From 68153bb2fffbe59804370e514482f95c4b2053ff Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 4 Jun 2024 17:16:25 -0700 Subject: libbpf: Add BTF field iterator Implement iterator-based type ID and string offset BTF field iterator. This is used extensively in BTF-handling code and BPF linker code for various sanity checks, rewriting IDs/offsets, etc. Currently this is implemented as visitor pattern calling custom callbacks, which makes the logic (especially in simple cases) unnecessarily obscure and harder to follow. Having equivalent functionality using iterator pattern makes for simpler to understand and maintain code. As we add more code for BTF processing logic in libbpf, it's best to switch to iterator pattern before adding more callback-based code. The idea for iterator-based implementation is to record offsets of necessary fields within fixed btf_type parts (which should be iterated just once), and, for kinds that have multiple members (based on vlen field), record where in each member necessary fields are located. Generic iteration code then just keeps track of last offset that was returned and handles N members correctly. Return type is just u32 pointer, where NULL is returned when all relevant fields were already iterated. Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Tested-by: Alan Maguire Acked-by: Eduard Zingerman Acked-by: Jiri Olsa Link: https://lore.kernel.org/bpf/20240605001629.4061937-2-andrii@kernel.org --- tools/lib/bpf/btf.c | 162 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 162 insertions(+) (limited to 'tools/lib/bpf/btf.c') diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 2d0840ef599a..50ff8b6eaf36 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -5133,6 +5133,168 @@ int btf_type_visit_str_offs(struct btf_type *t, str_off_visit_fn visit, void *ct return 0; } +int btf_field_iter_init(struct btf_field_iter *it, struct btf_type *t, enum btf_field_iter_kind iter_kind) +{ + it->p = NULL; + it->m_idx = -1; + it->off_idx = 0; + it->vlen = 0; + + 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; + } + 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; + } + break; + default: + return -EINVAL; + } + + if (it->desc.m_sz) + it->vlen = btf_vlen(t); + + it->p = t; + return 0; +} + +__u32 *btf_field_iter_next(struct btf_field_iter *it) +{ + if (!it->p) + return NULL; + + if (it->m_idx < 0) { + if (it->off_idx < it->desc.t_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; + } + + /* if type doesn't have members, stop */ + if (it->desc.m_sz == 0) { + it->p = NULL; + return NULL; + } + + if (it->off_idx >= it->desc.m_cnt) { + /* exhausted this member's fields, go to the next member */ + it->m_idx++; + it->p += it->desc.m_sz; + it->off_idx = 0; + } + + if (it->m_idx < it->vlen) + return it->p + it->desc.m_offs[it->off_idx++]; + + it->p = NULL; + return NULL; +} + int btf_ext_visit_type_ids(struct btf_ext *btf_ext, type_id_visit_fn visit, void *ctx) { const struct btf_ext_info *seg; -- cgit v1.2.3-58-ga151 From 2bce2c1cb2f0acbf619737a10575f99df0c43984 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 4 Jun 2024 17:16:26 -0700 Subject: libbpf: Make use of BTF field iterator in BPF linker code Switch all BPF linker code dealing with iterating BTF type ID and string offset fields to new btf_field_iter facilities. Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Tested-by: Alan Maguire Acked-by: Eduard Zingerman Acked-by: Jiri Olsa Link: https://lore.kernel.org/bpf/20240605001629.4061937-3-andrii@kernel.org --- tools/lib/bpf/btf.c | 4 +-- tools/lib/bpf/libbpf_internal.h | 4 +-- tools/lib/bpf/linker.c | 58 +++++++++++++++++++++++++---------------- 3 files changed, 40 insertions(+), 26 deletions(-) (limited to 'tools/lib/bpf/btf.c') diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 50ff8b6eaf36..d72260ac26a5 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -5267,7 +5267,7 @@ __u32 *btf_field_iter_next(struct btf_field_iter *it) return NULL; if (it->m_idx < 0) { - if (it->off_idx < it->desc.t_cnt) + 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; @@ -5281,7 +5281,7 @@ __u32 *btf_field_iter_next(struct btf_field_iter *it) return NULL; } - if (it->off_idx >= it->desc.m_cnt) { + 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; diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 80f3d346db33..96c0b0993f8b 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -515,11 +515,11 @@ enum btf_field_iter_kind { struct btf_field_desc { /* once-per-type offsets */ - int t_cnt, t_offs[2]; + int t_off_cnt, t_offs[2]; /* member struct size, or zero, if no members */ int m_sz; /* repeated per-member offsets */ - int m_cnt, m_offs[1]; + int m_off_cnt, m_offs[1]; }; struct btf_field_iter { 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 -- cgit v1.2.3-58-ga151 From c2641123696b572a3b059e1b45777317ba9f9086 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 4 Jun 2024 17:16:27 -0700 Subject: libbpf: Make use of BTF field iterator in BTF handling code Use new BTF field iterator logic to replace all the callback-based visitor calls. There is still a .BTF.ext callback-based visitor APIs that should be converted, which will happens as a follow up. Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Tested-by: Alan Maguire Acked-by: Eduard Zingerman Acked-by: Jiri Olsa Link: https://lore.kernel.org/bpf/20240605001629.4061937-4-andrii@kernel.org --- tools/lib/bpf/btf.c | 76 +++++++++++++++++++++++++++++++++++++---------------- 1 file changed, 54 insertions(+), 22 deletions(-) (limited to 'tools/lib/bpf/btf.c') diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index d72260ac26a5..0190fd819f58 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) -- cgit v1.2.3-58-ga151 From 072088704433f75dacf9e33179dd7a81f0a238d4 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 4 Jun 2024 17:16:29 -0700 Subject: libbpf: Remove callback-based type/string BTF field visitor helpers Now that all libbpf/bpftool code switched to btf_field_iter, remove btf_type_visit_type_ids() and btf_type_visit_str_offs() callback-based helpers as not needed anymore. Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Tested-by: Alan Maguire Acked-by: Eduard Zingerman Acked-by: Jiri Olsa Link: https://lore.kernel.org/bpf/20240605001629.4061937-6-andrii@kernel.org --- tools/lib/bpf/btf.c | 130 ---------------------------------------- tools/lib/bpf/libbpf_internal.h | 2 - 2 files changed, 132 deletions(-) (limited to 'tools/lib/bpf/btf.c') diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 0190fd819f58..775ca55a541c 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -5035,136 +5035,6 @@ 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 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; - } - - 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; - } - 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; - } - return 0; - } - - default: - return -EINVAL; - } -} - -int btf_type_visit_str_offs(struct btf_type *t, str_off_visit_fn visit, void *ctx) -{ - int i, n, err; - - err = visit(&t->name_off, ctx); - if (err) - return err; - - switch (btf_kind(t)) { - 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->name_off, ctx); - if (err) - return err; - } - break; - } - 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; - } - 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; - } - 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; - } - - return 0; -} - int btf_field_iter_init(struct btf_field_iter *it, struct btf_type *t, enum btf_field_iter_kind iter_kind) { it->p = NULL; diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 96c0b0993f8b..e2f06609c624 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -535,8 +535,6 @@ __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, -- cgit v1.2.3-58-ga151 From 58e185a0dc359a6c1c9eff348d7badfc9f722159 Mon Sep 17 00:00:00 2001 From: Alan Maguire Date: Thu, 13 Jun 2024 10:50:06 +0100 Subject: libbpf: Add btf__distill_base() creating split BTF with distilled base BTF To support more robust split BTF, adding supplemental context for the base BTF type ids that split BTF refers to is required. Without such references, a simple shuffling of base BTF type ids (without any other significant change) invalidates the split BTF. Here the attempt is made to store additional context to make split BTF more robust. This context comes in the form of distilled base BTF providing minimal information (name and - in some cases - size) for base INTs, FLOATs, STRUCTs, UNIONs, ENUMs and ENUM64s along with modified split BTF that points at that base and contains any additional types needed (such as TYPEDEF, PTR and anonymous STRUCT/UNION declarations). This information constitutes the minimal BTF representation needed to disambiguate or remove split BTF references to base BTF. The rules are as follows: - INT, FLOAT, FWD are recorded in full. - if a named base BTF STRUCT or UNION is referred to from split BTF, it will be encoded as a zero-member sized STRUCT/UNION (preserving size for later relocation checks). Only base BTF STRUCT/UNIONs that are either embedded in split BTF STRUCT/UNIONs or that have multiple STRUCT/UNION instances of the same name will _need_ size checks at relocation time, but as it is possible a different set of types will be duplicates in the later to-be-resolved base BTF, we preserve size information for all named STRUCT/UNIONs. - if an ENUM[64] is named, a ENUM forward representation (an ENUM with no values) of the same size is used. - in all other cases, the type is added to the new split BTF. Avoiding struct/union/enum/enum64 expansion is important to keep the distilled base BTF representation to a minimum size. When successful, new representations of the distilled base BTF and new split BTF that refers to it are returned. Both need to be freed by the caller. So to take a simple example, with split BTF with a type referring to "struct sk_buff", we will generate distilled base BTF with a 0-member STRUCT sk_buff of the appropriate size, and the split BTF will refer to it instead. Tools like pahole can utilize such split BTF to populate the .BTF section (split BTF) and an additional .BTF.base section. Then when the split BTF is loaded, the distilled base BTF can be used to relocate split BTF to reference the current (and possibly changed) base BTF. So for example if "struct sk_buff" was id 502 when the split BTF was originally generated, we can use the distilled base BTF to see that id 502 refers to a "struct sk_buff" and replace instances of id 502 with the current (relocated) base BTF sk_buff type id. Distilled base BTF is small; when building a kernel with all modules using distilled base BTF as a test, overall module size grew by only 5.3Mb total across ~2700 modules. Signed-off-by: Alan Maguire Signed-off-by: Andrii Nakryiko Acked-by: Eduard Zingerman Link: https://lore.kernel.org/bpf/20240613095014.357981-2-alan.maguire@oracle.com --- tools/lib/bpf/btf.c | 319 ++++++++++++++++++++++++++++++++++++++++++++++- tools/lib/bpf/btf.h | 21 ++++ tools/lib/bpf/libbpf.map | 1 + 3 files changed, 335 insertions(+), 6 deletions(-) (limited to 'tools/lib/bpf/btf.c') diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 775ca55a541c..407ed92b4134 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -1770,9 +1770,8 @@ static int btf_rewrite_str(struct btf_pipe *p, __u32 *str_off) return 0; } -int btf__add_type(struct btf *btf, const struct btf *src_btf, const struct btf_type *src_type) +static int btf_add_type(struct btf_pipe *p, 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; @@ -1783,10 +1782,10 @@ int btf__add_type(struct btf *btf, const struct btf *src_btf, const struct btf_t return libbpf_err(sz); /* deconstruct BTF, if necessary, and invalidate raw_data */ - if (btf_ensure_modifiable(btf)) + if (btf_ensure_modifiable(p->dst)) return libbpf_err(-ENOMEM); - t = btf_add_type_mem(btf, sz); + t = btf_add_type_mem(p->dst, sz); if (!t) return libbpf_err(-ENOMEM); @@ -1797,12 +1796,19 @@ int btf__add_type(struct btf *btf, const struct btf *src_btf, const struct btf_t return libbpf_err(err); while ((str_off = btf_field_iter_next(&it))) { - err = btf_rewrite_str(&p, str_off); + err = btf_rewrite_str(p, str_off); if (err) return libbpf_err(err); } - return btf_commit_type(btf, sz); + return btf_commit_type(p->dst, sz); +} + +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 }; + + return btf_add_type(&p, src_type); } static size_t btf_dedup_identity_hash_fn(long key, void *ctx); @@ -5276,3 +5282,304 @@ int btf_ext_visit_str_offs(struct btf_ext *btf_ext, str_off_visit_fn visit, void return 0; } + +struct btf_distill { + struct btf_pipe pipe; + int *id_map; + unsigned int split_start_id; + unsigned int split_start_str; + int diff_id; +}; + +static int btf_add_distilled_type_ids(struct btf_distill *dist, __u32 i) +{ + struct btf_type *split_t = btf_type_by_id(dist->pipe.src, i); + struct btf_field_iter it; + __u32 *id; + int err; + + err = btf_field_iter_init(&it, split_t, BTF_FIELD_ITER_IDS); + if (err) + return err; + while ((id = btf_field_iter_next(&it))) { + struct btf_type *base_t; + + if (!*id) + continue; + /* split BTF id, not needed */ + if (*id >= dist->split_start_id) + continue; + /* already added ? */ + if (dist->id_map[*id] > 0) + continue; + + /* only a subset of base BTF types should be referenced from + * split BTF; ensure nothing unexpected is referenced. + */ + base_t = btf_type_by_id(dist->pipe.src, *id); + switch (btf_kind(base_t)) { + case BTF_KIND_INT: + case BTF_KIND_FLOAT: + case BTF_KIND_FWD: + case BTF_KIND_ARRAY: + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + case BTF_KIND_TYPEDEF: + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + case BTF_KIND_PTR: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + case BTF_KIND_VOLATILE: + case BTF_KIND_FUNC_PROTO: + case BTF_KIND_TYPE_TAG: + dist->id_map[*id] = *id; + break; + default: + pr_warn("unexpected reference to base type[%u] of kind [%u] when creating distilled base BTF.\n", + *id, btf_kind(base_t)); + return -EINVAL; + } + /* If a base type is used, ensure types it refers to are + * marked as used also; so for example if we find a PTR to INT + * we need both the PTR and INT. + * + * The only exception is named struct/unions, since distilled + * base BTF composite types have no members. + */ + if (btf_is_composite(base_t) && base_t->name_off) + continue; + err = btf_add_distilled_type_ids(dist, *id); + if (err) + return err; + } + return 0; +} + +static int btf_add_distilled_types(struct btf_distill *dist) +{ + bool adding_to_base = dist->pipe.dst->start_id == 1; + int id = btf__type_cnt(dist->pipe.dst); + struct btf_type *t; + int i, err = 0; + + + /* Add types for each of the required references to either distilled + * base or split BTF, depending on type characteristics. + */ + for (i = 1; i < dist->split_start_id; i++) { + const char *name; + int kind; + + if (!dist->id_map[i]) + continue; + t = btf_type_by_id(dist->pipe.src, i); + kind = btf_kind(t); + name = btf__name_by_offset(dist->pipe.src, t->name_off); + + switch (kind) { + case BTF_KIND_INT: + case BTF_KIND_FLOAT: + case BTF_KIND_FWD: + /* Named int, float, fwd are added to base. */ + if (!adding_to_base) + continue; + err = btf_add_type(&dist->pipe, t); + break; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + /* Named struct/union are added to base as 0-vlen + * struct/union of same size. Anonymous struct/unions + * are added to split BTF as-is. + */ + if (adding_to_base) { + if (!t->name_off) + continue; + err = btf_add_composite(dist->pipe.dst, kind, name, t->size); + } else { + if (t->name_off) + continue; + err = btf_add_type(&dist->pipe, t); + } + break; + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + /* Named enum[64]s are added to base as a sized + * enum; relocation will match with appropriately-named + * and sized enum or enum64. + * + * Anonymous enums are added to split BTF as-is. + */ + if (adding_to_base) { + if (!t->name_off) + continue; + err = btf__add_enum(dist->pipe.dst, name, t->size); + } else { + if (t->name_off) + continue; + err = btf_add_type(&dist->pipe, t); + } + break; + case BTF_KIND_ARRAY: + case BTF_KIND_TYPEDEF: + case BTF_KIND_PTR: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + case BTF_KIND_VOLATILE: + case BTF_KIND_FUNC_PROTO: + case BTF_KIND_TYPE_TAG: + /* All other types are added to split BTF. */ + if (adding_to_base) + continue; + err = btf_add_type(&dist->pipe, t); + break; + default: + pr_warn("unexpected kind when adding base type '%s'[%u] of kind [%u] to distilled base BTF.\n", + name, i, kind); + return -EINVAL; + + } + if (err < 0) + break; + dist->id_map[i] = id++; + } + return err; +} + +/* Split BTF ids without a mapping will be shifted downwards since distilled + * base BTF is smaller than the original base BTF. For those that have a + * mapping (either to base or updated split BTF), update the id based on + * that mapping. + */ +static int btf_update_distilled_type_ids(struct btf_distill *dist, __u32 i) +{ + struct btf_type *t = btf_type_by_id(dist->pipe.dst, i); + struct btf_field_iter it; + __u32 *id; + int err; + + err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_IDS); + if (err) + return err; + while ((id = btf_field_iter_next(&it))) { + if (dist->id_map[*id]) + *id = dist->id_map[*id]; + else if (*id >= dist->split_start_id) + *id -= dist->diff_id; + } + return 0; +} + +/* Create updated split BTF with distilled base BTF; distilled base BTF + * consists of BTF information required to clarify the types that split + * BTF refers to, omitting unneeded details. Specifically it will contain + * base types and memberless definitions of named structs, unions and enumerated + * types. Associated reference types like pointers, arrays and anonymous + * structs, unions and enumerated types will be added to split BTF. + * Size is recorded for named struct/unions to help guide matching to the + * target base BTF during later relocation. + * + * The only case where structs, unions or enumerated types are fully represented + * is when they are anonymous; in such cases, the anonymous type is added to + * split BTF in full. + * + * We return newly-created split BTF where the split BTF refers to a newly-created + * distilled base BTF. Both must be freed separately by the caller. + */ +int btf__distill_base(const struct btf *src_btf, struct btf **new_base_btf, + struct btf **new_split_btf) +{ + struct btf *new_base = NULL, *new_split = NULL; + const struct btf *old_base; + unsigned int n = btf__type_cnt(src_btf); + struct btf_distill dist = {}; + struct btf_type *t; + int i, err = 0; + + /* src BTF must be split BTF. */ + old_base = btf__base_btf(src_btf); + if (!new_base_btf || !new_split_btf || !old_base) + return libbpf_err(-EINVAL); + + new_base = btf__new_empty(); + if (!new_base) + return libbpf_err(-ENOMEM); + dist.id_map = calloc(n, sizeof(*dist.id_map)); + if (!dist.id_map) { + err = -ENOMEM; + goto done; + } + dist.pipe.src = src_btf; + dist.pipe.dst = new_base; + dist.pipe.str_off_map = hashmap__new(btf_dedup_identity_hash_fn, btf_dedup_equal_fn, NULL); + if (IS_ERR(dist.pipe.str_off_map)) { + err = -ENOMEM; + goto done; + } + dist.split_start_id = btf__type_cnt(old_base); + dist.split_start_str = old_base->hdr->str_len; + + /* Pass over src split BTF; generate the list of base BTF type ids it + * references; these will constitute our distilled BTF set to be + * distributed over base and split BTF as appropriate. + */ + for (i = src_btf->start_id; i < n; i++) { + err = btf_add_distilled_type_ids(&dist, i); + if (err < 0) + goto done; + } + /* Next add types for each of the required references to base BTF and split BTF + * in turn. + */ + err = btf_add_distilled_types(&dist); + if (err < 0) + goto done; + + /* Create new split BTF with distilled base BTF as its base; the final + * state is split BTF with distilled base BTF that represents enough + * about its base references to allow it to be relocated with the base + * BTF available. + */ + new_split = btf__new_empty_split(new_base); + if (!new_split_btf) { + err = -errno; + goto done; + } + dist.pipe.dst = new_split; + /* First add all split types */ + for (i = src_btf->start_id; i < n; i++) { + t = btf_type_by_id(src_btf, i); + err = btf_add_type(&dist.pipe, t); + if (err < 0) + goto done; + } + /* Now add distilled types to split BTF that are not added to base. */ + err = btf_add_distilled_types(&dist); + if (err < 0) + goto done; + + /* All split BTF ids will be shifted downwards since there are less base + * BTF ids in distilled base BTF. + */ + dist.diff_id = dist.split_start_id - btf__type_cnt(new_base); + + n = btf__type_cnt(new_split); + /* Now update base/split BTF ids. */ + for (i = 1; i < n; i++) { + err = btf_update_distilled_type_ids(&dist, i); + if (err < 0) + break; + } +done: + free(dist.id_map); + hashmap__free(dist.pipe.str_off_map); + if (err) { + btf__free(new_split); + btf__free(new_base); + return libbpf_err(err); + } + *new_base_btf = new_base; + *new_split_btf = new_split; + + return 0; +} diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 8e6880d91c84..cb08ee9a5a10 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -107,6 +107,27 @@ LIBBPF_API struct btf *btf__new_empty(void); */ LIBBPF_API struct btf *btf__new_empty_split(struct btf *base_btf); +/** + * @brief **btf__distill_base()** creates new versions of the split BTF + * *src_btf* and its base BTF. The new base BTF will only contain the types + * needed to improve robustness of the split BTF to small changes in base BTF. + * When that split BTF is loaded against a (possibly changed) base, this + * distilled base BTF will help update references to that (possibly changed) + * base BTF. + * + * Both the new split and its associated new base BTF must be freed by + * the caller. + * + * If successful, 0 is returned and **new_base_btf** and **new_split_btf** + * will point at new base/split BTF. Both the new split and its associated + * new base BTF must be freed by the caller. + * + * A negative value is returned on error and the thread-local `errno` variable + * is set to the error code as well. + */ +LIBBPF_API int btf__distill_base(const struct btf *src_btf, struct btf **new_base_btf, + struct btf **new_split_btf); + LIBBPF_API struct btf *btf__parse(const char *path, struct btf_ext **btf_ext); LIBBPF_API struct btf *btf__parse_split(const char *path, struct btf *base_btf); LIBBPF_API struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext); diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 40595233dc7f..175d1536e070 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -419,6 +419,7 @@ LIBBPF_1.4.0 { LIBBPF_1.5.0 { global: + btf__distill_base; bpf_map__autoattach; bpf_map__set_autoattach; bpf_program__attach_sockmap; -- cgit v1.2.3-58-ga151 From 19e00c897d5031bed969dd79af28e899e038009f Mon Sep 17 00:00:00 2001 From: Alan Maguire Date: Thu, 13 Jun 2024 10:50:08 +0100 Subject: libbpf: Split BTF relocation Map distilled base BTF type ids referenced in split BTF and their references to the base BTF passed in, and if the mapping succeeds, reparent the split BTF to the base BTF. Relocation is done by first verifying that distilled base BTF only consists of named INT, FLOAT, ENUM, FWD, STRUCT and UNION kinds; then we sort these to speed lookups. Once sorted, the base BTF is iterated, and for each relevant kind we check for an equivalent in distilled base BTF. When found, the mapping from distilled -> base BTF id and string offset is recorded. In establishing mappings, we need to ensure we check STRUCT/UNION size when the STRUCT/UNION is embedded in a split BTF STRUCT/UNION, and when duplicate names exist for the same STRUCT/UNION. Otherwise size is ignored in matching STRUCT/UNIONs. Once all mappings are established, we can update type ids and string offsets in split BTF and reparent it to the new base. Signed-off-by: Alan Maguire Signed-off-by: Andrii Nakryiko Acked-by: Eduard Zingerman Link: https://lore.kernel.org/bpf/20240613095014.357981-4-alan.maguire@oracle.com --- tools/lib/bpf/Build | 2 +- tools/lib/bpf/btf.c | 17 ++ tools/lib/bpf/btf.h | 14 ++ tools/lib/bpf/btf_relocate.c | 506 ++++++++++++++++++++++++++++++++++++++++ tools/lib/bpf/libbpf.map | 1 + tools/lib/bpf/libbpf_internal.h | 3 + 6 files changed, 542 insertions(+), 1 deletion(-) create mode 100644 tools/lib/bpf/btf_relocate.c (limited to 'tools/lib/bpf/btf.c') diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build index b6619199a706..336da6844d42 100644 --- a/tools/lib/bpf/Build +++ b/tools/lib/bpf/Build @@ -1,4 +1,4 @@ libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o \ netlink.o bpf_prog_linfo.o libbpf_probes.o hashmap.o \ btf_dump.o ringbuf.o strset.o linker.o gen_loader.o relo_core.o \ - usdt.o zip.o elf.o features.o + usdt.o zip.o elf.o features.o btf_relocate.o diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 407ed92b4134..5e20354fbcfa 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -5583,3 +5583,20 @@ done: return 0; } + +const struct btf_header *btf_header(const struct btf *btf) +{ + return btf->hdr; +} + +void btf_set_base_btf(struct btf *btf, const struct btf *base_btf) +{ + btf->base_btf = (struct btf *)base_btf; + btf->start_id = btf__type_cnt(base_btf); + btf->start_str_off = base_btf->hdr->str_len; +} + +int btf__relocate(struct btf *btf, const struct btf *base_btf) +{ + return libbpf_err(btf_relocate(btf, base_btf, NULL)); +} diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index cb08ee9a5a10..8a93120b7385 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -252,6 +252,20 @@ struct btf_dedup_opts { LIBBPF_API int btf__dedup(struct btf *btf, const struct btf_dedup_opts *opts); +/** + * @brief **btf__relocate()** will check the split BTF *btf* for references + * to base BTF kinds, and verify those references are compatible with + * *base_btf*; if they are, *btf* is adjusted such that is re-parented to + * *base_btf* and type ids and strings are adjusted to accommodate this. + * + * If successful, 0 is returned and **btf** now has **base_btf** as its + * base. + * + * A negative value is returned on error and the thread-local `errno` variable + * is set to the error code as well. + */ +LIBBPF_API int btf__relocate(struct btf *btf, const struct btf *base_btf); + struct btf_dump; struct btf_dump_opts { diff --git a/tools/lib/bpf/btf_relocate.c b/tools/lib/bpf/btf_relocate.c new file mode 100644 index 000000000000..eabb8755f662 --- /dev/null +++ b/tools/lib/bpf/btf_relocate.c @@ -0,0 +1,506 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024, Oracle and/or its affiliates. */ + +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif + +#include "btf.h" +#include "bpf.h" +#include "libbpf.h" +#include "libbpf_internal.h" + +struct btf; + +struct btf_relocate { + struct btf *btf; + const struct btf *base_btf; + const struct btf *dist_base_btf; + unsigned int nr_base_types; + unsigned int nr_split_types; + unsigned int nr_dist_base_types; + int dist_str_len; + int base_str_len; + __u32 *id_map; + __u32 *str_map; +}; + +/* Set temporarily in relocation id_map if distilled base struct/union is + * embedded in a split BTF struct/union; in such a case, size information must + * match between distilled base BTF and base BTF representation of type. + */ +#define BTF_IS_EMBEDDED ((__u32)-1) + +/* triple used in sorting/searching distilled base BTF. */ +struct btf_name_info { + const char *name; + /* set when search requires a size match */ + int needs_size:1, + size:31; + __u32 id; +}; + +static int btf_relocate_rewrite_type_id(struct btf_relocate *r, __u32 i) +{ + struct btf_type *t = btf_type_by_id(r->btf, i); + struct btf_field_iter it; + __u32 *id; + int err; + + err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_IDS); + if (err) + return err; + + while ((id = btf_field_iter_next(&it))) + *id = r->id_map[*id]; + return 0; +} + +/* Simple string comparison used for sorting within BTF, since all distilled + * types are named. If strings match, and size is non-zero for both elements + * fall back to using size for ordering. + */ +static int cmp_btf_name_size(const void *n1, const void *n2) +{ + const struct btf_name_info *ni1 = n1; + const struct btf_name_info *ni2 = n2; + int name_diff = strcmp(ni1->name, ni2->name); + + if (!name_diff && ni1->needs_size && ni2->needs_size) + return ni2->size - ni1->size; + return name_diff; +} + +/* Binary search with a small twist; find leftmost element that matches + * so that we can then iterate through all exact matches. So for example + * searching { "a", "bb", "bb", "c" } we would always match on the + * leftmost "bb". + */ +static struct btf_name_info *search_btf_name_size(struct btf_name_info *key, + struct btf_name_info *vals, + int nelems) +{ + struct btf_name_info *ret = NULL; + int high = nelems - 1; + int low = 0; + + while (low <= high) { + int mid = (low + high)/2; + struct btf_name_info *val = &vals[mid]; + int diff = cmp_btf_name_size(key, val); + + if (diff == 0) + ret = val; + /* even if found, keep searching for leftmost match */ + if (diff <= 0) + high = mid - 1; + else + low = mid + 1; + } + return ret; +} + +/* If a member of a split BTF struct/union refers to a base BTF + * struct/union, mark that struct/union id temporarily in the id_map + * with BTF_IS_EMBEDDED. Members can be const/restrict/volatile/typedef + * reference types, but if a pointer is encountered, the type is no longer + * considered embedded. + */ +static int btf_mark_embedded_composite_type_ids(struct btf_relocate *r, __u32 i) +{ + struct btf_type *t = btf_type_by_id(r->btf, i); + struct btf_field_iter it; + __u32 *id; + int err; + + if (!btf_is_composite(t)) + return 0; + + err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_IDS); + if (err) + return err; + + while ((id = btf_field_iter_next(&it))) { + __u32 next_id = *id; + + while (next_id) { + t = btf_type_by_id(r->btf, next_id); + switch (btf_kind(t)) { + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + case BTF_KIND_VOLATILE: + case BTF_KIND_TYPEDEF: + case BTF_KIND_TYPE_TAG: + next_id = t->type; + break; + case BTF_KIND_ARRAY: { + struct btf_array *a = btf_array(t); + + next_id = a->type; + break; + } + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + if (next_id < r->nr_dist_base_types) + r->id_map[next_id] = BTF_IS_EMBEDDED; + next_id = 0; + break; + default: + next_id = 0; + break; + } + } + } + + return 0; +} + +/* Build a map from distilled base BTF ids to base BTF ids. To do so, iterate + * through base BTF looking up distilled type (using binary search) equivalents. + */ +static int btf_relocate_map_distilled_base(struct btf_relocate *r) +{ + struct btf_name_info *dist_base_info_sorted, *dist_base_info_sorted_end; + struct btf_type *base_t, *dist_t; + __u8 *base_name_cnt = NULL; + int err = 0; + __u32 id; + + /* generate a sort index array of name/type ids sorted by name for + * distilled base BTF to speed name-based lookups. + */ + dist_base_info_sorted = calloc(r->nr_dist_base_types, sizeof(*dist_base_info_sorted)); + if (!dist_base_info_sorted) { + err = -ENOMEM; + goto done; + } + dist_base_info_sorted_end = dist_base_info_sorted + r->nr_dist_base_types; + for (id = 0; id < r->nr_dist_base_types; id++) { + dist_t = btf_type_by_id(r->dist_base_btf, id); + dist_base_info_sorted[id].name = btf__name_by_offset(r->dist_base_btf, + dist_t->name_off); + dist_base_info_sorted[id].id = id; + dist_base_info_sorted[id].size = dist_t->size; + dist_base_info_sorted[id].needs_size = true; + } + qsort(dist_base_info_sorted, r->nr_dist_base_types, sizeof(*dist_base_info_sorted), + cmp_btf_name_size); + + /* Mark distilled base struct/union members of split BTF structs/unions + * in id_map with BTF_IS_EMBEDDED; this signals that these types + * need to match both name and size, otherwise embeddding the base + * struct/union in the split type is invalid. + */ + for (id = r->nr_dist_base_types; id < r->nr_split_types; id++) { + err = btf_mark_embedded_composite_type_ids(r, id); + if (err) + goto done; + } + + /* Collect name counts for composite types in base BTF. If multiple + * instances of a struct/union of the same name exist, we need to use + * size to determine which to map to since name alone is ambiguous. + */ + base_name_cnt = calloc(r->base_str_len, sizeof(*base_name_cnt)); + if (!base_name_cnt) { + err = -ENOMEM; + goto done; + } + for (id = 1; id < r->nr_base_types; id++) { + base_t = btf_type_by_id(r->base_btf, id); + if (!btf_is_composite(base_t) || !base_t->name_off) + continue; + if (base_name_cnt[base_t->name_off] < 255) + base_name_cnt[base_t->name_off]++; + } + + /* Now search base BTF for matching distilled base BTF types. */ + for (id = 1; id < r->nr_base_types; id++) { + struct btf_name_info *dist_name_info, *dist_name_info_next = NULL; + struct btf_name_info base_name_info = {}; + int dist_kind, base_kind; + + base_t = btf_type_by_id(r->base_btf, id); + /* distilled base consists of named types only. */ + if (!base_t->name_off) + continue; + base_kind = btf_kind(base_t); + base_name_info.id = id; + base_name_info.name = btf__name_by_offset(r->base_btf, base_t->name_off); + switch (base_kind) { + case BTF_KIND_INT: + case BTF_KIND_FLOAT: + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + /* These types should match both name and size */ + base_name_info.needs_size = true; + base_name_info.size = base_t->size; + break; + case BTF_KIND_FWD: + /* No size considerations for fwds. */ + break; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + /* Size only needs to be used for struct/union if there + * are multiple types in base BTF with the same name. + * If there are multiple _distilled_ types with the same + * name (a very unlikely scenario), that doesn't matter + * unless corresponding _base_ types to match them are + * missing. + */ + base_name_info.needs_size = base_name_cnt[base_t->name_off] > 1; + base_name_info.size = base_t->size; + break; + default: + continue; + } + /* iterate over all matching distilled base types */ + for (dist_name_info = search_btf_name_size(&base_name_info, dist_base_info_sorted, + r->nr_dist_base_types); + dist_name_info != NULL; dist_name_info = dist_name_info_next) { + /* Are there more distilled matches to process after + * this one? + */ + dist_name_info_next = dist_name_info + 1; + if (dist_name_info_next >= dist_base_info_sorted_end || + cmp_btf_name_size(&base_name_info, dist_name_info_next)) + dist_name_info_next = NULL; + + if (!dist_name_info->id || dist_name_info->id > r->nr_dist_base_types) { + pr_warn("base BTF id [%d] maps to invalid distilled base BTF id [%d]\n", + id, dist_name_info->id); + err = -EINVAL; + goto done; + } + dist_t = btf_type_by_id(r->dist_base_btf, dist_name_info->id); + dist_kind = btf_kind(dist_t); + + /* Validate that the found distilled type is compatible. + * Do not error out on mismatch as another match may + * occur for an identically-named type. + */ + switch (dist_kind) { + case BTF_KIND_FWD: + switch (base_kind) { + case BTF_KIND_FWD: + if (btf_kflag(dist_t) != btf_kflag(base_t)) + continue; + break; + case BTF_KIND_STRUCT: + if (btf_kflag(base_t)) + continue; + break; + case BTF_KIND_UNION: + if (!btf_kflag(base_t)) + continue; + break; + default: + continue; + } + break; + case BTF_KIND_INT: + if (dist_kind != base_kind || + btf_int_encoding(base_t) != btf_int_encoding(dist_t)) + continue; + break; + case BTF_KIND_FLOAT: + if (dist_kind != base_kind) + continue; + break; + case BTF_KIND_ENUM: + /* ENUM and ENUM64 are encoded as sized ENUM in + * distilled base BTF. + */ + if (base_kind != dist_kind && base_kind != BTF_KIND_ENUM64) + continue; + break; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + /* size verification is required for embedded + * struct/unions. + */ + if (r->id_map[dist_name_info->id] == BTF_IS_EMBEDDED && + base_t->size != dist_t->size) + continue; + break; + default: + continue; + } + if (r->id_map[dist_name_info->id] && + r->id_map[dist_name_info->id] != BTF_IS_EMBEDDED) { + /* we already have a match; this tells us that + * multiple base types of the same name + * have the same size, since for cases where + * multiple types have the same name we match + * on name and size. In this case, we have + * no way of determining which to relocate + * to in base BTF, so error out. + */ + pr_warn("distilled base BTF type '%s' [%u], size %u has multiple candidates of the same size (ids [%u, %u]) in base BTF\n", + base_name_info.name, dist_name_info->id, + base_t->size, id, r->id_map[dist_name_info->id]); + err = -EINVAL; + goto done; + } + /* map id and name */ + r->id_map[dist_name_info->id] = id; + r->str_map[dist_t->name_off] = base_t->name_off; + } + } + /* ensure all distilled BTF ids now have a mapping... */ + for (id = 1; id < r->nr_dist_base_types; id++) { + const char *name; + + if (r->id_map[id] && r->id_map[id] != BTF_IS_EMBEDDED) + continue; + dist_t = btf_type_by_id(r->dist_base_btf, id); + name = btf__name_by_offset(r->dist_base_btf, dist_t->name_off); + pr_warn("distilled base BTF type '%s' [%d] is not mapped to base BTF id\n", + name, id); + err = -EINVAL; + break; + } +done: + free(base_name_cnt); + free(dist_base_info_sorted); + return err; +} + +/* distilled base should only have named int/float/enum/fwd/struct/union types. */ +static int btf_relocate_validate_distilled_base(struct btf_relocate *r) +{ + unsigned int i; + + for (i = 1; i < r->nr_dist_base_types; i++) { + struct btf_type *t = btf_type_by_id(r->dist_base_btf, i); + int kind = btf_kind(t); + + switch (kind) { + case BTF_KIND_INT: + case BTF_KIND_FLOAT: + case BTF_KIND_ENUM: + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + case BTF_KIND_FWD: + if (t->name_off) + break; + pr_warn("type [%d], kind [%d] is invalid for distilled base BTF; it is anonymous\n", + i, kind); + return -EINVAL; + default: + pr_warn("type [%d] in distilled based BTF has unexpected kind [%d]\n", + i, kind); + return -EINVAL; + } + } + return 0; +} + +static int btf_relocate_rewrite_strs(struct btf_relocate *r, __u32 i) +{ + struct btf_type *t = btf_type_by_id(r->btf, i); + struct btf_field_iter it; + __u32 *str_off; + int off, err; + + err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_STRS); + if (err) + return err; + + while ((str_off = btf_field_iter_next(&it))) { + if (!*str_off) + continue; + if (*str_off >= r->dist_str_len) { + *str_off += r->base_str_len - r->dist_str_len; + } else { + off = r->str_map[*str_off]; + if (!off) { + pr_warn("string '%s' [offset %u] is not mapped to base BTF", + btf__str_by_offset(r->btf, off), *str_off); + return -ENOENT; + } + *str_off = off; + } + } + return 0; +} + +/* If successful, output of relocation is updated BTF with base BTF pointing + * at base_btf, and type ids, strings adjusted accordingly. + */ +int btf_relocate(struct btf *btf, const struct btf *base_btf, __u32 **id_map) +{ + unsigned int nr_types = btf__type_cnt(btf); + const struct btf_header *dist_base_hdr; + const struct btf_header *base_hdr; + struct btf_relocate r = {}; + int err = 0; + __u32 id, i; + + r.dist_base_btf = btf__base_btf(btf); + if (!base_btf || r.dist_base_btf == base_btf) + return -EINVAL; + + r.nr_dist_base_types = btf__type_cnt(r.dist_base_btf); + r.nr_base_types = btf__type_cnt(base_btf); + r.nr_split_types = nr_types - r.nr_dist_base_types; + r.btf = btf; + r.base_btf = base_btf; + + r.id_map = calloc(nr_types, sizeof(*r.id_map)); + r.str_map = calloc(btf_header(r.dist_base_btf)->str_len, sizeof(*r.str_map)); + dist_base_hdr = btf_header(r.dist_base_btf); + base_hdr = btf_header(r.base_btf); + r.dist_str_len = dist_base_hdr->str_len; + r.base_str_len = base_hdr->str_len; + if (!r.id_map || !r.str_map) { + err = -ENOMEM; + goto err_out; + } + + err = btf_relocate_validate_distilled_base(&r); + if (err) + goto err_out; + + /* Split BTF ids need to be adjusted as base and distilled base + * have different numbers of types, changing the start id of split + * BTF. + */ + for (id = r.nr_dist_base_types; id < nr_types; id++) + r.id_map[id] = id + r.nr_base_types - r.nr_dist_base_types; + + /* Build a map from distilled base ids to actual base BTF ids; it is used + * to update split BTF id references. Also build a str_map mapping from + * distilled base BTF names to base BTF names. + */ + err = btf_relocate_map_distilled_base(&r); + if (err) + goto err_out; + + /* Next, rewrite type ids in split BTF, replacing split ids with updated + * ids based on number of types in base BTF, and base ids with + * relocated ids from base_btf. + */ + for (i = 0, id = r.nr_dist_base_types; i < r.nr_split_types; i++, id++) { + err = btf_relocate_rewrite_type_id(&r, id); + if (err) + goto err_out; + } + /* String offsets now need to be updated using the str_map. */ + for (i = 0; i < r.nr_split_types; i++) { + err = btf_relocate_rewrite_strs(&r, i + r.nr_dist_base_types); + if (err) + goto err_out; + } + /* Finally reset base BTF to be base_btf */ + btf_set_base_btf(btf, base_btf); + + if (id_map) { + *id_map = r.id_map; + r.id_map = NULL; + } +err_out: + free(r.id_map); + free(r.str_map); + return err; +} diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 175d1536e070..8f0d9ea3b1b4 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -420,6 +420,7 @@ LIBBPF_1.4.0 { LIBBPF_1.5.0 { global: btf__distill_base; + btf__relocate; bpf_map__autoattach; bpf_map__set_autoattach; bpf_program__attach_sockmap; diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index e2f06609c624..408df59e0771 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -234,6 +234,9 @@ struct btf_type; struct btf_type *btf_type_by_id(const struct btf *btf, __u32 type_id); const char *btf_kind_str(const struct btf_type *t); const struct btf_type *skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id); +const struct btf_header *btf_header(const struct btf *btf); +void btf_set_base_btf(struct btf *btf, const struct btf *base_btf); +int btf_relocate(struct btf *btf, const struct btf *base_btf, __u32 **id_map); static inline enum btf_func_linkage btf_func_linkage(const struct btf_type *t) { -- cgit v1.2.3-58-ga151 From c86f180ffc993975fed5907a869fc9b1555d0cfb Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Thu, 13 Jun 2024 10:50:10 +0100 Subject: libbpf: Make btf_parse_elf process .BTF.base transparently Update btf_parse_elf() to check if .BTF.base section is present. The logic is as follows: if .BTF.base section exists: distilled_base := btf_new(.BTF.base) if distilled_base: btf := btf_new(.BTF, .base_btf=distilled_base) if base_btf: btf_relocate(btf, base_btf) else: btf := btf_new(.BTF) return btf In other words: - if .BTF.base section exists, load BTF from it and use it as a base for .BTF load; - if base_btf is specified and .BTF.base section exist, relocate newly loaded .BTF against base_btf. Signed-off-by: Eduard Zingerman Signed-off-by: Alan Maguire Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20240613095014.357981-6-alan.maguire@oracle.com --- tools/lib/bpf/btf.c | 164 +++++++++++++++++++++++++++++++++++----------------- tools/lib/bpf/btf.h | 1 + 2 files changed, 111 insertions(+), 54 deletions(-) (limited to 'tools/lib/bpf/btf.c') diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 5e20354fbcfa..ef1b2f573c1b 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -116,6 +116,9 @@ struct btf { /* whether strings are already deduplicated */ bool strs_deduped; + /* whether base_btf should be freed in btf_free for this instance */ + bool owns_base; + /* BTF object FD, if loaded into kernel */ int fd; @@ -969,6 +972,8 @@ void btf__free(struct btf *btf) free(btf->raw_data); free(btf->raw_data_swapped); free(btf->type_offs); + if (btf->owns_base) + btf__free(btf->base_btf); free(btf); } @@ -1084,53 +1089,38 @@ struct btf *btf__new_split(const void *data, __u32 size, struct btf *base_btf) return libbpf_ptr(btf_new(data, size, base_btf)); } -static struct btf *btf_parse_elf(const char *path, struct btf *base_btf, - struct btf_ext **btf_ext) +struct btf_elf_secs { + Elf_Data *btf_data; + Elf_Data *btf_ext_data; + Elf_Data *btf_base_data; +}; + +static int btf_find_elf_sections(Elf *elf, const char *path, struct btf_elf_secs *secs) { - Elf_Data *btf_data = NULL, *btf_ext_data = NULL; - int err = 0, fd = -1, idx = 0; - struct btf *btf = NULL; Elf_Scn *scn = NULL; - Elf *elf = NULL; + Elf_Data *data; GElf_Ehdr ehdr; size_t shstrndx; + int idx = 0; - if (elf_version(EV_CURRENT) == EV_NONE) { - pr_warn("failed to init libelf for %s\n", path); - return ERR_PTR(-LIBBPF_ERRNO__LIBELF); - } - - fd = open(path, O_RDONLY | O_CLOEXEC); - if (fd < 0) { - err = -errno; - pr_warn("failed to open %s: %s\n", path, strerror(errno)); - return ERR_PTR(err); - } - - err = -LIBBPF_ERRNO__FORMAT; - - elf = elf_begin(fd, ELF_C_READ, NULL); - if (!elf) { - pr_warn("failed to open %s as ELF file\n", path); - goto done; - } if (!gelf_getehdr(elf, &ehdr)) { pr_warn("failed to get EHDR from %s\n", path); - goto done; + goto err; } if (elf_getshdrstrndx(elf, &shstrndx)) { pr_warn("failed to get section names section index for %s\n", path); - goto done; + goto err; } if (!elf_rawdata(elf_getscn(elf, shstrndx), NULL)) { pr_warn("failed to get e_shstrndx from %s\n", path); - goto done; + goto err; } while ((scn = elf_nextscn(elf, scn)) != NULL) { + Elf_Data **field; GElf_Shdr sh; char *name; @@ -1138,42 +1128,102 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf, if (gelf_getshdr(scn, &sh) != &sh) { pr_warn("failed to get section(%d) header from %s\n", idx, path); - goto done; + goto err; } name = elf_strptr(elf, shstrndx, sh.sh_name); if (!name) { pr_warn("failed to get section(%d) name from %s\n", idx, path); - goto done; + goto err; } - if (strcmp(name, BTF_ELF_SEC) == 0) { - btf_data = elf_getdata(scn, 0); - if (!btf_data) { - pr_warn("failed to get section(%d, %s) data from %s\n", - idx, name, path); - goto done; - } - continue; - } else if (btf_ext && strcmp(name, BTF_EXT_ELF_SEC) == 0) { - btf_ext_data = elf_getdata(scn, 0); - if (!btf_ext_data) { - pr_warn("failed to get section(%d, %s) data from %s\n", - idx, name, path); - goto done; - } + + if (strcmp(name, BTF_ELF_SEC) == 0) + field = &secs->btf_data; + else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) + field = &secs->btf_ext_data; + else if (strcmp(name, BTF_BASE_ELF_SEC) == 0) + field = &secs->btf_base_data; + else continue; + + data = elf_getdata(scn, 0); + if (!data) { + pr_warn("failed to get section(%d, %s) data from %s\n", + idx, name, path); + goto err; } + *field = data; + } + + return 0; + +err: + return -LIBBPF_ERRNO__FORMAT; +} + +static struct btf *btf_parse_elf(const char *path, struct btf *base_btf, + struct btf_ext **btf_ext) +{ + struct btf_elf_secs secs = {}; + struct btf *dist_base_btf = NULL; + struct btf *btf = NULL; + int err = 0, fd = -1; + Elf *elf = NULL; + + if (elf_version(EV_CURRENT) == EV_NONE) { + pr_warn("failed to init libelf for %s\n", path); + return ERR_PTR(-LIBBPF_ERRNO__LIBELF); + } + + fd = open(path, O_RDONLY | O_CLOEXEC); + if (fd < 0) { + err = -errno; + pr_warn("failed to open %s: %s\n", path, strerror(errno)); + return ERR_PTR(err); } - if (!btf_data) { + elf = elf_begin(fd, ELF_C_READ, NULL); + if (!elf) { + pr_warn("failed to open %s as ELF file\n", path); + goto done; + } + + err = btf_find_elf_sections(elf, path, &secs); + if (err) + goto done; + + if (!secs.btf_data) { pr_warn("failed to find '%s' ELF section in %s\n", BTF_ELF_SEC, path); err = -ENODATA; goto done; } - btf = btf_new(btf_data->d_buf, btf_data->d_size, base_btf); - err = libbpf_get_error(btf); - if (err) + + if (secs.btf_base_data) { + dist_base_btf = btf_new(secs.btf_base_data->d_buf, secs.btf_base_data->d_size, + NULL); + if (IS_ERR(dist_base_btf)) { + err = PTR_ERR(dist_base_btf); + dist_base_btf = NULL; + goto done; + } + } + + btf = btf_new(secs.btf_data->d_buf, secs.btf_data->d_size, + dist_base_btf ?: base_btf); + if (IS_ERR(btf)) { + err = PTR_ERR(btf); goto done; + } + if (dist_base_btf && base_btf) { + err = btf__relocate(btf, base_btf); + if (err) + goto done; + btf__free(dist_base_btf); + dist_base_btf = NULL; + } + + if (dist_base_btf) + btf->owns_base = true; switch (gelf_getclass(elf)) { case ELFCLASS32: @@ -1187,11 +1237,12 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf, break; } - if (btf_ext && btf_ext_data) { - *btf_ext = btf_ext__new(btf_ext_data->d_buf, btf_ext_data->d_size); - err = libbpf_get_error(*btf_ext); - if (err) + if (btf_ext && secs.btf_ext_data) { + *btf_ext = btf_ext__new(secs.btf_ext_data->d_buf, secs.btf_ext_data->d_size); + if (IS_ERR(*btf_ext)) { + err = PTR_ERR(*btf_ext); goto done; + } } else if (btf_ext) { *btf_ext = NULL; } @@ -1205,6 +1256,7 @@ done: if (btf_ext) btf_ext__free(*btf_ext); + btf__free(dist_base_btf); btf__free(btf); return ERR_PTR(err); @@ -5598,5 +5650,9 @@ void btf_set_base_btf(struct btf *btf, const struct btf *base_btf) int btf__relocate(struct btf *btf, const struct btf *base_btf) { - return libbpf_err(btf_relocate(btf, base_btf, NULL)); + int err = btf_relocate(btf, base_btf, NULL); + + if (!err) + btf->owns_base = false; + return libbpf_err(err); } diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 8a93120b7385..b68d216837a9 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -18,6 +18,7 @@ extern "C" { #define BTF_ELF_SEC ".BTF" #define BTF_EXT_ELF_SEC ".BTF.ext" +#define BTF_BASE_ELF_SEC ".BTF.base" #define MAPS_ELF_SEC ".maps" struct btf; -- cgit v1.2.3-58-ga151 From e7ac331b30555cf1a0826784a346f36dbf800451 Mon Sep 17 00:00:00 2001 From: Alan Maguire Date: Thu, 20 Jun 2024 10:17:30 +0100 Subject: libbpf: Split field iter code into its own file kernel This will allow it to be shared with the kernel. No functional change. Suggested-by: Andrii Nakryiko Signed-off-by: Alan Maguire Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20240620091733.1967885-4-alan.maguire@oracle.com --- tools/lib/bpf/Build | 2 +- tools/lib/bpf/btf.c | 162 --------------------------------------------- tools/lib/bpf/btf_iter.c | 169 +++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 170 insertions(+), 163 deletions(-) create mode 100644 tools/lib/bpf/btf_iter.c (limited to 'tools/lib/bpf/btf.c') diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build index 336da6844d42..e2cd558ca0b4 100644 --- a/tools/lib/bpf/Build +++ b/tools/lib/bpf/Build @@ -1,4 +1,4 @@ libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o \ netlink.o bpf_prog_linfo.o libbpf_probes.o hashmap.o \ btf_dump.o ringbuf.o strset.o linker.o gen_loader.o relo_core.o \ - usdt.o zip.o elf.o features.o btf_relocate.o + usdt.o zip.o elf.o features.o btf_iter.o btf_relocate.o diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index ef1b2f573c1b..0c0f60cad769 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -5093,168 +5093,6 @@ struct btf *btf__load_module_btf(const char *module_name, struct btf *vmlinux_bt return btf__parse_split(path, vmlinux_btf); } -int btf_field_iter_init(struct btf_field_iter *it, struct btf_type *t, enum btf_field_iter_kind iter_kind) -{ - it->p = NULL; - it->m_idx = -1; - it->off_idx = 0; - it->vlen = 0; - - 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; - } - 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; - } - break; - default: - return -EINVAL; - } - - if (it->desc.m_sz) - it->vlen = btf_vlen(t); - - it->p = t; - return 0; -} - -__u32 *btf_field_iter_next(struct btf_field_iter *it) -{ - if (!it->p) - return NULL; - - 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; - } - - /* if type doesn't have members, stop */ - if (it->desc.m_sz == 0) { - it->p = NULL; - return NULL; - } - - 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; - } - - if (it->m_idx < it->vlen) - return it->p + it->desc.m_offs[it->off_idx++]; - - it->p = NULL; - return NULL; -} - int btf_ext_visit_type_ids(struct btf_ext *btf_ext, type_id_visit_fn visit, void *ctx) { const struct btf_ext_info *seg; diff --git a/tools/lib/bpf/btf_iter.c b/tools/lib/bpf/btf_iter.c new file mode 100644 index 000000000000..c308aa60285d --- /dev/null +++ b/tools/lib/bpf/btf_iter.c @@ -0,0 +1,169 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* Copyright (c) 2021 Facebook */ +/* Copyright (c) 2024, Oracle and/or its affiliates. */ + +#include "btf.h" +#include "libbpf_internal.h" + +int btf_field_iter_init(struct btf_field_iter *it, struct btf_type *t, + enum btf_field_iter_kind iter_kind) +{ + it->p = NULL; + it->m_idx = -1; + it->off_idx = 0; + it->vlen = 0; + + 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; + } + 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; + } + break; + default: + return -EINVAL; + } + + if (it->desc.m_sz) + it->vlen = btf_vlen(t); + + it->p = t; + return 0; +} + +__u32 *btf_field_iter_next(struct btf_field_iter *it) +{ + if (!it->p) + return NULL; + + 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; + } + + /* if type doesn't have members, stop */ + if (it->desc.m_sz == 0) { + it->p = NULL; + return NULL; + } + + 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; + } + + if (it->m_idx < it->vlen) + return it->p + it->desc.m_offs[it->off_idx++]; + + it->p = NULL; + return NULL; +} -- cgit v1.2.3-58-ga151 From c73a9683cb21012b6c0f14217974837151c527a8 Mon Sep 17 00:00:00 2001 From: Antoine Tenart Date: Mon, 24 Jun 2024 11:09:07 +0200 Subject: libbpf: Skip base btf sanity checks When upgrading to libbpf 1.3 we noticed a big performance hit while loading programs using CORE on non base-BTF symbols. This was tracked down to the new BTF sanity check logic. The issue is the base BTF definitions are checked first for the base BTF and then again for every module BTF. Loading 5 dummy programs (using libbpf-rs) that are using CORE on a non-base BTF symbol on my system: - Before this fix: 3s. - With this fix: 0.1s. Fix this by only checking the types starting at the BTF start id. This should ensure the base BTF is still checked as expected but only once (btf->start_id == 1 when creating the base BTF), and then only additional types are checked for each module BTF. Fixes: 3903802bb99a ("libbpf: Add basic BTF sanity validation") Signed-off-by: Antoine Tenart Signed-off-by: Andrii Nakryiko Reviewed-by: Alan Maguire Link: https://lore.kernel.org/bpf/20240624090908.171231-1-atenart@kernel.org --- tools/lib/bpf/btf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/lib/bpf/btf.c') diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 0c0f60cad769..cd5dd6619214 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -601,7 +601,7 @@ static int btf_sanity_check(const struct btf *btf) __u32 i, n = btf__type_cnt(btf); int err; - for (i = 1; i < n; i++) { + for (i = btf->start_id; i < n; i++) { t = btf_type_by_id(btf, i); err = btf_validate_type(btf, t, i); if (err) -- cgit v1.2.3-58-ga151 From 5b747c23f17d791e08fdf4baa7e14b704625518c Mon Sep 17 00:00:00 2001 From: Alan Maguire Date: Sat, 29 Jun 2024 11:00:58 +0100 Subject: libbpf: Fix error handling in btf__distill_base() Coverity points out that after calling btf__new_empty_split() the wrong value is checked for error. Fixes: 58e185a0dc35 ("libbpf: Add btf__distill_base() creating split BTF with distilled base BTF") Reported-by: Andrii Nakryiko Signed-off-by: Alan Maguire Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20240629100058.2866763-1-alan.maguire@oracle.com --- tools/lib/bpf/btf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/lib/bpf/btf.c') diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index cd5dd6619214..32c00db3b91b 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -5431,7 +5431,7 @@ int btf__distill_base(const struct btf *src_btf, struct btf **new_base_btf, * BTF available. */ new_split = btf__new_empty_split(new_base); - if (!new_split_btf) { + if (!new_split) { err = -errno; goto done; } -- cgit v1.2.3-58-ga151