbtree.c @@ -31,6 +31,28 @@ static void test_rbtree_add_nodes(void) rbtree__destroy(skel); } +static void test_rbtree_add_nodes_nested(void) +{ + LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); + struct rbtree *skel; + int ret; + + skel = rbtree__open_and_load(); + if (!ASSERT_OK_PTR(skel, "rbtree__open_and_load")) + return; + + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.rbtree_add_nodes_nested), &opts); + ASSERT_OK(ret, "rbtree_add_nodes_nested run"); + ASSERT_OK(opts.retval, "rbtree_add_nodes_nested retval"); + ASSERT_EQ(skel->data->less_callback_ran, 1, "rbtree_add_nodes_nested less_callback_ran"); + + rbtree__destroy(skel); +} + static void test_rbtree_add_and_remove(void) { LIBBPF_OPTS(bpf_test_run_opts, opts, @@ -53,6 +75,27 @@ static void test_rbtree_add_and_remove(void) rbtree__destroy(skel); } +static void test_rbtree_add_and_remove_array(void) +{ + LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); + struct rbtree *skel; + int ret; + + skel = rbtree__open_and_load(); + if (!ASSERT_OK_PTR(skel, "rbtree__open_and_load")) + return; + + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.rbtree_add_and_remove_array), &opts); + ASSERT_OK(ret, "rbtree_add_and_remove_array"); + ASSERT_OK(opts.retval, "rbtree_add_and_remove_array retval"); + + rbtree__destroy(skel); +} + static void test_rbtree_first_and_remove(void) { LIBBPF_OPTS(bpf_test_run_opts, opts, @@ -104,8 +147,12 @@ void test_rbtree_success(void) { if (test__start_subtest("rbtree_add_nodes")) test_rbtree_add_nodes(); + if (test__start_subtest("rbtree_add_nodes_nested")) + test_rbtree_add_nodes_nested(); if (test__start_subtest("rbtree_add_and_remove")) test_rbtree_add_and_remove(); + if (test__start_subtest("rbtree_add_and_remove_array")) + test_rbtree_add_and_remove_array(); if (test__start_subtest("rbtree_first_and_remove")) test_rbtree_first_and_remove(); if (test__start_subtest("rbtree_api_release_aliasing")) diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c index 920aee41bd58..6cc69900b310 100644 --- a/tools/testing/selftests/bpf/prog_tests/send_signal.c +++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c @@ -156,7 +156,8 @@ static void test_send_signal_tracepoint(bool signal_thread) static void test_send_signal_perf(bool signal_thread) { struct perf_event_attr attr = { - .sample_period = 1, + .freq = 1, + .sample_freq = 1000, .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_CLOCK, }; diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c index 1d3a20f01b60..7cd8be2780ca 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c @@ -70,7 +70,7 @@ static void *server_thread(void *arg) return (void *)(long)err; } -static int custom_cb(int fd, const struct post_socket_opts *opts) +static int custom_cb(int fd, void *opts) { char buf; int err; diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c index b1073d36d77a..327d51f59142 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c @@ -890,9 +890,6 @@ static void test_udp_dtime(struct test_tc_dtime *skel, int family, bool bpf_fwd) ASSERT_EQ(dtimes[INGRESS_FWDNS_P100], 0, dtime_cnt_str(t, INGRESS_FWDNS_P100)); - /* non mono delivery time is not forwarded */ - ASSERT_EQ(dtimes[INGRESS_FWDNS_P101], 0, - dtime_cnt_str(t, INGRESS_FWDNS_P101)); for (i = EGRESS_FWDNS_P100; i < SET_DTIME; i++) ASSERT_GT(dtimes[i], 0, dtime_cnt_str(t, i)); diff --git a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c index 29e183a80f49..bbcf12696a6b 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c +++ b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c @@ -3,9 +3,12 @@ #include <test_progs.h> #include <time.h> +#include <sys/epoll.h> + #include "struct_ops_module.skel.h" #include "struct_ops_nulled_out_cb.skel.h" #include "struct_ops_forgotten_cb.skel.h" +#include "struct_ops_detach.skel.h" static void check_map_info(struct bpf_map_info *info) { @@ -242,6 +245,58 @@ cleanup: struct_ops_forgotten_cb__destroy(skel); } +/* Detach a link from a user space program */ +static void test_detach_link(void) +{ + struct epoll_event ev, events[2]; + struct struct_ops_detach *skel; + struct bpf_link *link = NULL; + int fd, epollfd = -1, nfds; + int err; + + skel = struct_ops_detach__open_and_load(); + if (!ASSERT_OK_PTR(skel, "struct_ops_detach__open_and_load")) + return; + + link = bpf_map__attach_struct_ops(skel->maps.testmod_do_detach); + if (!ASSERT_OK_PTR(link, "attach_struct_ops")) + goto cleanup; + + fd = bpf_link__fd(link); + if (!ASSERT_GE(fd, 0, "link_fd")) + goto cleanup; + + epollfd = epoll_create1(0); + if (!ASSERT_GE(epollfd, 0, "epoll_create1")) + goto cleanup; + + ev.events = EPOLLHUP; + ev.data.fd = fd; + err = epoll_ctl(epollfd, EPOLL_CTL_ADD, fd, &ev); + if (!ASSERT_OK(err, "epoll_ctl")) + goto cleanup; + + err = bpf_link__detach(link); + if (!ASSERT_OK(err, "detach_link")) + goto cleanup; + + /* Wait for EPOLLHUP */ + nfds = epoll_wait(epollfd, events, 2, 500); + if (!ASSERT_EQ(nfds, 1, "epoll_wait")) + goto cleanup; + + if (!ASSERT_EQ(events[0].data.fd, fd, "epoll_wait_fd")) + goto cleanup; + if (!ASSERT_TRUE(events[0].events & EPOLLHUP, "events[0].events")) + goto cleanup; + +cleanup: + if (epollfd >= 0) + close(epollfd); + bpf_link__destroy(link); + struct_ops_detach__destroy(skel); +} + void serial_test_struct_ops_module(void) { if (test__start_subtest("struct_ops_load")) @@ -254,5 +309,7 @@ void serial_test_struct_ops_module(void) test_struct_ops_nulled_out_cb(); if (test__start_subtest("struct_ops_forgotten_cb")) test_struct_ops_forgotten_cb(); + if (test__start_subtest("test_detach_link")) + test_detach_link(); } diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index 98ef39efa77e..9dc3687bc406 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -87,6 +87,7 @@ #include "verifier_xadd.skel.h" #include "verifier_xdp.skel.h" #include "verifier_xdp_direct_packet_access.skel.h" +#include "verifier_bits_iter.skel.h" #define MAX_ENTRIES 11 @@ -204,6 +205,7 @@ void test_verifier_var_off(void) { RUN(verifier_var_off); } void test_verifier_xadd(void) { RUN(verifier_xadd); } void test_verifier_xdp(void) { RUN(verifier_xdp); } void test_verifier_xdp_direct_packet_access(void) { RUN(verifier_xdp_direct_packet_access); } +void test_verifier_bits_iter(void) { RUN(verifier_bits_iter); } static int init_test_val_map(struct bpf_object *obj, char *map_name) { diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_array_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_array_map.c index c5969ca6f26b..564835ba7d51 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_array_map.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_array_map.c @@ -6,12 +6,6 @@ char _license[] SEC("license") = "GPL"; -struct key_t { - int a; - int b; - int c; -}; - struct { __uint(type, BPF_MAP_TYPE_ARRAY); __uint(max_entries, 3); diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_array_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_array_map.c index 85fa710fad90..9f0e0705b2bf 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_array_map.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_array_map.c @@ -6,12 +6,6 @@ char _license[] SEC("license") = "GPL"; -struct key_t { - int a; - int b; - int c; -}; - struct { __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); __uint(max_entries, 3); diff --git a/tools/testing/selftests/bpf/progs/cpumask_success.c b/tools/testing/selftests/bpf/progs/cpumask_success.c index 7a1e64c6c065..fd8106831c32 100644 --- a/tools/testing/selftests/bpf/progs/cpumask_success.c +++ b/tools/testing/selftests/bpf/progs/cpumask_success.c @@ -12,6 +12,31 @@ char _license[] SEC("license") = "GPL"; int pid, nr_cpus; +struct kptr_nested { + struct bpf_cpumask __kptr * mask; +}; + +struct kptr_nested_pair { + struct bpf_cpumask __kptr * mask_1; + struct bpf_cpumask __kptr * mask_2; +}; + +struct kptr_nested_mid { + int dummy; + struct kptr_nested m; +}; + +struct kptr_nested_deep { + struct kptr_nested_mid ptrs[2]; + struct kptr_nested_pair ptr_pairs[3]; +}; + +private(MASK) static struct bpf_cpumask __kptr * global_mask_array[2]; +private(MASK) static struct bpf_cpumask __kptr * global_mask_array_l2[2][1]; +private(MASK) static struct bpf_cpumask __kptr * global_mask_array_one[1]; +private(MASK) static struct kptr_nested global_mask_nested[2]; +private(MASK_DEEP) static struct kptr_nested_deep global_mask_nested_deep; + static bool is_test_task(void) { int cur_pid = bpf_get_current_pid_tgid() >> 32; @@ -461,6 +486,152 @@ int BPF_PROG(test_global_mask_rcu, struct task_struct *task, u64 clone_flags) } SEC("tp_btf/task_newtask") +int BPF_PROG(test_global_mask_array_one_rcu, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *local, *prev; + + if (!is_test_task()) + return 0; + + /* Kptr arrays with one element are special cased, being treated + * just like a single pointer. + */ + + local = create_cpumask(); + if (!local) + return 0; + + prev = bpf_kptr_xchg(&global_mask_array_one[0], local); + if (prev) { + bpf_cpumask_release(prev); + err = 3; + return 0; + } + + bpf_rcu_read_lock(); + local = global_mask_array_one[0]; + if (!local) { + err = 4; + bpf_rcu_read_unlock(); + return 0; + } + + bpf_rcu_read_unlock(); + + return 0; +} + +static int _global_mask_array_rcu(struct bpf_cpumask **mask0, + struct bpf_cpumask **mask1) +{ + struct bpf_cpumask *local; + + if (!is_test_task()) + return 0; + + /* Check if two kptrs in the array work and independently */ + + local = create_cpumask(); + if (!local) + return 0; + + bpf_rcu_read_lock(); + + local = bpf_kptr_xchg(mask0, local); + if (local) { + err = 1; + goto err_exit; + } + + /* [<mask 0>, NULL] */ + if (!*mask0 || *mask1) { + err = 2; + goto err_exit; + } + + local = create_cpumask(); + if (!local) { + err = 9; + goto err_exit; + } + + local = bpf_kptr_xchg(mask1, local); + if (local) { + err = 10; + goto err_exit; + } + + /* [<mask 0>, <mask 1>] */ + if (!*mask0 || !*mask1 || *mask0 == *mask1) { + err = 11; + goto err_exit; + } + +err_exit: + if (local) + bpf_cpumask_release(local); + bpf_rcu_read_unlock(); + return 0; +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_global_mask_array_rcu, struct task_struct *task, u64 clone_flags) +{ + return _global_mask_array_rcu(&global_mask_array[0], &global_mask_array[1]); +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_global_mask_array_l2_rcu, struct task_struct *task, u64 clone_flags) +{ + return _global_mask_array_rcu(&global_mask_array_l2[0][0], &global_mask_array_l2[1][0]); +} + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_global_mask_nested_rcu, struct task_struct *task, u64 clone_flags) +{ + return _global_mask_array_rcu(&global_mask_nested[0].mask, &global_mask_nested[1].mask); +} + +/* Ensure that the field->offset has been correctly advanced from one + * nested struct or array sub-tree to another. In the case of + * kptr_nested_deep, it comprises two sub-trees: ktpr_1 and kptr_2. By + * calling bpf_kptr_xchg() on every single kptr in both nested sub-trees, + * the verifier should reject the program if the field->offset of any kptr + * is incorrect. + * + * For instance, if we have 10 kptrs in a nested struct and a program that + * accesses each kptr individually with bpf_kptr_xchg(), the compiler + * should emit instructions to access 10 different offsets if it works + * correctly. If the field->offset values of any pair of them are + * incorrectly the same, the number of unique offsets in btf_record for + * this nested struct should be less than 10. The verifier should fail to + * discover some of the offsets emitted by the compiler. + * + * Even if the field->offset values of kptrs are not duplicated, the + * verifier should fail to find a btf_field for the instruction accessing a + * kptr if the corresponding field->offset is pointing to a random + * incorrect offset. + */ +SEC("tp_btf/task_newtask") +int BPF_PROG(test_global_mask_nested_deep_rcu, struct task_struct *task, u64 clone_flags) +{ + int r, i; + + r = _global_mask_array_rcu(&global_mask_nested_deep.ptrs[0].m.mask, + &global_mask_nested_deep.ptrs[1].m.mask); + if (r) + return r; + + for (i = 0; i < 3; i++) { + r = _global_mask_array_rcu(&global_mask_nested_deep.ptr_pairs[i].mask_1, + &global_mask_nested_deep.ptr_pairs[i].mask_2); + if (r) + return r; + } + return 0; +} + +SEC("tp_btf/task_newtask") int BPF_PROG(test_cpumask_weight, struct task_struct *task, u64 clone_flags) { struct bpf_cpumask *local; diff --git a/tools/testing/selftests/bpf/progs/linked_list.c b/tools/testing/selftests/bpf/progs/linked_list.c index 26205ca80679..f69bf3e30321 100644 --- a/tools/testing/selftests/bpf/progs/linked_list.c +++ b/tools/testing/selftests/bpf/progs/linked_list.c @@ -11,6 +11,22 @@ #include "linked_list.h" +struct head_nested_inner { + struct bpf_spin_lock lock; + struct bpf_list_head head __contains(foo, node2); +}; + +struct head_nested { + int dummy; + struct head_nested_inner inner; +}; + +private(C) struct bpf_spin_lock glock_c; +private(C) struct bpf_list_head ghead_array[2] __contains(foo, node2); +private(C) struct bpf_list_head ghead_array_one[1] __contains(foo, node2); + +private(D) struct head_nested ghead_nested; + static __always_inline int list_push_pop(struct bpf_spin_lock *lock, struct bpf_list_head *head, bool leave_in_map) { @@ -310,6 +326,32 @@ int global_list_push_pop(void *ctx) } SEC("tc") +int global_list_push_pop_nested(void *ctx) +{ + return test_list_push_pop(&ghead_nested.inner.lock, &ghead_nested.inner.head); +} + +SEC("tc") +int global_list_array_push_pop(void *ctx) +{ + int r; + + r = test_list_push_pop(&glock_c, &ghead_array[0]); + if (r) + return r; + + r = test_list_push_pop(&glock_c, &ghead_array[1]); + if (r) + return r; + + /* Arrays with only one element is a special case, being treated + * just like a bpf_list_head variable by the verifier, not an + * array. + */ + return test_list_push_pop(&glock_c, &ghead_array_one[0]); +} + +SEC("tc") int map_list_push_pop_multiple(void *ctx) { struct map_value *v; diff --git a/tools/testing/selftests/bpf/progs/rbtree.c b/tools/testing/selftests/bpf/progs/rbtree.c index b09f4fffe57c..a3620c15c136 100644 --- a/tools/testing/selftests/bpf/progs/rbtree.c +++ b/tools/testing/selftests/bpf/progs/rbtree.c @@ -13,6 +13,15 @@ struct node_data { struct bpf_rb_node node; }; +struct root_nested_inner { + struct bpf_spin_lock glock; + struct bpf_rb_root root __contains(node_data, node); +}; + +struct root_nested { + struct root_nested_inner inner; +}; + long less_callback_ran = -1; long removed_key = -1; long first_data[2] = {-1, -1}; @@ -20,6 +29,9 @@ long first_data[2] = {-1, -1}; #define private(name) SEC(".data." #name) __hidden __attribute__((aligned(8))) private(A) struct bpf_spin_lock glock; private(A) struct bpf_rb_root groot __contains(node_data, node); +private(A) struct bpf_rb_root groot_array[2] __contains(node_data, node); +private(A) struct bpf_rb_root groot_array_one[1] __contains(node_data, node); +private(B) struct root_nested groot_nested; static bool less(struct bpf_rb_node *a, const struct bpf_rb_node *b) { @@ -72,6 +84,12 @@ long rbtree_add_nodes(void *ctx) } SEC("tc") +long rbtree_add_nodes_nested(void *ctx) +{ + return __add_three(&groot_nested.inner.root, &groot_nested.inner.glock); +} + +SEC("tc") long rbtree_add_and_remove(void *ctx) { struct bpf_rb_node *res = NULL; @@ -110,6 +128,65 @@ err_out: } SEC("tc") +long rbtree_add_and_remove_array(void *ctx) +{ + struct bpf_rb_node *res1 = NULL, *res2 = NULL, *res3 = NULL; + struct node_data *nodes[3][2] = {{NULL, NULL}, {NULL, NULL}, {NULL, NULL}}; + struct node_data *n; + long k1 = -1, k2 = -1, k3 = -1; + int i, j; + + for (i = 0; i < 3; i++) { + for (j = 0; j < 2; j++) { + nodes[i][j] = bpf_obj_new(typeof(*nodes[i][j])); + if (!nodes[i][j]) + goto err_out; + nodes[i][j]->key = i * 2 + j; + } + } + + bpf_spin_lock(&glock); + for (i = 0; i < 2; i++) + for (j = 0; j < 2; j++) + bpf_rbtree_add(&groot_array[i], &nodes[i][j]->node, less); + for (j = 0; j < 2; j++) + bpf_rbtree_add(&groot_array_one[0], &nodes[2][j]->node, less); + res1 = bpf_rbtree_remove(&groot_array[0], &nodes[0][0]->node); + res2 = bpf_rbtree_remove(&groot_array[1], &nodes[1][0]->node); + res3 = bpf_rbtree_remove(&groot_array_one[0], &nodes[2][0]->node); + bpf_spin_unlock(&glock); + + if (res1) { + n = container_of(res1, struct node_data, node); + k1 = n->key; + bpf_obj_drop(n); + } + if (res2) { + n = container_of(res2, struct node_data, node); + k2 = n->key; + bpf_obj_drop(n); + } + if (res3) { + n = container_of(res3, struct node_data, node); + k3 = n->key; + bpf_obj_drop(n); + } + if (k1 != 0 || k2 != 2 || k3 != 4) + return 2; + + return 0; + +err_out: + for (i = 0; i < 3; i++) { + for (j = 0; j < 2; j++) { + if (nodes[i][j]) + bpf_obj_drop(nodes[i][j]); + } + } + return 1; +} + +SEC("tc") long rbtree_first_and_remove(void *ctx) { struct bpf_rb_node *res = NULL; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_detach.c b/tools/testing/selftests/bpf/progs/struct_ops_detach.c new file mode 100644 index 000000000000..56b787a89876 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/struct_ops_detach.c @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include "../bpf_testmod/bpf_testmod.h" + +char _license[] SEC("license") = "GPL"; + +SEC(".struct_ops.link") +struct bpf_testmod_ops testmod_do_detach; diff --git a/tools/testing/selftests/bpf/progs/test_bpf_nf.c b/tools/testing/selftests/bpf/progs/test_bpf_nf.c index 77ad8adf68da..0289d8ce2b80 100644 --- a/tools/testing/selftests/bpf/progs/test_bpf_nf.c +++ b/tools/testing/selftests/bpf/progs/test_bpf_nf.c @@ -9,10 +9,14 @@ #define EINVAL 22 #define ENOENT 2 +#define NF_CT_ZONE_DIR_ORIG (1 << IP_CT_DIR_ORIGINAL) +#define NF_CT_ZONE_DIR_REPL (1 << IP_CT_DIR_REPLY) + extern unsigned long CONFIG_HZ __kconfig; int test_einval_bpf_tuple = 0; int test_einval_reserved = 0; +int test_einval_reserved_new = 0; int test_einval_netns_id = 0; int test_einval_len_opts = 0; int test_eproto_l4proto = 0; @@ -22,6 +26,11 @@ int test_eafnosupport = 0; int test_alloc_entry = -EINVAL; int test_insert_entry = -EAFNOSUPPORT; int test_succ_lookup = -ENOENT; +int test_ct_zone_id_alloc_entry = -EINVAL; +int test_ct_zone_id_insert_entry = -EAFNOSUPPORT; +int test_ct_zone_id_succ_lookup = -ENOENT; +int test_ct_zone_dir_enoent_lookup = 0; +int test_ct_zone_id_enoent_lookup = 0; u32 test_delta_timeout = 0; u32 test_status = 0; u32 test_insert_lookup_mark = 0; @@ -45,6 +54,17 @@ struct bpf_ct_opts___local { s32 netns_id; s32 error; u8 l4proto; + u8 dir; + u8 reserved[2]; +}; + +struct bpf_ct_opts___new { + s32 netns_id; + s32 error; + u8 l4proto; + u8 dir; + u16 ct_zone_id; + u8 ct_zone_dir; u8 reserved[3]; } __attribute__((preserve_access_index)); @@ -220,10 +240,97 @@ nf_ct_test(struct nf_conn *(*lookup_fn)(void *, struct bpf_sock_tuple *, u32, } } +static __always_inline void +nf_ct_opts_new_test(struct nf_conn *(*lookup_fn)(void *, struct bpf_sock_tuple *, u32, + struct bpf_ct_opts___new *, u32), + struct nf_conn *(*alloc_fn)(void *, struct bpf_sock_tuple *, u32, + struct bpf_ct_opts___new *, u32), + void *ctx) +{ + struct bpf_ct_opts___new opts_def = { .l4proto = IPPROTO_TCP, .netns_id = -1 }; + struct bpf_sock_tuple bpf_tuple; + struct nf_conn *ct; + + __builtin_memset(&bpf_tuple, 0, sizeof(bpf_tuple.ipv4)); + + opts_def.reserved[0] = 1; + ct = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, + sizeof(opts_def)); + opts_def.reserved[0] = 0; + if (ct) + bpf_ct_release(ct); + else + test_einval_reserved_new = opts_def.error; + + bpf_tuple.ipv4.saddr = bpf_get_prandom_u32(); /* src IP */ + bpf_tuple.ipv4.daddr = bpf_get_prandom_u32(); /* dst IP */ + bpf_tuple.ipv4.sport = bpf_get_prandom_u32(); /* src port */ + bpf_tuple.ipv4.dport = bpf_get_prandom_u32(); /* dst port */ + + /* use non-default ct zone */ + opts_def.ct_zone_id = 10; + opts_def.ct_zone_dir = NF_CT_ZONE_DIR_ORIG; + ct = alloc_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, + sizeof(opts_def)); + if (ct) { + __u16 sport = bpf_get_prandom_u32(); + __u16 dport = bpf_get_prandom_u32(); + union nf_inet_addr saddr = {}; + union nf_inet_addr daddr = {}; + struct nf_conn *ct_ins; + + bpf_ct_set_timeout(ct, 10000); + + /* snat */ + saddr.ip = bpf_get_prandom_u32(); + bpf_ct_set_nat_info(ct, &saddr, sport, NF_NAT_MANIP_SRC___local); + /* dnat */ + daddr.ip = bpf_get_prandom_u32(); + bpf_ct_set_nat_info(ct, &daddr, dport, NF_NAT_MANIP_DST___local); + + ct_ins = bpf_ct_insert_entry(ct); + if (ct_ins) { + struct nf_conn *ct_lk; + + /* entry should exist in same ct zone we inserted it */ + ct_lk = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), + &opts_def, sizeof(opts_def)); + if (ct_lk) { + bpf_ct_release(ct_lk); + test_ct_zone_id_succ_lookup = 0; + } + + /* entry should not exist with wrong direction */ + opts_def.ct_zone_dir = NF_CT_ZONE_DIR_REPL; + ct_lk = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), + &opts_def, sizeof(opts_def)); + opts_def.ct_zone_dir = NF_CT_ZONE_DIR_ORIG; + if (ct_lk) + bpf_ct_release(ct_lk); + else + test_ct_zone_dir_enoent_lookup = opts_def.error; + + /* entry should not exist in default ct zone */ + opts_def.ct_zone_id = 0; + ct_lk = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), + &opts_def, sizeof(opts_def)); + if (ct_lk) + bpf_ct_release(ct_lk); + else + test_ct_zone_id_enoent_lookup = opts_def.error; + + bpf_ct_release(ct_ins); + test_ct_zone_id_insert_entry = 0; + } + test_ct_zone_id_alloc_entry = 0; + } +} + SEC("xdp") int nf_xdp_ct_test(struct xdp_md *ctx) { nf_ct_test((void *)bpf_xdp_ct_lookup, (void *)bpf_xdp_ct_alloc, ctx); + nf_ct_opts_new_test((void *)bpf_xdp_ct_lookup, (void *)bpf_xdp_ct_alloc, ctx); return 0; } @@ -231,6 +338,7 @@ SEC("tc") int nf_skb_ct_test(struct __sk_buff *ctx) { nf_ct_test((void *)bpf_skb_ct_lookup, (void *)bpf_skb_ct_alloc, ctx); + nf_ct_opts_new_test((void *)bpf_skb_ct_lookup, (void *)bpf_skb_ct_alloc, ctx); return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h index 99d2ea9fb658..f48f85f1bd70 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h +++ b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h @@ -92,7 +92,7 @@ struct { __uint(value_size, sizeof(int)); } tls_sock_map SEC(".maps"); -SEC("sk_skb1") +SEC("sk_skb/stream_parser") int bpf_prog1(struct __sk_buff *skb) { int *f, two = 2; @@ -104,7 +104,7 @@ int bpf_prog1(struct __sk_buff *skb) return skb->len; } -SEC("sk_skb2") +SEC("sk_skb/stream_verdict") int bpf_prog2(struct __sk_buff *skb) { __u32 lport = skb->local_port; @@ -151,7 +151,7 @@ static inline void bpf_write_pass(struct __sk_buff *skb, int offset) memcpy(c + offset, "PASS", 4); } -SEC("sk_skb3") +SEC("sk_skb/stream_verdict") int bpf_prog3(struct __sk_buff *skb) { int err, *f, ret = SK_PASS; @@ -177,9 +177,6 @@ int bpf_prog3(struct __sk_buff *skb) return bpf_sk_redirect_hash(skb, &tls_sock_map, &ret, flags); #endif } - f = bpf_map_lookup_elem(&sock_skb_opts, &one); - if (f && *f) - ret = SK_DROP; err = bpf_skb_adjust_room(skb, 4, 0, 0); if (err) return SK_DROP; @@ -233,7 +230,7 @@ int bpf_sockmap(struct bpf_sock_ops *skops) return 0; } -SEC("sk_msg1") +SEC("sk_msg") int bpf_prog4(struct sk_msg_md *msg) { int *bytes, zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5; @@ -263,7 +260,7 @@ int bpf_prog4(struct sk_msg_md *msg) return SK_PASS; } -SEC("sk_msg2") +SEC("sk_msg") int bpf_prog6(struct sk_msg_md *msg) { int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5, key = 0; @@ -308,7 +305,7 @@ int bpf_prog6(struct sk_msg_md *msg) #endif } -SEC("sk_msg3") +SEC("sk_msg") int bpf_prog8(struct sk_msg_md *msg) { void *data_end = (void *)(long) msg->data_end; @@ -329,7 +326,8 @@ int bpf_prog8(struct sk_msg_md *msg) return SK_PASS; } -SEC("sk_msg4") + +SEC("sk_msg") int bpf_prog9(struct sk_msg_md *msg) { void *data_end = (void *)(long) msg->data_end; @@ -347,7 +345,7 @@ int bpf_prog9(struct sk_msg_md *msg) return SK_PASS; } -SEC("sk_msg5") +SEC("sk_msg") int bpf_prog10(struct sk_msg_md *msg) { int *bytes, *start, *end, *start_push, *end_push, *start_pop, *pop; diff --git a/tools/testing/selftests/bpf/progs/test_tc_dtime.c b/tools/testing/selftests/bpf/progs/test_tc_dtime.c index 74ec09f040b7..ca8e8734d901 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_dtime.c +++ b/tools/testing/selftests/bpf/progs/test_tc_dtime.c @@ -222,17 +222,21 @@ int egress_host(struct __sk_buff *skb) return TC_ACT_OK; if (skb_proto(skb_type) == IPPROTO_TCP) { - if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO && + if (skb->tstamp_type == BPF_SKB_CLOCK_MONOTONIC && skb->tstamp) inc_dtimes(EGRESS_ENDHOST); else inc_errs(EGRESS_ENDHOST); - } else { - if (skb->tstamp_type == BPF_SKB_TSTAMP_UNSPEC && + } else if (skb_proto(skb_type) == IPPROTO_UDP) { + if (skb->tstamp_type == BPF_SKB_CLOCK_TAI && skb->tstamp) inc_dtimes(EGRESS_ENDHOST); else inc_errs(EGRESS_ENDHOST); + } else { + if (skb->tstamp_type == BPF_SKB_CLOCK_REALTIME && + skb->tstamp) + inc_errs(EGRESS_ENDHOST); } skb->tstamp = EGRESS_ENDHOST_MAGIC; @@ -252,7 +256,7 @@ int ingress_host(struct __sk_buff *skb) if (!skb_type) return TC_ACT_OK; - if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO && + if (skb->tstamp_type == BPF_SKB_CLOCK_MONOTONIC && skb->tstamp == EGRESS_FWDNS_MAGIC) inc_dtimes(INGRESS_ENDHOST); else @@ -315,7 +319,6 @@ int egress_fwdns_prio100(struct __sk_buff *skb) SEC("tc") int ingress_fwdns_prio101(struct __sk_buff *skb) { - __u64 expected_dtime = EGRESS_ENDHOST_MAGIC; int skb_type; skb_type = skb_get_type(skb); @@ -323,29 +326,24 @@ int ingress_fwdns_prio101(struct __sk_buff *skb) /* Should have handled in prio100 */ return TC_ACT_SHOT; - if (skb_proto(skb_type) == IPPROTO_UDP) - expected_dtime = 0; - if (skb->tstamp_type) { if (fwdns_clear_dtime() || - skb->tstamp_type != BPF_SKB_TSTAMP_DELIVERY_MONO || - skb->tstamp != expected_dtime) + (skb->tstamp_type != BPF_SKB_CLOCK_MONOTONIC && + skb->tstamp_type != BPF_SKB_CLOCK_TAI) || + skb->tstamp != EGRESS_ENDHOST_MAGIC) inc_errs(INGRESS_FWDNS_P101); else inc_dtimes(INGRESS_FWDNS_P101); } else { - if (!fwdns_clear_dtime() && expected_dtime) + if (!fwdns_clear_dtime()) inc_errs(INGRESS_FWDNS_P101); } - if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO) { + if (skb->tstamp_type == BPF_SKB_CLOCK_MONOTONIC) { skb->tstamp = INGRESS_FWDNS_MAGIC; } else { if (bpf_skb_set_tstamp(skb, INGRESS_FWDNS_MAGIC, - BPF_SKB_TSTAMP_DELIVERY_MONO)) - inc_errs(SET_DTIME); - if (!bpf_skb_set_tstamp(skb, INGRESS_FWDNS_MAGIC, - BPF_SKB_TSTAMP_UNSPEC)) + BPF_SKB_CLOCK_MONOTONIC)) inc_errs(SET_DTIME); } @@ -370,7 +368,7 @@ int egress_fwdns_prio101(struct __sk_buff *skb) if (skb->tstamp_type) { if (fwdns_clear_dtime() || - skb->tstamp_type != BPF_SKB_TSTAMP_DELIVERY_MONO || + skb->tstamp_type != BPF_SKB_CLOCK_MONOTONIC || skb->tstamp != INGRESS_FWDNS_MAGIC) inc_errs(EGRESS_FWDNS_P101); else @@ -380,14 +378,11 @@ int egress_fwdns_prio101(struct __sk_buff *skb) inc_errs(EGRESS_FWDNS_P101); } - if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO) { + if (skb->tstamp_type == BPF_SKB_CLOCK_MONOTONIC) { skb->tstamp = EGRESS_FWDNS_MAGIC; } else { if (bpf_skb_set_tstamp(skb, EGRESS_FWDNS_MAGIC, - BPF_SKB_TSTAMP_DELIVERY_MONO)) - inc_errs(SET_DTIME); - if (!bpf_skb_set_tstamp(skb, INGRESS_FWDNS_MAGIC, - BPF_SKB_TSTAMP_UNSPEC)) + BPF_SKB_CLOCK_MONOTONIC)) inc_errs(SET_DTIME); } diff --git a/tools/testing/selftests/bpf/progs/verifier_bits_iter.c b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c new file mode 100644 index 000000000000..716113c2bce2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c @@ -0,0 +1,153 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2024 Yafang Shao <laoar.shao@gmail.com> */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#include "bpf_misc.h" +#include "task_kfunc_common.h" + +char _license[] SEC("license") = "GPL"; + +int bpf_iter_bits_new(struct bpf_iter_bits *it, const u64 *unsafe_ptr__ign, + u32 nr_bits) __ksym __weak; +int *bpf_iter_bits_next(struct bpf_iter_bits *it) __ksym __weak; +void bpf_iter_bits_destroy(struct bpf_iter_bits *it) __ksym __weak; + +SEC("iter.s/cgroup") +__description("bits iter without destroy") +__failure __msg("Unreleased reference") +int BPF_PROG(no_destroy, struct bpf_iter_meta *meta, struct cgroup *cgrp) +{ + struct bpf_iter_bits it; + u64 data = 1; + + bpf_iter_bits_new(&it, &data, 1); + bpf_iter_bits_next(&it); + return 0; +} + +SEC("iter/cgroup") +__description("uninitialized iter in ->next()") +__failure __msg("expected an initialized iter_bits as arg #1") +int BPF_PROG(next_uninit, struct bpf_iter_meta *meta, struct cgroup *cgrp) +{ + struct bpf_iter_bits *it = NULL; + + bpf_iter_bits_next(it); + return 0; +} + +SEC("iter/cgroup") +__description("uninitialized iter in ->destroy()") +__failure __msg("expected an initialized iter_bits as arg #1") +int BPF_PROG(destroy_uninit, struct bpf_iter_meta *meta, struct cgroup *cgrp) +{ + struct bpf_iter_bits it = {}; + + bpf_iter_bits_destroy(&it); + return 0; +} + +SEC("syscall") +__description("null pointer") +__success __retval(0) +int null_pointer(void) +{ + int nr = 0; + int *bit; + + bpf_for_each(bits, bit, NULL, 1) + nr++; + return nr; +} + +SEC("syscall") +__description("bits copy") +__success __retval(10) +int bits_copy(void) +{ + u64 data = 0xf7310UL; /* 4 + 3 + 2 + 1 + 0*/ + int nr = 0; + int *bit; + + bpf_for_each(bits, bit, &data, 1) + nr++; + return nr; +} + +SEC("syscall") +__description("bits memalloc") +__success __retval(64) +int bits_memalloc(void) +{ + u64 data[2]; + int nr = 0; + int *bit; + + __builtin_memset(&data, 0xf0, sizeof(data)); /* 4 * 16 */ + bpf_for_each(bits, bit, &data[0], sizeof(data) / sizeof(u64)) + nr++; + return nr; +} + +SEC("syscall") +__description("bit index") +__success __retval(8) +int bit_index(void) +{ + u64 data = 0x100; + int bit_idx = 0; + int *bit; + + bpf_for_each(bits, bit, &data, 1) { + if (*bit == 0) + continue; + bit_idx = *bit; + } + return bit_idx; +} + +SEC("syscall") +__description("bits nomem") +__success __retval(0) +int bits_nomem(void) +{ + u64 data[4]; + int nr = 0; + int *bit; + + __builtin_memset(&data, 0xff, sizeof(data)); + bpf_for_each(bits, bit, &data[0], 513) /* Be greater than 512 */ + nr++; + return nr; +} + +SEC("syscall") +__description("fewer words") +__success __retval(1) +int fewer_words(void) +{ + u64 data[2] = {0x1, 0xff}; + int nr = 0; + int *bit; + + bpf_for_each(bits, bit, &data[0], 1) + nr++; + return nr; +} + +SEC("syscall") +__description("zero words") +__success __retval(0) +int zero_words(void) +{ + u64 data[2] = {0x1, 0xff}; + int nr = 0; + int *bit; + + bpf_for_each(bits, bit, &data[0], 0) + nr++; + return nr; +} diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index 92752f5eeded..9cba4ec844a5 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -63,7 +63,8 @@ int passed; int failed; int map_fd[9]; struct bpf_map *maps[9]; -int prog_fd[11]; +struct bpf_program *progs[9]; +struct bpf_link *links[9]; int txmsg_pass; int txmsg_redir; @@ -680,7 +681,8 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt, } } - s->bytes_recvd += recv; + if (recv > 0) + s->bytes_recvd += recv; if (opt->check_recved_len && s->bytes_recvd > total_bytes) { errno = EMSGSIZE; @@ -952,7 +954,8 @@ enum { static int run_options(struct sockmap_options *options, int cg_fd, int test) { - int i, key, next_key, err, tx_prog_fd = -1, zero = 0; + int i, key, next_key, err, zero = 0; + struct bpf_program *tx_prog; /* If base test skip BPF setup */ if (test == BASE || test == BASE_SENDPAGE) @@ -960,48 +963,44 @@ static int run_options(struct sockmap_options *options, int cg_fd, int test) /* Attach programs to sockmap */ if (!txmsg_omit_skb_parser) { - err = bpf_prog_attach(prog_fd[0], map_fd[0], - BPF_SK_SKB_STREAM_PARSER, 0); - if (err) { + links[0] = bpf_program__attach_sockmap(progs[0], map_fd[0]); + if (!links[0]) { fprintf(stderr, - "ERROR: bpf_prog_attach (sockmap %i->%i): %d (%s)\n", - prog_fd[0], map_fd[0], err, strerror(errno)); - return err; + "ERROR: bpf_program__attach_sockmap (sockmap %i->%i): (%s)\n", + bpf_program__fd(progs[0]), map_fd[0], strerror(errno)); + return -1; } } - err = bpf_prog_attach(prog_fd[1], map_fd[0], - BPF_SK_SKB_STREAM_VERDICT, 0); - if (err) { - fprintf(stderr, "ERROR: bpf_prog_attach (sockmap): %d (%s)\n", - err, strerror(errno)); - return err; + links[1] = bpf_program__attach_sockmap(progs[1], map_fd[0]); + if (!links[1]) { + fprintf(stderr, "ERROR: bpf_program__attach_sockmap (sockmap): (%s)\n", + strerror(errno)); + return -1; } /* Attach programs to TLS sockmap */ if (txmsg_ktls_skb) { if (!txmsg_omit_skb_parser) { - err = bpf_prog_attach(prog_fd[0], map_fd[8], - BPF_SK_SKB_STREAM_PARSER, 0); - if (err) { + links[2] = bpf_program__attach_sockmap(progs[0], map_fd[8]); + if (!links[2]) { fprintf(stderr, - "ERROR: bpf_prog_attach (TLS sockmap %i->%i): %d (%s)\n", - prog_fd[0], map_fd[8], err, strerror(errno)); - return err; + "ERROR: bpf_program__attach_sockmap (TLS sockmap %i->%i): (%s)\n", + bpf_program__fd(progs[0]), map_fd[8], strerror(errno)); + return -1; } } - err = bpf_prog_attach(prog_fd[2], map_fd[8], - BPF_SK_SKB_STREAM_VERDICT, 0); - if (err) { - fprintf(stderr, "ERROR: bpf_prog_attach (TLS sockmap): %d (%s)\n", - err, strerror(errno)); - return err; + links[3] = bpf_program__attach_sockmap(progs[2], map_fd[8]); + if (!links[3]) { + fprintf(stderr, "ERROR: bpf_program__attach_sockmap (TLS sockmap): (%s)\n", + strerror(errno)); + return -1; } } /* Attach to cgroups */ - err = bpf_prog_attach(prog_fd[3], cg_fd, BPF_CGROUP_SOCK_OPS, 0); + err = bpf_prog_attach(bpf_program__fd(progs[3]), cg_fd, BPF_CGROUP_SOCK_OPS, 0); if (err) { fprintf(stderr, "ERROR: bpf_prog_attach (groups): %d (%s)\n", err, strerror(errno)); @@ -1017,30 +1016,31 @@ run: /* Attach txmsg program to sockmap */ if (txmsg_pass) - tx_prog_fd = prog_fd[4]; + tx_prog = progs[4]; else if (txmsg_redir) - tx_prog_fd = prog_fd[5]; + tx_prog = progs[5]; else if (txmsg_apply) - tx_prog_fd = prog_fd[6]; + tx_prog = progs[6]; else if (txmsg_cork) - tx_prog_fd = prog_fd[7]; + tx_prog = progs[7]; else if (txmsg_drop) - tx_prog_fd = prog_fd[8]; + tx_prog = progs[8]; else - tx_prog_fd = 0; + tx_prog = NULL; - if (tx_prog_fd) { - int redir_fd, i = 0; + if (tx_prog) { + int redir_fd; - err = bpf_prog_attach(tx_prog_fd, - map_fd[1], BPF_SK_MSG_VERDICT, 0); - if (err) { + links[4] = bpf_program__attach_sockmap(tx_prog, map_fd[1]); + if (!links[4]) { fprintf(stderr, - "ERROR: bpf_prog_attach (txmsg): %d (%s)\n", - err, strerror(errno)); + "ERROR: bpf_program__attach_sockmap (txmsg): (%s)\n", + strerror(errno)); + err = -1; goto out; } + i = 0; err = bpf_map_update_elem(map_fd[1], &i, &c1, BPF_ANY); if (err) { fprintf(stderr, @@ -1279,16 +1279,14 @@ run: fprintf(stderr, "unknown test\n"); out: /* Detatch and zero all the maps */ - bpf_prog_detach2(prog_fd[3], cg_fd, BPF_CGROUP_SOCK_OPS); - bpf_prog_detach2(prog_fd[0], map_fd[0], BPF_SK_SKB_STREAM_PARSER); - bpf_prog_detach2(prog_fd[1], map_fd[0], BPF_SK_SKB_STREAM_VERDICT); - bpf_prog_detach2(prog_fd[0], map_fd[8], BPF_SK_SKB_STREAM_PARSER); - bpf_prog_detach2(prog_fd[2], map_fd[8], BPF_SK_SKB_STREAM_VERDICT); + bpf_prog_detach2(bpf_program__fd(progs[3]), cg_fd, BPF_CGROUP_SOCK_OPS); - if (tx_prog_fd >= 0) - bpf_prog_detach2(tx_prog_fd, map_fd[1], BPF_SK_MSG_VERDICT); + for (i = 0; i < ARRAY_SIZE(links); i++) { + if (links[i]) + bpf_link__detach(links[i]); + } - for (i = 0; i < 8; i++) { + for (i = 0; i < ARRAY_SIZE(map_fd); i++) { key = next_key = 0; bpf_map_update_elem(map_fd[i], &key, &zero, BPF_ANY); while (bpf_map_get_next_key(map_fd[i], &key, &next_key) == 0) { @@ -1783,34 +1781,6 @@ char *map_names[] = { "tls_sock_map", }; -int prog_attach_type[] = { - BPF_SK_SKB_STREAM_PARSER, - BPF_SK_SKB_STREAM_VERDICT, - BPF_SK_SKB_STREAM_VERDICT, - BPF_CGROUP_SOCK_OPS, - BPF_SK_MSG_VERDICT, - BPF_SK_MSG_VERDICT, - BPF_SK_MSG_VERDICT, - BPF_SK_MSG_VERDICT, - BPF_SK_MSG_VERDICT, - BPF_SK_MSG_VERDICT, - BPF_SK_MSG_VERDICT, -}; - -int prog_type[] = { - BPF_PROG_TYPE_SK_SKB, - BPF_PROG_TYPE_SK_SKB, - BPF_PROG_TYPE_SK_SKB, - BPF_PROG_TYPE_SOCK_OPS, - BPF_PROG_TYPE_SK_MSG, - BPF_PROG_TYPE_SK_MSG, - BPF_PROG_TYPE_SK_MSG, - BPF_PROG_TYPE_SK_MSG, - BPF_PROG_TYPE_SK_MSG, - BPF_PROG_TYPE_SK_MSG, - BPF_PROG_TYPE_SK_MSG, -}; - static int populate_progs(char *bpf_file) { struct bpf_program *prog; @@ -1829,17 +1799,10 @@ static int populate_progs(char *bpf_file) return -1; } - bpf_object__for_each_program(prog, obj) { - bpf_program__set_type(prog, prog_type[i]); - bpf_program__set_expected_attach_type(prog, - prog_attach_type[i]); - i++; - } - i = bpf_object__load(obj); i = 0; bpf_object__for_each_program(prog, obj) { - prog_fd[i] = bpf_program__fd(prog); + progs[i] = prog; i++; } @@ -1853,6 +1816,9 @@ static int populate_progs(char *bpf_file) } } + for (i = 0; i < ARRAY_SIZE(links); i++) + links[i] = NULL; + return 0; } diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c b/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c index 7b5fc98838cd..aebc58c24dc5 100644 --- a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c +++ b/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c @@ -139,14 +139,14 @@ out: return ret; } -static int v6only_true(int fd, const struct post_socket_opts *opts) +static int v6only_true(int fd, void *opts) { int mode = true; return setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, &mode, sizeof(mode)); } -static int v6only_false(int fd, const struct post_socket_opts *opts) +static int v6only_false(int fd, void *opts) { int mode = false; diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index df04bda1c927..610392dfc4fb 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -1237,11 +1237,6 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, fixup_prog_kfuncs(prog, fd_array, test->fixup_kfunc_btf_id); } -struct libcap { - struct __user_cap_header_struct hdr; - struct __user_cap_data_struct data[2]; -}; - static int set_admin(bool admin) { int err; diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index 70e29f316fe7..465d196c7165 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -211,7 +211,7 @@ long ksym_get_addr(const char *name) */ int kallsyms_find(const char *sym, unsigned long long *addr) { - char type, name[500]; + char type, name[500], *match; unsigned long long value; int err = 0; FILE *f; @@ -221,6 +221,17 @@ int kallsyms_find(const char *sym, unsigned long long *addr) return -EINVAL; while (fscanf(f, "%llx %c %499s%*[^\n]\n", &value, &type, name) > 0) { + /* If CONFIG_LTO_CLANG_THIN is enabled, static variable/function + * symbols could be promoted to global due to cross-file inlining. + * For such cases, clang compiler will add .llvm.<hash> suffix + * to those symbols to avoid potential naming conflict. + * Let us ignore .llvm.<hash> suffix during symbol comparison. + */ + if (type == 'd') { + match = strstr(name, ".llvm."); + if (match) + *match = '\0'; + } if (strcmp(name, sym) == 0) { *addr = value; goto out; diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile index 4933d045ab66..c9f2f48fc30f 100644 --- a/tools/testing/selftests/drivers/net/hw/Makefile +++ b/tools/testing/selftests/drivers/net/hw/Makefile @@ -11,6 +11,7 @@ TEST_PROGS = \ hw_stats_l3_gre.sh \ loopback.sh \ pp_alloc_fail.py \ + rss_ctx.py \ # TEST_FILES := \ diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py new file mode 100755 index 000000000000..68c7d40214eb --- /dev/null +++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py @@ -0,0 +1,383 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +import datetime +import random +from lib.py import ksft_run, ksft_pr, ksft_exit, ksft_eq, ksft_ge, ksft_lt +from lib.py import NetDrvEpEnv +from lib.py import NetdevFamily +from lib.py import KsftSkipEx +from lib.py import rand_port +from lib.py import ethtool, ip, GenerateTraffic, CmdExitFailure + + +def _rss_key_str(key): + return ":".join(["{:02x}".format(x) for x in key]) + + +def _rss_key_rand(length): + return [random.randint(0, 255) for _ in range(length)] + + +def get_rss(cfg, context=0): + return ethtool(f"-x {cfg.ifname} context {context}", json=True)[0] + + +def get_drop_err_sum(cfg): + stats = ip("-s -s link show dev " + cfg.ifname, json=True)[0] + cnt = 0 + for key in ['errors', 'dropped', 'over_errors', 'fifo_errors', + 'length_errors', 'crc_errors', 'missed_errors', + 'frame_errors']: + cnt += stats["stats64"]["rx"][key] + return cnt, stats["stats64"]["tx"]["carrier_changes"] + + +def ethtool_create(cfg, act, opts): + output = ethtool(f"{act} {cfg.ifname} {opts}").stdout + # Output will be something like: "New RSS context is 1" or + # "Added rule with ID 7", we want the integer from the end + return int(output.split()[-1]) + + +def require_ntuple(cfg): + features = ethtool(f"-k {cfg.ifname}", json=True)[0] + if not features["ntuple-filters"]["active"]: + # ntuple is more of a capability than a config knob, don't bother + # trying to enable it (until some driver actually needs it). + raise KsftSkipEx("Ntuple filters not enabled on the device: " + str(features["ntuple-filters"])) + + +# Get Rx packet counts for all queues, as a simple list of integers +# if @prev is specified the prev counts will be subtracted +def _get_rx_cnts(cfg, prev=None): + cfg.wait_hw_stats_settle() + data = cfg.netdevnl.qstats_get({"ifindex": cfg.ifindex, "scope": ["queue"]}, dump=True) + data = [x for x in data if x['queue-type'] == "rx"] + max_q = max([x["queue-id"] for x in data]) + queue_stats = [0] * (max_q + 1) + for q in data: + queue_stats[q["queue-id"]] = q["rx-packets"] + if prev and q["queue-id"] < len(prev): + queue_stats[q["queue-id"]] -= prev[q["queue-id"]] + return queue_stats + + +def test_rss_key_indir(cfg): + """ + Test basics like updating the main RSS key and indirection table. + """ + if len(_get_rx_cnts(cfg)) < 2: + KsftSkipEx("Device has only one queue (or doesn't support queue stats)") + + data = get_rss(cfg) + want_keys = ['rss-hash-key', 'rss-hash-function', 'rss-indirection-table'] + for k in want_keys: + if k not in data: + raise KsftFailEx("ethtool results missing key: " + k) + if not data[k]: + raise KsftFailEx(f"ethtool results empty for '{k}': {data[k]}") + + key_len = len(data['rss-hash-key']) + + # Set the key + key = _rss_key_rand(key_len) + ethtool(f"-X {cfg.ifname} hkey " + _rss_key_str(key)) + + data = get_rss(cfg) + ksft_eq(key, data['rss-hash-key']) + + # Set the indirection table + ethtool(f"-X {cfg.ifname} equal 2") + data = get_rss(cfg) + ksft_eq(0, min(data['rss-indirection-table'])) + ksft_eq(1, max(data['rss-indirection-table'])) + + # Check we only get traffic on the first 2 queues + cnts = _get_rx_cnts(cfg) + GenerateTraffic(cfg).wait_pkts_and_stop(20000) + cnts = _get_rx_cnts(cfg, prev=cnts) + # 2 queues, 20k packets, must be at least 5k per queue + ksft_ge(cnts[0], 5000, "traffic on main context (1/2): " + str(cnts)) + ksft_ge(cnts[1], 5000, "traffic on main context (2/2): " + str(cnts)) + # The other queues should be unused + ksft_eq(sum(cnts[2:]), 0, "traffic on unused queues: " + str(cnts)) + + # Restore, and check traffic gets spread again + ethtool(f"-X {cfg.ifname} default") + + cnts = _get_rx_cnts(cfg) + GenerateTraffic(cfg).wait_pkts_and_stop(20000) + cnts = _get_rx_cnts(cfg, prev=cnts) + # First two queues get less traffic than all the rest + ksft_lt(sum(cnts[:2]), sum(cnts[2:]), "traffic distributed: " + str(cnts)) + + +def test_rss_context(cfg, ctx_cnt=1, create_with_cfg=None): + """ + Test separating traffic into RSS contexts. + The queues will be allocated 2 for each context: + ctx0 ctx1 ctx2 ctx3 + [0 1] [2 3] [4 5] [6 7] ... + """ + + require_ntuple(cfg) + + requested_ctx_cnt = ctx_cnt + + # Try to allocate more queues when necessary + qcnt = len(_get_rx_cnts(cfg)) + if qcnt >= 2 + 2 * ctx_cnt: + qcnt = None + else: + try: + ksft_pr(f"Increasing queue count {qcnt} -> {2 + 2 * ctx_cnt}") + ethtool(f"-L {cfg.ifname} combined {2 + 2 * ctx_cnt}") + except: + raise KsftSkipEx("Not enough queues for the test") + + ntuple = [] + ctx_id = [] + ports = [] + try: + # Use queues 0 and 1 for normal traffic + ethtool(f"-X {cfg.ifname} equal 2") + + for i in range(ctx_cnt): + want_cfg = f"start {2 + i * 2} equal 2" + create_cfg = want_cfg if create_with_cfg else "" + + try: + ctx_id.append(ethtool_create(cfg, "-X", f"context new {create_cfg}")) + except CmdExitFailure: + # try to carry on and skip at the end + if i == 0: + raise + ksft_pr(f"Failed to create context {i + 1}, trying to test what we got") + ctx_cnt = i + break + + if not create_with_cfg: + ethtool(f"-X {cfg.ifname} context {ctx_id[i]} {want_cfg}") + + # Sanity check the context we just created + data = get_rss(cfg, ctx_id[i]) + ksft_eq(min(data['rss-indirection-table']), 2 + i * 2, "Unexpected context cfg: " + str(data)) + ksft_eq(max(data['rss-indirection-table']), 2 + i * 2 + 1, "Unexpected context cfg: " + str(data)) + + ports.append(rand_port()) + flow = f"flow-type tcp{cfg.addr_ipver} dst-port {ports[i]} context {ctx_id[i]}" + ntuple.append(ethtool_create(cfg, "-N", flow)) + + for i in range(ctx_cnt): + cnts = _get_rx_cnts(cfg) + GenerateTraffic(cfg, port=ports[i]).wait_pkts_and_stop(20000) + cnts = _get_rx_cnts(cfg, prev=cnts) + + ksft_lt(sum(cnts[ :2]), 10000, "traffic on main context:" + str(cnts)) + ksft_ge(sum(cnts[2+i*2:4+i*2]), 20000, f"traffic on context {i}: " + str(cnts)) + ksft_eq(sum(cnts[2:2+i*2] + cnts[4+i*2:]), 0, "traffic on other contexts: " + str(cnts)) + finally: + for nid in ntuple: + ethtool(f"-N {cfg.ifname} delete {nid}") + for cid in ctx_id: + ethtool(f"-X {cfg.ifname} context {cid} delete") + ethtool(f"-X {cfg.ifname} default") + if qcnt: + ethtool(f"-L {cfg.ifname} combined {qcnt}") + + if requested_ctx_cnt != ctx_cnt: + raise KsftSkipEx(f"Tested only {ctx_cnt} contexts, wanted {requested_ctx_cnt}") + + +def test_rss_context4(cfg): + test_rss_context(cfg, 4) + + +def test_rss_context32(cfg): + test_rss_context(cfg, 32) + + +def test_rss_context4_create_with_cfg(cfg): + test_rss_context(cfg, 4, create_with_cfg=True) + + +def test_rss_context_out_of_order(cfg, ctx_cnt=4): + """ + Test separating traffic into RSS contexts. + Contexts are removed in semi-random order, and steering re-tested + to make sure removal doesn't break steering to surviving contexts. + Test requires 3 contexts to work. + """ + + require_ntuple(cfg) + + requested_ctx_cnt = ctx_cnt + + # Try to allocate more queues when necessary + qcnt = len(_get_rx_cnts(cfg)) + if qcnt >= 2 + 2 * ctx_cnt: + qcnt = None + else: + try: + ksft_pr(f"Increasing queue count {qcnt} -> {2 + 2 * ctx_cnt}") + ethtool(f"-L {cfg.ifname} combined {2 + 2 * ctx_cnt}") + except: + raise KsftSkipEx("Not enough queues for the test") + + ntuple = [] + ctx_id = [] + ports = [] + + def remove_ctx(idx): + ethtool(f"-N {cfg.ifname} delete {ntuple[idx]}") + ntuple[idx] = None + ethtool(f"-X {cfg.ifname} context {ctx_id[idx]} delete") + ctx_id[idx] = None + + def check_traffic(): + for i in range(ctx_cnt): + cnts = _get_rx_cnts(cfg) + GenerateTraffic(cfg, port=ports[i]).wait_pkts_and_stop(20000) + cnts = _get_rx_cnts(cfg, prev=cnts) + + if ctx_id[i] is None: + ksft_lt(sum(cnts[ :2]), 10000, "traffic on main context:" + str(cnts)) + ksft_ge(sum(cnts[2+i*2:4+i*2]), 20000, f"traffic on context {i}: " + str(cnts)) + ksft_eq(sum(cnts[2:2+i*2] + cnts[4+i*2:]), 0, "traffic on other contexts: " + str(cnts)) + else: + ksft_ge(sum(cnts[ :2]), 20000, "traffic on main context:" + str(cnts)) + ksft_eq(sum(cnts[2: ]), 0, "traffic on other contexts: " + str(cnts)) + + try: + # Use queues 0 and 1 for normal traffic + ethtool(f"-X {cfg.ifname} equal 2") + + for i in range(ctx_cnt): + ctx_id.append(ethtool_create(cfg, "-X", f"context new start {2 + i * 2} equal 2")) + + ports.append(rand_port()) + flow = f"flow-type tcp{cfg.addr_ipver} dst-port {ports[i]} context {ctx_id[i]}" + ntuple.append(ethtool_create(cfg, "-N", flow)) + + check_traffic() + + # Remove middle context + remove_ctx(ctx_cnt // 2) + check_traffic() + + # Remove first context + remove_ctx(0) + check_traffic() + + # Remove last context + remove_ctx(-1) + check_traffic() + + finally: + for nid in ntuple: + if nid is not None: + ethtool(f"-N {cfg.ifname} delete {nid}") + for cid in ctx_id: + if cid is not None: + ethtool(f"-X {cfg.ifname} context {cid} delete") + ethtool(f"-X {cfg.ifname} default") + if qcnt: + ethtool(f"-L {cfg.ifname} combined {qcnt}") + + if requested_ctx_cnt != ctx_cnt: + raise KsftSkipEx(f"Tested only {ctx_cnt} contexts, wanted {requested_ctx_cnt}") + + +def test_rss_context_overlap(cfg, other_ctx=0): + """ + Test contexts overlapping with each other. + Use 4 queues for the main context, but only queues 2 and 3 for context 1. + """ + + require_ntuple(cfg) + + queue_cnt = len(_get_rx_cnts(cfg)) + if queue_cnt >= 4: + queue_cnt = None + else: + try: + ksft_pr(f"Increasing queue count {queue_cnt} -> 4") + ethtool(f"-L {cfg.ifname} combined 4") + except: + raise KsftSkipEx("Not enough queues for the test") + + ctx_id = None + ntuple = None + if other_ctx == 0: + ethtool(f"-X {cfg.ifname} equal 4") + else: + other_ctx = ethtool_create(cfg, "-X", "context new") + ethtool(f"-X {cfg.ifname} context {other_ctx} equal 4") + + try: + ctx_id = ethtool_create(cfg, "-X", "context new") + ethtool(f"-X {cfg.ifname} context {ctx_id} start 2 equal 2") + + port = rand_port() + if other_ctx: + flow = f"flow-type tcp{cfg.addr_ipver} dst-port {port} context {other_ctx}" + ntuple = ethtool_create(cfg, "-N", flow) + + # Test the main context + cnts = _get_rx_cnts(cfg) + GenerateTraffic(cfg, port=port).wait_pkts_and_stop(20000) + cnts = _get_rx_cnts(cfg, prev=cnts) + + ksft_ge(sum(cnts[ :4]), 20000, "traffic on main context: " + str(cnts)) + ksft_ge(sum(cnts[ :2]), 7000, "traffic on main context (1/2): " + str(cnts)) + ksft_ge(sum(cnts[2:4]), 7000, "traffic on main context (2/2): " + str(cnts)) + if other_ctx == 0: + ksft_eq(sum(cnts[4: ]), 0, "traffic on other queues: " + str(cnts)) + + # Now create a rule for context 1 and make sure traffic goes to a subset + if other_ctx: + ethtool(f"-N {cfg.ifname} delete {ntuple}") + ntuple = None + flow = f"flow-type tcp{cfg.addr_ipver} dst-port {port} context {ctx_id}" + ntuple = ethtool_create(cfg, "-N", flow) + + cnts = _get_rx_cnts(cfg) + GenerateTraffic(cfg, port=port).wait_pkts_and_stop(20000) + cnts = _get_rx_cnts(cfg, prev=cnts) + + ksft_lt(sum(cnts[ :2]), 7000, "traffic on main context: " + str(cnts)) + ksft_ge(sum(cnts[2:4]), 20000, "traffic on extra context: " + str(cnts)) + if other_ctx == 0: + ksft_eq(sum(cnts[4: ]), 0, "traffic on other queues: " + str(cnts)) + finally: + if ntuple is not None: + ethtool(f"-N {cfg.ifname} delete {ntuple}") + if ctx_id: + ethtool(f"-X {cfg.ifname} context {ctx_id} delete") + if other_ctx == 0: + ethtool(f"-X {cfg.ifname} default") + else: + ethtool(f"-X {cfg.ifname} context {other_ctx} delete") + if queue_cnt: + ethtool(f"-L {cfg.ifname} combined {queue_cnt}") + + +def test_rss_context_overlap2(cfg): + test_rss_context_overlap(cfg, True) + + +def main() -> None: + with NetDrvEpEnv(__file__, nsim_test=False) as cfg: + cfg.netdevnl = NetdevFamily() + + ksft_run([test_rss_key_indir, + test_rss_context, test_rss_context4, test_rss_context32, + test_rss_context_overlap, test_rss_context_overlap2, + test_rss_context_out_of_order, test_rss_context4_create_with_cfg], + args=(cfg, )) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py index edcedd7bffab..a5e800b8f103 100644 --- a/tools/testing/selftests/drivers/net/lib/py/env.py +++ b/tools/testing/selftests/drivers/net/lib/py/env.py @@ -1,9 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 import os +import time from pathlib import Path from lib.py import KsftSkipEx, KsftXfailEx -from lib.py import cmd, ip +from lib.py import cmd, ethtool, ip from lib.py import NetNS, NetdevSimDev from .remote import Remote @@ -82,6 +83,8 @@ class NetDrvEpEnv: self.env = _load_env_file(src_path) + self._stats_settle_time = None + # Things we try to destroy self.remote = None # These are for local testing state @@ -222,3 +225,17 @@ class NetDrvEpEnv: if remote: if not self._require_cmd(comm, "remote"): raise KsftSkipEx("Test requires (remote) command: " + comm) + + def wait_hw_stats_settle(self): + """ + Wait for HW stats to become consistent, some devices DMA HW stats + periodically so events won't be reflected until next sync. + Good drivers will tell us via ethtool what their sync period is. + """ + if self._stats_settle_time is None: + data = ethtool("-c " + self.ifname, json=True)[0] + + self._stats_settle_time = 0.025 + \ + data.get('stats-block-usecs', 0) / 1000 / 1000 + + time.sleep(self._stats_settle_time) diff --git a/tools/testing/selftests/drivers/net/lib/py/load.py b/tools/testing/selftests/drivers/net/lib/py/load.py index abdb677bdb1c..d9c10613ae67 100644 --- a/tools/testing/selftests/drivers/net/lib/py/load.py +++ b/tools/testing/selftests/drivers/net/lib/py/load.py @@ -5,28 +5,45 @@ import time from lib.py import ksft_pr, cmd, ip, rand_port, wait_port_listen class GenerateTraffic: - def __init__(self, env): + def __init__(self, env, port=None): env.require_cmd("iperf3", remote=True) self.env = env - port = rand_port() - self._iperf_server = cmd(f"iperf3 -s -p {port}", background=True) + if port is None: + port = rand_port() + self._iperf_server = cmd(f"iperf3 -s -1 -p {port}", background=True) wait_port_listen(port) time.sleep(0.1) self._iperf_client = cmd(f"iperf3 -c {env.addr} -P 16 -p {port} -t 86400", background=True, host=env.remote) # Wait for traffic to ramp up - pkt = ip("-s link show dev " + env.ifname, json=True)[0]["stats64"]["rx"]["packets"] + if not self._wait_pkts(pps=1000): + self.stop(verbose=True) + raise Exception("iperf3 traffic did not ramp up") + + def _wait_pkts(self, pkt_cnt=None, pps=None): + """ + Wait until we've seen pkt_cnt or until traffic ramps up to pps. + Only one of pkt_cnt or pss can be specified. + """ + pkt_start = ip("-s link show dev " + self.env.ifname, json=True)[0]["stats64"]["rx"]["packets"] for _ in range(50): time.sleep(0.1) - now = ip("-s link show dev " + env.ifname, json=True)[0]["stats64"]["rx"]["packets"] - if now - pkt > 1000: - return - pkt = now - self.stop(verbose=True) - raise Exception("iperf3 traffic did not ramp up") + pkt_now = ip("-s link show dev " + self.env.ifname, json=True)[0]["stats64"]["rx"]["packets"] + if pps: + if pkt_now - pkt_start > pps / 10: + return True + pkt_start = pkt_now + elif pkt_cnt: + if pkt_now - pkt_start > pkt_cnt: + return True + return False + + def wait_pkts_and_stop(self, pkt_cnt): + failed = not self._wait_pkts(pkt_cnt=pkt_cnt) + self.stop(verbose=failed) def stop(self, verbose=None): self._iperf_client.process(terminate=True) diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh index 31252bc8775e..4994bea5daf8 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh @@ -11,7 +11,7 @@ ALL_TESTS="single_mask_test identical_filters_test two_masks_test \ multiple_masks_test ctcam_edge_cases_test delta_simple_test \ delta_two_masks_one_key_test delta_simple_rehash_test \ bloom_simple_test bloom_complex_test bloom_delta_test \ - max_erp_entries_test max_group_size_test" + max_erp_entries_test max_group_size_test collision_test" NUM_NETIFS=2 source $lib_dir/lib.sh source $lib_dir/tc_common.sh @@ -457,7 +457,7 @@ delta_two_masks_one_key_test() { # If 2 keys are the same and only differ in mask in a way that # they belong under the same ERP (second is delta of the first), - # there should be no C-TCAM spill. + # there should be C-TCAM spill. RET=0 @@ -474,8 +474,8 @@ delta_two_masks_one_key_test() tp_record "mlxsw:*" "tc filter add dev $h2 ingress protocol ip \ pref 2 handle 102 flower $tcflags dst_ip 192.0.2.2 \ action drop" - tp_check_hits "mlxsw:mlxsw_sp_acl_atcam_entry_add_ctcam_spill" 0 - check_err $? "incorrect C-TCAM spill while inserting the second rule" + tp_check_hits "mlxsw:mlxsw_sp_acl_atcam_entry_add_ctcam_spill" 1 + check_err $? "C-TCAM spill did not happen while inserting the second rule" $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ -t ip -q @@ -1087,6 +1087,53 @@ max_group_size_test() log_test "max ACL group size test ($tcflags). max size $max_size" } +collision_test() +{ + # Filters cannot share an eRP if in the common unmasked part (i.e., + # without the delta bits) they have the same values. If the driver does + # not prevent such configuration (by spilling into the C-TCAM), then + # multiple entries will be present in the device with the same key, + # leading to collisions and a reduced scale. + # + # Create such a scenario and make sure all the filters are successfully + # added. + + RET=0 + + local ret + + if [[ "$tcflags" != "skip_sw" ]]; then + return 0; + fi + + # Add a single dst_ip/24 filter and multiple dst_ip/32 filters that all + # have the same values in the common unmasked part (dst_ip/24). + + tc filter add dev $h2 ingress pref 1 proto ipv4 handle 101 \ + flower $tcflags dst_ip 198.51.100.0/24 \ + action drop + + for i in {0..255}; do + tc filter add dev $h2 ingress pref 2 proto ipv4 \ + handle $((102 + i)) \ + flower $tcflags dst_ip 198.51.100.${i}/32 \ + action drop + ret=$? + [[ $ret -ne 0 ]] && break + done + + check_err $ret "failed to add all the filters" + + for i in {255..0}; do + tc filter del dev $h2 ingress pref 2 proto ipv4 \ + handle $((102 + i)) flower + done + + tc filter del dev $h2 ingress pref 1 proto ipv4 handle 101 flower + + log_test "collision test ($tcflags)" +} + setup_prepare() { h1=${NETIFS[p1]} diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index d9393569d03a..bc3925200637 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -55,6 +55,7 @@ TEST_PROGS += bind_bhash.sh TEST_PROGS += ip_local_port_range.sh TEST_PROGS += rps_default_mask.sh TEST_PROGS += big_tcp.sh +TEST_PROGS += netns-sysctl.sh TEST_PROGS_EXTENDED := toeplitz_client.sh toeplitz.sh TEST_GEN_FILES = socket nettest TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any diff --git a/tools/testing/selftests/net/amt.sh b/tools/testing/selftests/net/amt.sh index 7e7ed6c558da..d458b45c775b 100755 --- a/tools/testing/selftests/net/amt.sh +++ b/tools/testing/selftests/net/amt.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 # Author: Taehee Yoo <ap420073@gmail.com> diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index d4891f7a2bfa..f46e27cd1e70 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -26,7 +26,6 @@ CONFIG_INET_ESP=y CONFIG_INET_ESP_OFFLOAD=y CONFIG_NET_FOU=y CONFIG_NET_FOU_IP_TUNNELS=y -CONFIG_IP_GRE=m CONFIG_NETFILTER=y CONFIG_NETFILTER_ADVANCED=y CONFIG_NF_CONNTRACK=m diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index fa7b59ff4029..224346426ef2 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -39,6 +39,7 @@ TEST_PROGS = bridge_fdb_learning_limit.sh \ ipip_hier_gre.sh \ lib_sh_test.sh \ local_termination.sh \ + min_max_mtu.sh \ mirror_gre_bound.sh \ mirror_gre_bridge_1d.sh \ mirror_gre_bridge_1d_vlan.sh \ @@ -70,6 +71,7 @@ TEST_PROGS = bridge_fdb_learning_limit.sh \ router_broadcast.sh \ router_mpath_nh_res.sh \ router_mpath_nh.sh \ + router_mpath_seed.sh \ router_multicast.sh \ router_multipath.sh \ router_nh.sh \ diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index eabbdf00d8ca..9086d2015296 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -1134,12 +1134,19 @@ bridge_ageing_time_get() } declare -A SYSCTL_ORIG +sysctl_save() +{ + local key=$1; shift + + SYSCTL_ORIG[$key]=$(sysctl -n $key) +} + sysctl_set() { local key=$1; shift local value=$1; shift - SYSCTL_ORIG[$key]=$(sysctl -n $key) + sysctl_save "$key" sysctl -qw $key="$value" } diff --git a/tools/testing/selftests/net/forwarding/min_max_mtu.sh b/tools/testing/selftests/net/forwarding/min_max_mtu.sh new file mode 100755 index 000000000000..97bb8b221bed --- /dev/null +++ b/tools/testing/selftests/net/forwarding/min_max_mtu.sh @@ -0,0 +1,283 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +--------------------+ +# | H1 | +# | | +# | $h1.10 + | +# | 192.0.2.2/24 | | +# | 2001:db8:1::2/64 | | +# | | | +# | $h1 + | +# | | | +# +------------------|-+ +# | +# +------------------|-+ +# | SW | | +# | $swp1 + | +# | | | +# | $swp1.10 + | +# | 192.0.2.1/24 | +# | 2001:db8:1::1/64 | +# | | +# +--------------------+ + +ALL_TESTS=" + ping_ipv4 + ping_ipv6 + max_mtu_config_test + max_mtu_traffic_test + min_mtu_config_test + min_mtu_traffic_test +" + +NUM_NETIFS=2 +source lib.sh + +h1_create() +{ + simple_if_init $h1 + vlan_create $h1 10 v$h1 192.0.2.2/24 2001:db8:1::2/64 +} + +h1_destroy() +{ + vlan_destroy $h1 10 192.0.2.2/24 2001:db8:1::2/64 + simple_if_fini $h1 +} + +switch_create() +{ + ip li set dev $swp1 up + vlan_create $swp1 10 "" 192.0.2.1/24 2001:db8:1::1/64 +} + +switch_destroy() +{ + ip li set dev $swp1 down + vlan_destroy $swp1 10 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + vrf_prepare + + h1_create + + switch_create + + forwarding_enable +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + switch_destroy + + h1_destroy + + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1.10 192.0.2.1 +} + +ping_ipv6() +{ + ping6_test $h1.10 2001:db8:1::1 +} + +min_max_mtu_get_if() +{ + local dev=$1; shift + local min_max=$1; shift + + ip -d -j link show $dev | jq ".[].$min_max" +} + +ensure_compatible_min_max_mtu() +{ + local min_max=$1; shift + + local mtu=$(min_max_mtu_get_if ${NETIFS[p1]} $min_max) + local i + + for ((i = 2; i <= NUM_NETIFS; ++i)); do + local current_mtu=$(min_max_mtu_get_if ${NETIFS[p$i]} $min_max) + + if [ $current_mtu -ne $mtu ]; then + return 1 + fi + done +} + +mtu_set_if() +{ + local dev=$1; shift + local mtu=$1; shift + local should_fail=${1:-0}; shift + + mtu_set $dev $mtu 2>/dev/null + check_err_fail $should_fail $? "Set MTU $mtu for $dev" +} + +mtu_set_all_if() +{ + local mtu=$1; shift + local i + + for ((i = 1; i <= NUM_NETIFS; ++i)); do + mtu_set_if ${NETIFS[p$i]} $mtu + mtu_set_if ${NETIFS[p$i]}.10 $mtu + done +} + +mtu_restore_all_if() +{ + local i + + for ((i = 1; i <= NUM_NETIFS; ++i)); do + mtu_restore ${NETIFS[p$i]}.10 + mtu_restore ${NETIFS[p$i]} + done +} + +mtu_test_ping4() +{ + local mtu=$1; shift + local should_fail=$1; shift + + # Ping adds 8 bytes for ICMP header and 20 bytes for IP header + local ping_headers_len=$((20 + 8)) + local pkt_size=$((mtu - ping_headers_len)) + + ping_do $h1.10 192.0.2.1 "-s $pkt_size -M do" + check_err_fail $should_fail $? "Ping, packet size: $pkt_size" +} + +mtu_test_ping6() +{ + local mtu=$1; shift + local should_fail=$1; shift + + # Ping adds 8 bytes for ICMP header and 40 bytes for IPv6 header + local ping6_headers_len=$((40 + 8)) + local pkt_size=$((mtu - ping6_headers_len)) + + ping6_do $h1.10 2001:db8:1::1 "-s $pkt_size -M do" + check_err_fail $should_fail $? "Ping6, packet size: $pkt_size" +} + +max_mtu_config_test() +{ + local i + + RET=0 + + for ((i = 1; i <= NUM_NETIFS; ++i)); do + local dev=${NETIFS[p$i]} + local max_mtu=$(min_max_mtu_get_if $dev "max_mtu") + local should_fail + + should_fail=0 + mtu_set_if $dev $max_mtu $should_fail + mtu_restore $dev + + should_fail=1 + mtu_set_if $dev $((max_mtu + 1)) $should_fail + mtu_restore $dev + done + + log_test "Test maximum MTU configuration" +} + +max_mtu_traffic_test() +{ + local should_fail + local max_mtu + + RET=0 + + if ! ensure_compatible_min_max_mtu "max_mtu"; then + log_test_xfail "Topology has incompatible maximum MTU values" + return + fi + + max_mtu=$(min_max_mtu_get_if ${NETIFS[p1]} "max_mtu") + + should_fail=0 + mtu_set_all_if $max_mtu + mtu_test_ping4 $max_mtu $should_fail + mtu_test_ping6 $max_mtu $should_fail + mtu_restore_all_if + + should_fail=1 + mtu_set_all_if $((max_mtu - 1)) + mtu_test_ping4 $max_mtu $should_fail + mtu_test_ping6 $max_mtu $should_fail + mtu_restore_all_if + + log_test "Test traffic, packet size is maximum MTU" +} + +min_mtu_config_test() +{ + local i + + RET=0 + + for ((i = 1; i <= NUM_NETIFS; ++i)); do + local dev=${NETIFS[p$i]} + local min_mtu=$(min_max_mtu_get_if $dev "min_mtu") + local should_fail + + should_fail=0 + mtu_set_if $dev $min_mtu $should_fail + mtu_restore $dev + + should_fail=1 + mtu_set_if $dev $((min_mtu - 1)) $should_fail + mtu_restore $dev + done + + log_test "Test minimum MTU configuration" +} + +min_mtu_traffic_test() +{ + local should_fail=0 + local min_mtu + + RET=0 + + if ! ensure_compatible_min_max_mtu "min_mtu"; then + log_test_xfail "Topology has incompatible minimum MTU values" + return + fi + + min_mtu=$(min_max_mtu_get_if ${NETIFS[p1]} "min_mtu") + mtu_set_all_if $min_mtu + mtu_test_ping4 $min_mtu $should_fail + # Do not test minimum MTU with IPv6, as IPv6 requires higher MTU. + + mtu_restore_all_if + + log_test "Test traffic, packet size is minimum MTU" +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/router_mpath_seed.sh b/tools/testing/selftests/net/forwarding/router_mpath_seed.sh new file mode 100755 index 000000000000..314cb906c1eb --- /dev/null +++ b/tools/testing/selftests/net/forwarding/router_mpath_seed.sh @@ -0,0 +1,333 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +-------------------------+ +-------------------------+ +# | H1 | | H2 | +# | $h1 + | | + $h2 | +# | 192.0.2.1/28 | | | | 192.0.2.34/28 | +# | 2001:db8:1::1/64 | | | | 2001:db8:3::2/64 | +# +-------------------|-----+ +-|-----------------------+ +# | | +# +-------------------|-----+ +-|-----------------------+ +# | R1 | | | | R2 | +# | $rp11 + | | + $rp21 | +# | 192.0.2.2/28 | | 192.0.2.33/28 | +# | 2001:db8:1::2/64 | | 2001:db8:3::1/64 | +# | | | | +# | $rp12 + | | + $rp22 | +# | 192.0.2.17/28 | | | | 192.0.2.18..27/28 | +# | 2001:db8:2::17/64 | | | | 2001:db8:2::18..27/64 | +# +-------------------|-----+ +-|-----------------------+ +# | | +# `----------' + +ALL_TESTS=" + ping_ipv4 + ping_ipv6 + test_mpath_seed_stability_ipv4 + test_mpath_seed_stability_ipv6 + test_mpath_seed_get + test_mpath_seed_ipv4 + test_mpath_seed_ipv6 +" +NUM_NETIFS=6 +source lib.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64 + ip -4 route add 192.0.2.32/28 vrf v$h1 nexthop via 192.0.2.2 + ip -6 route add 2001:db8:3::/64 vrf v$h1 nexthop via 2001:db8:1::2 +} + +h1_destroy() +{ + ip -6 route del 2001:db8:3::/64 vrf v$h1 nexthop via 2001:db8:1::2 + ip -4 route del 192.0.2.32/28 vrf v$h1 nexthop via 192.0.2.2 + simple_if_fini $h1 192.0.2.1/28 2001:db8:1::1/64 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.34/28 2001:db8:3::2/64 + ip -4 route add 192.0.2.0/28 vrf v$h2 nexthop via 192.0.2.33 + ip -6 route add 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:3::1 +} + +h2_destroy() +{ + ip -6 route del 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:3::1 + ip -4 route del 192.0.2.0/28 vrf v$h2 nexthop via 192.0.2.33 + simple_if_fini $h2 192.0.2.34/28 2001:db8:3::2/64 +} + +router1_create() +{ + simple_if_init $rp11 192.0.2.2/28 2001:db8:1::2/64 + __simple_if_init $rp12 v$rp11 192.0.2.17/28 2001:db8:2::17/64 +} + +router1_destroy() +{ + __simple_if_fini $rp12 192.0.2.17/28 2001:db8:2::17/64 + simple_if_fini $rp11 192.0.2.2/28 2001:db8:1::2/64 +} + +router2_create() +{ + simple_if_init $rp21 192.0.2.33/28 2001:db8:3::1/64 + __simple_if_init $rp22 v$rp21 192.0.2.18/28 2001:db8:2::18/64 + ip -4 route add 192.0.2.0/28 vrf v$rp21 nexthop via 192.0.2.17 + ip -6 route add 2001:db8:1::/64 vrf v$rp21 nexthop via 2001:db8:2::17 +} + +router2_destroy() +{ + ip -6 route del 2001:db8:1::/64 vrf v$rp21 nexthop via 2001:db8:2::17 + ip -4 route del 192.0.2.0/28 vrf v$rp21 nexthop via 192.0.2.17 + __simple_if_fini $rp22 192.0.2.18/28 2001:db8:2::18/64 + simple_if_fini $rp21 192.0.2.33/28 2001:db8:3::1/64 +} + +nexthops_create() +{ + local i + for i in $(seq 10); do + ip nexthop add id $((1000 + i)) via 192.0.2.18 dev $rp12 + ip nexthop add id $((2000 + i)) via 2001:db8:2::18 dev $rp12 + done + + ip nexthop add id 1000 group $(seq -s / 1001 1010) hw_stats on + ip nexthop add id 2000 group $(seq -s / 2001 2010) hw_stats on + ip -4 route add 192.0.2.32/28 vrf v$rp11 nhid 1000 + ip -6 route add 2001:db8:3::/64 vrf v$rp11 nhid 2000 +} + +nexthops_destroy() +{ + local i + + ip -6 route del 2001:db8:3::/64 vrf v$rp11 nhid 2000 + ip -4 route del 192.0.2.32/28 vrf v$rp11 nhid 1000 + ip nexthop del id 2000 + ip nexthop del id 1000 + + for i in $(seq 10 -1 1); do + ip nexthop del id $((2000 + i)) + ip nexthop del id $((1000 + i)) + done +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + rp11=${NETIFS[p2]} + + rp12=${NETIFS[p3]} + rp22=${NETIFS[p4]} + + rp21=${NETIFS[p5]} + h2=${NETIFS[p6]} + + sysctl_save net.ipv4.fib_multipath_hash_seed + + vrf_prepare + + h1_create + h2_create + router1_create + router2_create + + forwarding_enable +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + nexthops_destroy + router2_destroy + router1_destroy + h2_destroy + h1_destroy + + vrf_cleanup + + sysctl_restore net.ipv4.fib_multipath_hash_seed +} + +ping_ipv4() +{ + ping_test $h1 192.0.2.34 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:3::2 +} + +test_mpath_seed_get() +{ + RET=0 + + local i + for ((i = 0; i < 100; i++)); do + local seed_w=$((999331 * i)) + sysctl -qw net.ipv4.fib_multipath_hash_seed=$seed_w + local seed_r=$(sysctl -n net.ipv4.fib_multipath_hash_seed) + ((seed_r == seed_w)) + check_err $? "mpath seed written as $seed_w, but read as $seed_r" + done + + log_test "mpath seed set/get" +} + +nh_stats_snapshot() +{ + local group_id=$1; shift + + ip -j -s -s nexthop show id $group_id | + jq -c '[.[].group_stats | sort_by(.id) | .[].packets]' +} + +get_active_nh() +{ + local s0=$1; shift + local s1=$1; shift + + jq -n --argjson s0 "$s0" --argjson s1 "$s1" -f /dev/stdin <<-"EOF" + [range($s0 | length)] | + map($s1[.] - $s0[.]) | + map(if . > 8 then 1 else 0 end) | + index(1) + EOF +} + +probe_nh() +{ + local group_id=$1; shift + local -a mz=("$@") + + local s0=$(nh_stats_snapshot $group_id) + "${mz[@]}" + local s1=$(nh_stats_snapshot $group_id) + + get_active_nh "$s0" "$s1" +} + +probe_seed() +{ + local group_id=$1; shift + local seed=$1; shift + local -a mz=("$@") + + sysctl -qw net.ipv4.fib_multipath_hash_seed=$seed + probe_nh "$group_id" "${mz[@]}" +} + +test_mpath_seed() +{ + local group_id=$1; shift + local what=$1; shift + local -a mz=("$@") + local ii + + RET=0 + + local -a tally=(0 0 0 0 0 0 0 0 0 0) + for ((ii = 0; ii < 100; ii++)); do + local act=$(probe_seed $group_id $((999331 * ii)) "${mz[@]}") + ((tally[act]++)) + done + + local tally_str="${tally[@]}" + for ((ii = 0; ii < ${#tally[@]}; ii++)); do + ((tally[ii] > 0)) + check_err $? "NH #$ii not hit, tally='$tally_str'" + done + + log_test "mpath seed $what" + sysctl -qw net.ipv4.fib_multipath_hash_seed=0 +} + +test_mpath_seed_ipv4() +{ + test_mpath_seed 1000 IPv4 \ + $MZ $h1 -A 192.0.2.1 -B 192.0.2.34 -q \ + -p 64 -d 0 -c 10 -t udp +} + +test_mpath_seed_ipv6() +{ + test_mpath_seed 2000 IPv6 \ + $MZ -6 $h1 -A 2001:db8:1::1 -B 2001:db8:3::2 -q \ + -p 64 -d 0 -c 10 -t udp +} + +check_mpath_seed_stability() +{ + local seed=$1; shift + local act_0=$1; shift + local act_1=$1; shift + + ((act_0 == act_1)) + check_err $? "seed $seed: active NH moved from $act_0 to $act_1 after seed change" +} + +test_mpath_seed_stability() +{ + local group_id=$1; shift + local what=$1; shift + local -a mz=("$@") + + RET=0 + + local seed_0=0 + local seed_1=3221338814 + local seed_2=3735928559 + + # Initial active NH before touching the seed at all. + local act_ini=$(probe_nh $group_id "${mz[@]}") + + local act_0_0=$(probe_seed $group_id $seed_0 "${mz[@]}") + local act_1_0=$(probe_seed $group_id $seed_1 "${mz[@]}") + local act_2_0=$(probe_seed $group_id $seed_2 "${mz[@]}") + + local act_0_1=$(probe_seed $group_id $seed_0 "${mz[@]}") + local act_1_1=$(probe_seed $group_id $seed_1 "${mz[@]}") + local act_2_1=$(probe_seed $group_id $seed_2 "${mz[@]}") + + check_mpath_seed_stability initial $act_ini $act_0_0 + check_mpath_seed_stability $seed_0 $act_0_0 $act_0_1 + check_mpath_seed_stability $seed_1 $act_1_0 $act_1_1 + check_mpath_seed_stability $seed_2 $act_2_0 $act_2_1 + + log_test "mpath seed stability $what" + sysctl -qw net.ipv4.fib_multipath_hash_seed=0 +} + +test_mpath_seed_stability_ipv4() +{ + test_mpath_seed_stability 1000 IPv4 \ + $MZ $h1 -A 192.0.2.1 -B 192.0.2.34 -q \ + -p 64 -d 0 -c 10 -t udp +} + +test_mpath_seed_stability_ipv6() +{ + test_mpath_seed_stability 2000 IPv6 \ + $MZ -6 $h1 -A 2001:db8:1::1 -B 2001:db8:3::2 -q \ + -p 64 -d 0 -c 10 -t udp +} + +trap cleanup EXIT + +setup_prepare +setup_wait +nexthops_create + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/hsr/hsr_ping.sh b/tools/testing/selftests/net/hsr/hsr_ping.sh index 3684b813b0f6..f5d207fc770a 100755 --- a/tools/testing/selftests/net/hsr/hsr_ping.sh +++ b/tools/testing/selftests/net/hsr/hsr_ping.sh @@ -152,6 +152,15 @@ setup_hsr_interfaces() ip -net "$ns3" addr add 100.64.0.3/24 dev hsr3 ip -net "$ns3" addr add dead:beef:1::3/64 dev hsr3 nodad + ip -net "$ns1" link set address 00:11:22:00:01:01 dev ns1eth1 + ip -net "$ns1" link set address 00:11:22:00:01:02 dev ns1eth2 + + ip -net "$ns2" link set address 00:11:22:00:02:01 dev ns2eth1 + ip -net "$ns2" link set address 00:11:22:00:02:02 dev ns2eth2 + + ip -net "$ns3" link set address 00:11:22:00:03:01 dev ns3eth1 + ip -net "$ns3" link set address 00:11:22:00:03:02 dev ns3eth2 + # All Links up ip -net "$ns1" link set ns1eth1 up ip -net "$ns1" link set ns1eth2 up diff --git a/tools/testing/selftests/net/hsr/hsr_redbox.sh b/tools/testing/selftests/net/hsr/hsr_redbox.sh index 1f36785347c0..998103502d5d 100755 --- a/tools/testing/selftests/net/hsr/hsr_redbox.sh +++ b/tools/testing/selftests/net/hsr/hsr_redbox.sh @@ -96,6 +96,21 @@ setup_hsr_interfaces() ip -n "${ns4}" link set ns4eth1 up ip -n "${ns5}" link set ns5eth1 up + ip -net "$ns1" link set address 00:11:22:00:01:01 dev ns1eth1 + ip -net "$ns1" link set address 00:11:22:00:01:02 dev ns1eth2 + + ip -net "$ns2" link set address 00:11:22:00:02:01 dev ns2eth1 + ip -net "$ns2" link set address 00:11:22:00:02:02 dev ns2eth2 + ip -net "$ns2" link set address 00:11:22:00:02:03 dev ns2eth3 + + ip -net "$ns3" link set address 00:11:22:00:03:11 dev ns3eth1 + ip -net "$ns3" link set address 00:11:22:00:03:11 dev ns3eth2 + ip -net "$ns3" link set address 00:11:22:00:03:11 dev ns3eth3 + ip -net "$ns3" link set address 00:11:22:00:03:11 dev ns3br1 + + ip -net "$ns4" link set address 00:11:22:00:04:01 dev ns4eth1 + ip -net "$ns5" link set address 00:11:22:00:05:01 dev ns5eth1 + ip -net "${ns1}" link add name hsr1 type hsr slave1 ns1eth1 slave2 ns1eth2 supervision 45 version ${HSRv} proto 0 ip -net "${ns2}" link add name hsr2 type hsr slave1 ns2eth1 slave2 ns2eth2 interlink ns2eth3 supervision 45 version ${HSRv} proto 0 diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 9155c914c064..915f319bcc8b 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -125,28 +125,36 @@ slowwait_for_counter() slowwait "$timeout" until_counter_is ">= $((base + delta))" "$@" } +remove_ns_list() +{ + local item=$1 + local ns + local ns_list=("${NS_LIST[@]}") + NS_LIST=() + + for ns in "${ns_list[@]}"; do + if [ "${ns}" != "${item}" ]; then + NS_LIST+=("${ns}") + fi + done +} + cleanup_ns() { local ns="" - local errexit=0 local ret=0 - # disable errexit temporary - if [[ $- =~ "e" ]]; then - errexit=1 - set +e - fi - for ns in "$@"; do [ -z "${ns}" ] && continue - ip netns delete "${ns}" &> /dev/null + ip netns delete "${ns}" &> /dev/null || true if ! busywait $BUSYWAIT_TIMEOUT ip netns list \| grep -vq "^$ns$" &> /dev/null; then echo "Warn: Failed to remove namespace $ns" ret=1 + else + remove_ns_list "${ns}" fi done - [ $errexit -eq 1 ] && set -e return $ret } @@ -159,29 +167,30 @@ cleanup_all_ns() # setup_ns local remote setup_ns() { - local ns="" local ns_name="" local ns_list=() - local ns_exist= for ns_name in "$@"; do + # avoid conflicts with local var: internal error + if [ "${ns_name}" = "ns_name" ]; then + echo "Failed to setup namespace '${ns_name}': invalid name" + cleanup_ns "${ns_list[@]}" + exit $ksft_fail + fi + # Some test may setup/remove same netns multi times - if unset ${ns_name} 2> /dev/null; then - ns="${ns_name,,}-$(mktemp -u XXXXXX)" - eval readonly ${ns_name}="$ns" - ns_exist=false + if [ -z "${!ns_name}" ]; then + eval "${ns_name}=${ns_name,,}-$(mktemp -u XXXXXX)" else - eval ns='$'${ns_name} - cleanup_ns "$ns" - ns_exist=true + cleanup_ns "${!ns_name}" fi - if ! ip netns add "$ns"; then + if ! ip netns add "${!ns_name}"; then echo "Failed to create namespace $ns_name" cleanup_ns "${ns_list[@]}" return $ksft_skip fi - ip -n "$ns" link set lo up - ! $ns_exist && ns_list+=("$ns") + ip -n "${!ns_name}" link set lo up + ns_list+=("${!ns_name}") done NS_LIST+=("${ns_list[@]}") } diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py index 4769b4eb1ea1..b6ce3f33d41e 100644 --- a/tools/testing/selftests/net/lib/py/ksft.py +++ b/tools/testing/selftests/net/lib/py/ksft.py @@ -57,6 +57,11 @@ def ksft_ge(a, b, comment=""): _fail("Check failed", a, "<", b, comment) +def ksft_lt(a, b, comment=""): + if a >= b: + _fail("Check failed", a, ">=", b, comment) + + class ksft_raises: def __init__(self, expected_type): self.exception = None diff --git a/tools/testing/selftests/net/lib/py/utils.py b/tools/testing/selftests/net/lib/py/utils.py index 0540ea24921d..405aa510aaf2 100644 --- a/tools/testing/selftests/net/lib/py/utils.py +++ b/tools/testing/selftests/net/lib/py/utils.py @@ -1,12 +1,18 @@ # SPDX-License-Identifier: GPL-2.0 +import errno import json as _json import random import re +import socket import subprocess import time +class CmdExitFailure(Exception): + pass + + class cmd: def __init__(self, comm, shell=True, fail=True, ns=None, background=False, host=None, timeout=5): if ns: @@ -41,8 +47,8 @@ class cmd: if self.proc.returncode != 0 and fail: if len(stderr) > 0 and stderr[-1] == "\n": stderr = stderr[:-1] - raise Exception("Command failed: %s\nSTDOUT: %s\nSTDERR: %s" % - (self.proc.args, stdout, stderr)) + raise CmdExitFailure("Command failed: %s\nSTDOUT: %s\nSTDERR: %s" % + (self.proc.args, stdout, stderr)) class bkg(cmd): @@ -77,11 +83,24 @@ def ip(args, json=None, ns=None, host=None): return tool('ip', args, json=json, host=host) +def ethtool(args, json=None, ns=None, host=None): + return tool('ethtool', args, json=json, ns=ns, host=host) + + def rand_port(): """ - Get unprivileged port, for now just random, one day we may decide to check if used. + Get a random unprivileged port, try to make sure it's not already used. """ - return random.randint(10000, 65535) + for _ in range(1000): + port = random.randint(10000, 65535) + try: + with socket.socket(socket.AF_INET6, socket.SOCK_STREAM) as s: + s.bind(("", port)) + return port + except OSError as e: + if e.errno != errno.EADDRINUSE: + raise + raise Exception("Can't find any free unprivileged port") def wait_port_listen(port, proto="tcp", ns=None, host=None, sleep=0.005, deadline=5): diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index 6ffa9b7a3260..194c8fc2e55a 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -1,6 +1,9 @@ #! /bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/../lib.sh" +. "$(dirname "${0}")/../net_helper.sh" + readonly KSFT_PASS=0 readonly KSFT_FAIL=1 readonly KSFT_SKIP=4 @@ -361,20 +364,7 @@ mptcp_lib_check_transfer() { # $1: ns, $2: port mptcp_lib_wait_local_port_listen() { - local listener_ns="${1}" - local port="${2}" - - local port_hex - port_hex="$(printf "%04X" "${port}")" - - local _ - for _ in $(seq 10); do - ip netns exec "${listener_ns}" cat /proc/net/tcp* | \ - awk "BEGIN {rc=1} {if (\$2 ~ /:${port_hex}\$/ && \$4 ~ /0A/) \ - {rc=0; exit}} END {exit rc}" && - break - sleep 0.1 - done + wait_local_port_listen "${@}" "tcp" } mptcp_lib_check_output() { @@ -438,17 +428,13 @@ mptcp_lib_check_tools() { } mptcp_lib_ns_init() { - local sec rndh - - sec=$(date +%s) - rndh=$(printf %x "${sec}")-$(mktemp -u XXXXXX) + if ! setup_ns ${@}; then + mptcp_lib_pr_fail "Failed to setup namespace ${@}" + exit ${KSFT_FAIL} + fi local netns for netns in "${@}"; do - eval "${netns}=${netns}-${rndh}" - - ip netns add "${!netns}" || exit ${KSFT_SKIP} - ip -net "${!netns}" link set lo up ip netns exec "${!netns}" sysctl -q net.mptcp.enabled=1 ip netns exec "${!netns}" sysctl -q net.ipv4.conf.all.rp_filter=0 ip netns exec "${!netns}" sysctl -q net.ipv4.conf.default.rp_filter=0 @@ -456,9 +442,10 @@ mptcp_lib_ns_init() { } mptcp_lib_ns_exit() { + cleanup_ns "${@}" + local netns for netns in "${@}"; do - ip netns del "${netns}" rm -f /tmp/"${netns}".{nstat,out} done } diff --git a/tools/testing/selftests/net/netns-sysctl.sh b/tools/testing/selftests/net/netns-sysctl.sh new file mode 100755 index 000000000000..45c34a3b9aae --- /dev/null +++ b/tools/testing/selftests/net/netns-sysctl.sh @@ -0,0 +1,40 @@ +#!/bin/bash -e +# SPDX-License-Identifier: GPL-2.0 +# +# This test checks that the network buffer sysctls are present +# in a network namespaces, and that they are readonly. + +source lib.sh + +cleanup() { + cleanup_ns $test_ns +} + +trap cleanup EXIT + +fail() { + echo "ERROR: $*" >&2 + exit 1 +} + +setup_ns test_ns + +for sc in {r,w}mem_{default,max}; do + # check that this is writable in a netns + [ -w "/proc/sys/net/core/$sc" ] || + fail "$sc isn't writable in the init netns!" + + # change the value in the host netns + sysctl -qw "net.core.$sc=300000" || + fail "Can't write $sc in init netns!" + + # check that the value is read from the init netns + [ "$(ip netns exec $test_ns sysctl -n "net.core.$sc")" -eq 300000 ] || + fail "Value for $sc mismatch!" + + # check that this isn't writable in a netns + ip netns exec $test_ns [ -w "/proc/sys/net/core/$sc" ] && + fail "$sc is writable in a netns!" +done + +echo 'Test passed OK' |