diff options
Diffstat (limited to 'tools/lib/bpf/btf.c')
| -rw-r--r-- | tools/lib/bpf/btf.c | 2277 |
1 files changed, 1871 insertions, 406 deletions
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 6bdbc389b493..d9c10830d749 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) /* Copyright (c) 2018 Facebook */ +#include <byteswap.h> #include <endian.h> #include <stdio.h> #include <stdlib.h> @@ -21,26 +22,108 @@ #include "libbpf_internal.h" #include "hashmap.h" -/* make sure libbpf doesn't use kernel-only integer typedefs */ -#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 - #define BTF_MAX_NR_TYPES 0x7fffffffU #define BTF_MAX_STR_OFFSET 0x7fffffffU static struct btf_type btf_void; struct btf { - union { - struct btf_header *hdr; - void *data; - }; - struct btf_type **types; - const char *strings; - void *nohdr_data; + /* raw BTF data in native endianness */ + void *raw_data; + /* raw BTF data in non-native endianness */ + void *raw_data_swapped; + __u32 raw_size; + /* whether target endianness differs from the native one */ + bool swapped_endian; + + /* + * When BTF is loaded from an ELF or raw memory it is stored + * in a contiguous memory block. The hdr, type_data, and, strs_data + * point inside that memory region to their respective parts of BTF + * representation: + * + * +--------------------------------+ + * | Header | Types | Strings | + * +--------------------------------+ + * ^ ^ ^ + * | | | + * hdr | | + * types_data-+ | + * strs_data------------+ + * + * If BTF data is later modified, e.g., due to types added or + * removed, BTF deduplication performed, etc, this contiguous + * representation is broken up into three independently allocated + * memory regions to be able to modify them independently. + * raw_data is nulled out at that point, but can be later allocated + * and cached again if user calls btf__get_raw_data(), at which point + * raw_data will contain a contiguous copy of header, types, and + * strings: + * + * +----------+ +---------+ +-----------+ + * | Header | | Types | | Strings | + * +----------+ +---------+ +-----------+ + * ^ ^ ^ + * | | | + * hdr | | + * types_data----+ | + * strs_data------------------+ + * + * +----------+---------+-----------+ + * | Header | Types | Strings | + * raw_data----->+----------+---------+-----------+ + */ + struct btf_header *hdr; + + void *types_data; + size_t types_data_cap; /* used size stored in hdr->type_len */ + + /* type ID to `struct btf_type *` lookup index + * type_offs[0] corresponds to the first non-VOID type: + * - for base BTF it's type [1]; + * - for split BTF it's the first non-base BTF type. + */ + __u32 *type_offs; + size_t type_offs_cap; + /* number of types in this BTF instance: + * - doesn't include special [0] void type; + * - for split BTF counts number of types added on top of base BTF. + */ __u32 nr_types; - __u32 types_size; - __u32 data_size; + /* if not NULL, points to the base BTF on top of which the current + * split BTF is based + */ + struct btf *base_btf; + /* BTF type ID of the first type in this BTF instance: + * - for base BTF it's equal to 1; + * - for split BTF it's equal to biggest type ID of base BTF plus 1. + */ + int start_id; + /* logical string offset of this BTF instance: + * - for base BTF it's equal to 0; + * - for split BTF it's equal to total size of base BTF's string section size. + */ + int start_str_off; + + void *strs_data; + size_t strs_data_cap; /* used size stored in hdr->str_len */ + + /* lookup index for each unique string in strings section */ + struct hashmap *strs_hash; + /* whether strings are already deduplicated */ + bool strs_deduped; + /* extra indirection layer to make strings hashmap work with stable + * string offsets and ability to transparently choose between + * btf->strs_data or btf_dedup->strs_data as a source of strings. + * This is used for BTF strings dedup to transfer deduplicated strings + * data back to struct btf without re-building strings index. + */ + void **strs_data_ptr; + + /* BTF object FD, if loaded into kernel */ int fd; + + /* Pointer size (in bytes) for a target architecture of this BTF */ int ptr_sz; }; @@ -49,110 +132,155 @@ static inline __u64 ptr_to_u64(const void *ptr) return (__u64) (unsigned long) ptr; } -static int btf_add_type(struct btf *btf, struct btf_type *t) +/* Ensure given dynamically allocated memory region pointed to by *data* with + * capacity of *cap_cnt* elements each taking *elem_sz* bytes has enough + * memory to accomodate *add_cnt* new elements, assuming *cur_cnt* elements + * are already used. At most *max_cnt* elements can be ever allocated. + * If necessary, memory is reallocated and all existing data is copied over, + * new pointer to the memory region is stored at *data, new memory region + * capacity (in number of elements) is stored in *cap. + * On success, memory pointer to the beginning of unused memory is returned. + * On error, NULL is returned. + */ +void *btf_add_mem(void **data, size_t *cap_cnt, size_t elem_sz, + size_t cur_cnt, size_t max_cnt, size_t add_cnt) { - if (btf->types_size - btf->nr_types < 2) { - struct btf_type **new_types; - __u32 expand_by, new_size; + size_t new_cnt; + void *new_data; - if (btf->types_size == BTF_MAX_NR_TYPES) - return -E2BIG; + if (cur_cnt + add_cnt <= *cap_cnt) + return *data + cur_cnt * elem_sz; - expand_by = max(btf->types_size >> 2, 16U); - new_size = min(BTF_MAX_NR_TYPES, btf->types_size + expand_by); + /* requested more than the set limit */ + if (cur_cnt + add_cnt > max_cnt) + return NULL; - new_types = realloc(btf->types, sizeof(*new_types) * new_size); - if (!new_types) - return -ENOMEM; + new_cnt = *cap_cnt; + new_cnt += new_cnt / 4; /* expand by 25% */ + if (new_cnt < 16) /* but at least 16 elements */ + new_cnt = 16; + if (new_cnt > max_cnt) /* but not exceeding a set limit */ + new_cnt = max_cnt; + if (new_cnt < cur_cnt + add_cnt) /* also ensure we have enough memory */ + new_cnt = cur_cnt + add_cnt; + + new_data = libbpf_reallocarray(*data, new_cnt, elem_sz); + if (!new_data) + return NULL; - if (btf->nr_types == 0) - new_types[0] = &btf_void; + /* zero out newly allocated portion of memory */ + memset(new_data + (*cap_cnt) * elem_sz, 0, (new_cnt - *cap_cnt) * elem_sz); - btf->types = new_types; - btf->types_size = new_size; - } + *data = new_data; + *cap_cnt = new_cnt; + return new_data + cur_cnt * elem_sz; +} + +/* Ensure given dynamically allocated memory region has enough allocated space + * to accommodate *need_cnt* elements of size *elem_sz* bytes each + */ +int btf_ensure_mem(void **data, size_t *cap_cnt, size_t elem_sz, size_t need_cnt) +{ + void *p; + + if (need_cnt <= *cap_cnt) + return 0; - btf->types[++(btf->nr_types)] = t; + p = btf_add_mem(data, cap_cnt, elem_sz, *cap_cnt, SIZE_MAX, need_cnt - *cap_cnt); + if (!p) + return -ENOMEM; return 0; } -static int btf_parse_hdr(struct btf *btf) +static int btf_add_type_idx_entry(struct btf *btf, __u32 type_off) { - const struct btf_header *hdr = btf->hdr; - __u32 meta_left; + __u32 *p; - if (btf->data_size < sizeof(struct btf_header)) { - pr_debug("BTF header not found\n"); - return -EINVAL; - } + p = btf_add_mem((void **)&btf->type_offs, &btf->type_offs_cap, sizeof(__u32), + btf->nr_types, BTF_MAX_NR_TYPES, 1); + if (!p) + return -ENOMEM; - if (hdr->magic != BTF_MAGIC) { - pr_debug("Invalid BTF magic:%x\n", hdr->magic); - return -EINVAL; - } + *p = type_off; + return 0; +} - if (hdr->version != BTF_VERSION) { - pr_debug("Unsupported BTF version:%u\n", hdr->version); - return -ENOTSUP; - } +static void btf_bswap_hdr(struct btf_header *h) +{ + h->magic = bswap_16(h->magic); + h->hdr_len = bswap_32(h->hdr_len); + h->type_off = bswap_32(h->type_off); + h->type_len = bswap_32(h->type_len); + h->str_off = bswap_32(h->str_off); + h->str_len = bswap_32(h->str_len); +} - if (hdr->flags) { - pr_debug("Unsupported BTF flags:%x\n", hdr->flags); - return -ENOTSUP; - } +static int btf_parse_hdr(struct btf *btf) +{ + struct btf_header *hdr = btf->hdr; + __u32 meta_left; - meta_left = btf->data_size - sizeof(*hdr); - if (!meta_left) { - pr_debug("BTF has no data\n"); + if (btf->raw_size < sizeof(struct btf_header)) { + pr_debug("BTF header not found\n"); return -EINVAL; } - if (meta_left < hdr->type_off) { - pr_debug("Invalid BTF type section offset:%u\n", hdr->type_off); + if (hdr->magic == bswap_16(BTF_MAGIC)) { + btf->swapped_endian = true; + if (bswap_32(hdr->hdr_len) != sizeof(struct btf_header)) { + pr_warn("Can't load BTF with non-native endianness due to unsupported header length %u\n", + bswap_32(hdr->hdr_len)); + return -ENOTSUP; + } + btf_bswap_hdr(hdr); + } else if (hdr->magic != BTF_MAGIC) { + pr_debug("Invalid BTF magic:%x\n", hdr->magic); return -EINVAL; } - if (meta_left < hdr->str_off) { - pr_debug("Invalid BTF string section offset:%u\n", hdr->str_off); + meta_left = btf->raw_size - sizeof(*hdr); + if (meta_left < hdr->str_off + hdr->str_len) { + pr_debug("Invalid BTF total size:%u\n", btf->raw_size); return -EINVAL; } - if (hdr->type_off >= hdr->str_off) { - pr_debug("BTF type section offset >= string section offset. No type?\n"); + if (hdr->type_off + hdr->type_len > hdr->str_off) { + pr_debug("Invalid BTF data sections layout: type data at %u + %u, strings data at %u + %u\n", + hdr->type_off, hdr->type_len, hdr->str_off, hdr->str_len); return -EINVAL; } - if (hdr->type_off & 0x02) { + if (hdr->type_off % 4) { pr_debug("BTF type section is not aligned to 4 bytes\n"); return -EINVAL; } - btf->nohdr_data = btf->hdr + 1; - return 0; } static int btf_parse_str_sec(struct btf *btf) { const struct btf_header *hdr = btf->hdr; - const char *start = btf->nohdr_data + hdr->str_off; + const char *start = btf->strs_data; const char *end = start + btf->hdr->str_len; - if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_STR_OFFSET || - start[0] || end[-1]) { + if (btf->base_btf && hdr->str_len == 0) + return 0; + if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_STR_OFFSET || end[-1]) { + pr_debug("Invalid BTF string section\n"); + return -EINVAL; + } + if (!btf->base_btf && start[0]) { pr_debug("Invalid BTF string section\n"); return -EINVAL; } - - btf->strings = start; - return 0; } -static int btf_type_size(struct btf_type *t) +static int btf_type_size(const struct btf_type *t) { - int base_size = sizeof(struct btf_type); + const int base_size = sizeof(struct btf_type); __u16 vlen = btf_vlen(t); switch (btf_kind(t)) { @@ -185,25 +313,110 @@ static int btf_type_size(struct btf_type *t) } } +static void btf_bswap_type_base(struct btf_type *t) +{ + t->name_off = bswap_32(t->name_off); + t->info = bswap_32(t->info); + t->type = bswap_32(t->type); +} + +static int btf_bswap_type_rest(struct btf_type *t) +{ + struct btf_var_secinfo *v; + struct btf_member *m; + struct btf_array *a; + struct btf_param *p; + struct btf_enum *e; + __u16 vlen = btf_vlen(t); + int i; + + switch (btf_kind(t)) { + 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: + return 0; + case BTF_KIND_INT: + *(__u32 *)(t + 1) = bswap_32(*(__u32 *)(t + 1)); + return 0; + case BTF_KIND_ENUM: + for (i = 0, e = btf_enum(t); i < vlen; i++, e++) { + e->name_off = bswap_32(e->name_off); + e->val = bswap_32(e->val); + } + return 0; + case BTF_KIND_ARRAY: + a = btf_array(t); + a->type = bswap_32(a->type); + a->index_type = bswap_32(a->index_type); + a->nelems = bswap_32(a->nelems); + return 0; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + for (i = 0, m = btf_members(t); i < vlen; i++, m++) { + m->name_off = bswap_32(m->name_off); + m->type = bswap_32(m->type); + m->offset = bswap_32(m->offset); + } + return 0; + case BTF_KIND_FUNC_PROTO: + for (i = 0, p = btf_params(t); i < vlen; i++, p++) { + p->name_off = bswap_32(p->name_off); + p->type = bswap_32(p->type); + } + return 0; + case BTF_KIND_VAR: + btf_var(t)->linkage = bswap_32(btf_var(t)->linkage); + return 0; + case BTF_KIND_DATASEC: + for (i = 0, v = btf_var_secinfos(t); i < vlen; i++, v++) { + v->type = bswap_32(v->type); + v->offset = bswap_32(v->offset); + v->size = bswap_32(v->size); + } + return 0; + default: + pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t)); + return -EINVAL; + } +} + static int btf_parse_type_sec(struct btf *btf) { struct btf_header *hdr = btf->hdr; - void *nohdr_data = btf->nohdr_data; - void *next_type = nohdr_data + hdr->type_off; - void *end_type = nohdr_data + hdr->str_off; + void *next_type = btf->types_data; + void *end_type = next_type + hdr->type_len; + int err, type_size; - while (next_type < end_type) { - struct btf_type *t = next_type; - int type_size; - int err; + while (next_type + sizeof(struct btf_type) <= end_type) { + if (btf->swapped_endian) + btf_bswap_type_base(next_type); - type_size = btf_type_size(t); + type_size = btf_type_size(next_type); if (type_size < 0) return type_size; - next_type += type_size; - err = btf_add_type(btf, t); + if (next_type + type_size > end_type) { + pr_warn("BTF type [%d] is malformed\n", btf->start_id + btf->nr_types); + return -EINVAL; + } + + if (btf->swapped_endian && btf_bswap_type_rest(next_type)) + return -EINVAL; + + err = btf_add_type_idx_entry(btf, next_type - btf->types_data); if (err) return err; + + next_type += type_size; + btf->nr_types++; + } + + if (next_type != end_type) { + pr_warn("BTF types data is malformed\n"); + return -EINVAL; } return 0; @@ -211,24 +424,42 @@ static int btf_parse_type_sec(struct btf *btf) __u32 btf__get_nr_types(const struct btf *btf) { - return btf->nr_types; + return btf->start_id + btf->nr_types - 1; +} + +const struct btf *btf__base_btf(const struct btf *btf) +{ + return btf->base_btf; +} + +/* internal helper returning non-const pointer to a type */ +static struct btf_type *btf_type_by_id(struct btf *btf, __u32 type_id) +{ + if (type_id == 0) + return &btf_void; + if (type_id < btf->start_id) + return btf_type_by_id(btf->base_btf, type_id); + return btf->types_data + btf->type_offs[type_id - btf->start_id]; } const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id) { - if (type_id > btf->nr_types) + if (type_id >= btf->start_id + btf->nr_types) return NULL; - - return btf->types[type_id]; + return btf_type_by_id((struct btf *)btf, type_id); } static int determine_ptr_size(const struct btf *btf) { const struct btf_type *t; const char *name; - int i; + int i, n; - for (i = 1; i <= btf->nr_types; i++) { + if (btf->base_btf && btf->base_btf->ptr_sz > 0) + return btf->base_btf->ptr_sz; + + n = btf__get_nr_types(btf); + for (i = 1; i <= n; i++) { t = btf__type_by_id(btf, i); if (!btf_is_int(t)) continue; @@ -286,6 +517,38 @@ int btf__set_pointer_size(struct btf *btf, size_t ptr_sz) return 0; } +static bool is_host_big_endian(void) +{ +#if __BYTE_ORDER == __LITTLE_ENDIAN + return false; +#elif __BYTE_ORDER == __BIG_ENDIAN + return true; +#else +# error "Unrecognized __BYTE_ORDER__" +#endif +} + +enum btf_endianness btf__endianness(const struct btf *btf) +{ + if (is_host_big_endian()) + return btf->swapped_endian ? BTF_LITTLE_ENDIAN : BTF_BIG_ENDIAN; + else + return btf->swapped_endian ? BTF_BIG_ENDIAN : BTF_LITTLE_ENDIAN; +} + +int btf__set_endianness(struct btf *btf, enum btf_endianness endian) +{ + if (endian != BTF_LITTLE_ENDIAN && endian != BTF_BIG_ENDIAN) + return -EINVAL; + + btf->swapped_endian = is_host_big_endian() != (endian == BTF_BIG_ENDIAN); + if (!btf->swapped_endian) { + free(btf->raw_data_swapped); + btf->raw_data_swapped = NULL; + } + return 0; +} + static bool btf_type_is_void(const struct btf_type *t) { return t == &btf_void || btf_is_fwd(t); @@ -411,13 +674,13 @@ int btf__resolve_type(const struct btf *btf, __u32 type_id) __s32 btf__find_by_name(const struct btf *btf, const char *type_name) { - __u32 i; + __u32 i, nr_types = btf__get_nr_types(btf); if (!strcmp(type_name, "void")) return 0; - for (i = 1; i <= btf->nr_types; i++) { - const struct btf_type *t = btf->types[i]; + for (i = 1; i <= nr_types; i++) { + const struct btf_type *t = btf__type_by_id(btf, i); const char *name = btf__name_by_offset(btf, t->name_off); if (name && !strcmp(type_name, name)) @@ -430,13 +693,13 @@ __s32 btf__find_by_name(const struct btf *btf, const char *type_name) __s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name, __u32 kind) { - __u32 i; + __u32 i, nr_types = btf__get_nr_types(btf); if (kind == BTF_KIND_UNKN || !strcmp(type_name, "void")) return 0; - for (i = 1; i <= btf->nr_types; i++) { - const struct btf_type *t = btf->types[i]; + for (i = 1; i <= nr_types; i++) { + const struct btf_type *t = btf__type_by_id(btf, i); const char *name; if (btf_kind(t) != kind) @@ -449,6 +712,11 @@ __s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name, return -ENOENT; } +static bool btf_is_modifiable(const struct btf *btf) +{ + return (void *)btf->hdr != btf->raw_data; +} + void btf__free(struct btf *btf) { if (IS_ERR_OR_NULL(btf)) @@ -457,12 +725,75 @@ void btf__free(struct btf *btf) if (btf->fd >= 0) close(btf->fd); - free(btf->data); - free(btf->types); + if (btf_is_modifiable(btf)) { + /* if BTF was modified after loading, it will have a split + * in-memory representation for header, types, and strings + * sections, so we need to free all of them individually. It + * might still have a cached contiguous raw data present, + * which will be unconditionally freed below. + */ + free(btf->hdr); + free(btf->types_data); + free(btf->strs_data); + } + free(btf->raw_data); + free(btf->raw_data_swapped); + free(btf->type_offs); free(btf); } -struct btf *btf__new(const void *data, __u32 size) +static struct btf *btf_new_empty(struct btf *base_btf) +{ + struct btf *btf; + + btf = calloc(1, sizeof(*btf)); + if (!btf) + return ERR_PTR(-ENOMEM); + + btf->nr_types = 0; + btf->start_id = 1; + btf->start_str_off = 0; + btf->fd = -1; + btf->ptr_sz = sizeof(void *); + btf->swapped_endian = false; + + if (base_btf) { + btf->base_btf = base_btf; + btf->start_id = btf__get_nr_types(base_btf) + 1; + btf->start_str_off = base_btf->hdr->str_len; + } + + /* +1 for empty string at offset 0 */ + btf->raw_size = sizeof(struct btf_header) + (base_btf ? 0 : 1); + btf->raw_data = calloc(1, btf->raw_size); + if (!btf->raw_data) { + free(btf); + return ERR_PTR(-ENOMEM); + } + + btf->hdr = btf->raw_data; + btf->hdr->hdr_len = sizeof(struct btf_header); + btf->hdr->magic = BTF_MAGIC; + btf->hdr->version = BTF_VERSION; + + btf->types_data = btf->raw_data + btf->hdr->hdr_len; + btf->strs_data = btf->raw_data + btf->hdr->hdr_len; + btf->hdr->str_len = base_btf ? 0 : 1; /* empty string at offset 0 */ + + return btf; +} + +struct btf *btf__new_empty(void) +{ + return btf_new_empty(NULL); +} + +struct btf *btf__new_empty_split(struct btf *base_btf) +{ + return btf_new_empty(base_btf); +} + +static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf) { struct btf *btf; int err; @@ -471,26 +802,38 @@ struct btf *btf__new(const void *data, __u32 size) if (!btf) return ERR_PTR(-ENOMEM); - btf->fd = -1; + btf->nr_types = 0; + btf->start_id = 1; + btf->start_str_off = 0; + + if (base_btf) { + btf->base_btf = base_btf; + btf->start_id = btf__get_nr_types(base_btf) + 1; + btf->start_str_off = base_btf->hdr->str_len; + } - btf->data = malloc(size); - if (!btf->data) { + btf->raw_data = malloc(size); + if (!btf->raw_data) { err = -ENOMEM; goto done; } + memcpy(btf->raw_data, data, size); + btf->raw_size = size; - memcpy(btf->data, data, size); - btf->data_size = size; - + btf->hdr = btf->raw_data; err = btf_parse_hdr(btf); if (err) goto done; + btf->strs_data = btf->raw_data + btf->hdr->hdr_len + btf->hdr->str_off; + btf->types_data = btf->raw_data + btf->hdr->hdr_len + btf->hdr->type_off; + err = btf_parse_str_sec(btf); + err = err ?: btf_parse_type_sec(btf); if (err) goto done; - err = btf_parse_type_sec(btf); + btf->fd = -1; done: if (err) { @@ -501,18 +844,13 @@ done: return btf; } -static bool btf_check_endianness(const GElf_Ehdr *ehdr) +struct btf *btf__new(const void *data, __u32 size) { -#if __BYTE_ORDER == __LITTLE_ENDIAN - return ehdr->e_ident[EI_DATA] == ELFDATA2LSB; -#elif __BYTE_ORDER == __BIG_ENDIAN - return ehdr->e_ident[EI_DATA] == ELFDATA2MSB; -#else -# error "Unrecognized __BYTE_ORDER__" -#endif + return btf_new(data, size, NULL); } -struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext) +static struct btf *btf_parse_elf(const char *path, struct btf *base_btf, + struct btf_ext **btf_ext) { Elf_Data *btf_data = NULL, *btf_ext_data = NULL; int err = 0, fd = -1, idx = 0; @@ -520,6 +858,7 @@ struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext) Elf_Scn *scn = NULL; Elf *elf = NULL; GElf_Ehdr ehdr; + size_t shstrndx; if (elf_version(EV_CURRENT) == EV_NONE) { pr_warn("failed to init libelf for %s\n", path); @@ -544,11 +883,14 @@ struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext) pr_warn("failed to get EHDR from %s\n", path); goto done; } - if (!btf_check_endianness(&ehdr)) { - pr_warn("non-native ELF endianness is not supported\n"); + + if (elf_getshdrstrndx(elf, &shstrndx)) { + pr_warn("failed to get section names section index for %s\n", + path); goto done; } - if (!elf_rawdata(elf_getscn(elf, ehdr.e_shstrndx), NULL)) { + + if (!elf_rawdata(elf_getscn(elf, shstrndx), NULL)) { pr_warn("failed to get e_shstrndx from %s\n", path); goto done; } @@ -563,7 +905,7 @@ struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext) idx, path); goto done; } - name = elf_strptr(elf, ehdr.e_shstrndx, sh.sh_name); + name = elf_strptr(elf, shstrndx, sh.sh_name); if (!name) { pr_warn("failed to get section(%d) name from %s\n", idx, path); @@ -594,7 +936,7 @@ struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext) err = -ENOENT; goto done; } - btf = btf__new(btf_data->d_buf, btf_data->d_size); + btf = btf_new(btf_data->d_buf, btf_data->d_size, base_btf); if (IS_ERR(btf)) goto done; @@ -639,7 +981,17 @@ done: return btf; } -struct btf *btf__parse_raw(const char *path) +struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext) +{ + return btf_parse_elf(path, NULL, btf_ext); +} + +struct btf *btf__parse_elf_split(const char *path, struct btf *base_btf) +{ + return btf_parse_elf(path, base_btf, NULL); +} + +static struct btf *btf_parse_raw(const char *path, struct btf *base_btf) { struct btf *btf = NULL; void *data = NULL; @@ -659,13 +1011,7 @@ struct btf *btf__parse_raw(const char *path) err = -EIO; goto err_out; } - if (magic == __bswap_16(BTF_MAGIC)) { - /* non-native endian raw BTF */ - pr_warn("non-native BTF endianness is not supported\n"); - err = -LIBBPF_ERRNO__ENDIAN; - goto err_out; - } - if (magic != BTF_MAGIC) { + if (magic != BTF_MAGIC && magic != bswap_16(BTF_MAGIC)) { /* definitely not a raw BTF */ err = -EPROTO; goto err_out; @@ -699,7 +1045,7 @@ struct btf *btf__parse_raw(const char *path) } /* finally parse BTF data */ - btf = btf__new(data, sz); + btf = btf_new(data, sz, base_btf); err_out: free(data); @@ -708,18 +1054,38 @@ err_out: return err ? ERR_PTR(err) : btf; } -struct btf *btf__parse(const char *path, struct btf_ext **btf_ext) +struct btf *btf__parse_raw(const char *path) +{ + return btf_parse_raw(path, NULL); +} + +struct btf *btf__parse_raw_split(const char *path, struct btf *base_btf) +{ + return btf_parse_raw(path, base_btf); +} + +static struct btf *btf_parse(const char *path, struct btf *base_btf, struct btf_ext **btf_ext) { struct btf *btf; if (btf_ext) *btf_ext = NULL; - btf = btf__parse_raw(path); + btf = btf_parse_raw(path, base_btf); if (!IS_ERR(btf) || PTR_ERR(btf) != -EPROTO) return btf; - return btf__parse_elf(path, btf_ext); + return btf_parse_elf(path, base_btf, btf_ext); +} + +struct btf *btf__parse(const char *path, struct btf_ext **btf_ext) +{ + return btf_parse(path, NULL, btf_ext); +} + +struct btf *btf__parse_split(const char *path, struct btf *base_btf) +{ + return btf_parse(path, base_btf, NULL); } static int compare_vsi_off(const void *_a, const void *_b) @@ -798,7 +1164,7 @@ int btf__finalize_data(struct bpf_object *obj, struct btf *btf) __u32 i; for (i = 1; i <= btf->nr_types; i++) { - struct btf_type *t = btf->types[i]; + struct btf_type *t = btf_type_by_id(btf, i); /* Loader needs to fix up some of the things compiler * couldn't get its hands on while emitting BTF. This @@ -815,10 +1181,13 @@ int btf__finalize_data(struct bpf_object *obj, struct btf *btf) return err; } +static void *btf_get_raw_data(const struct btf *btf, __u32 *size, bool swap_endian); + int btf__load(struct btf *btf) { - __u32 log_buf_size = 0; + __u32 log_buf_size = 0, raw_size; char *log_buf = NULL; + void *raw_data; int err = 0; if (btf->fd >= 0) @@ -833,8 +1202,16 @@ retry_load: *log_buf = 0; } - btf->fd = bpf_load_btf(btf->data, btf->data_size, - log_buf, log_buf_size, false); + raw_data = btf_get_raw_data(btf, &raw_size, false); + if (!raw_data) { + err = -ENOMEM; + goto done; + } + /* cache native raw data representation */ + btf->raw_size = raw_size; + btf->raw_data = raw_data; + + btf->fd = bpf_load_btf(raw_data, raw_size, log_buf, log_buf_size, false); if (btf->fd < 0) { if (!log_buf || errno == ENOSPC) { log_buf_size = max((__u32)BPF_LOG_BUF_SIZE, @@ -865,49 +1242,111 @@ void btf__set_fd(struct btf *btf, int fd) btf->fd = fd; } -const void *btf__get_raw_data(const struct btf *btf, __u32 *size) +static void *btf_get_raw_data(const struct btf *btf, __u32 *size, bool swap_endian) { - *size = btf->data_size; - return btf->data; + struct btf_header *hdr = btf->hdr; + struct btf_type *t; + void *data, *p; + __u32 data_sz; + int i; + + data = swap_endian ? btf->raw_data_swapped : btf->raw_data; + if (data) { + *size = btf->raw_size; + return data; + } + + data_sz = hdr->hdr_len + hdr->type_len + hdr->str_len; + data = calloc(1, data_sz); + if (!data) + return NULL; + p = data; + + memcpy(p, hdr, hdr->hdr_len); + if (swap_endian) + btf_bswap_hdr(p); + p += hdr->hdr_len; + + memcpy(p, btf->types_data, hdr->type_len); + if (swap_endian) { + for (i = 0; i < btf->nr_types; i++) { + t = p + btf->type_offs[i]; + /* btf_bswap_type_rest() relies on native t->info, so + * we swap base type info after we swapped all the + * additional information + */ + if (btf_bswap_type_rest(t)) + goto err_out; + btf_bswap_type_base(t); + } + } + p += hdr->type_len; + + memcpy(p, btf->strs_data, hdr->str_len); + p += hdr->str_len; + + *size = data_sz; + return data; +err_out: + free(data); + return NULL; } -const char *btf__name_by_offset(const struct btf *btf, __u32 offset) +const void *btf__get_raw_data(const struct btf *btf_ro, __u32 *size) { - if (offset < btf->hdr->str_len) - return &btf->strings[offset]; + struct btf *btf = (struct btf *)btf_ro; + __u32 data_sz; + void *data; + + data = btf_get_raw_data(btf, &data_sz, btf->swapped_endian); + if (!data) + return NULL; + + btf->raw_size = data_sz; + if (btf->swapped_endian) + btf->raw_data_swapped = data; + else + btf->raw_data = data; + *size = data_sz; + return data; +} + +const char *btf__str_by_offset(const struct btf *btf, __u32 offset) +{ + if (offset < btf->start_str_off) + return btf__str_by_offset(btf->base_btf, offset); + else if (offset - btf->start_str_off < btf->hdr->str_len) + return btf->strs_data + (offset - btf->start_str_off); else return NULL; } -int btf__get_from_id(__u32 id, struct btf **btf) +const char *btf__name_by_offset(const struct btf *btf, __u32 offset) +{ + return btf__str_by_offset(btf, offset); +} + +struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf) { - struct bpf_btf_info btf_info = { 0 }; + struct bpf_btf_info btf_info; __u32 len = sizeof(btf_info); __u32 last_size; - int btf_fd; + struct btf *btf; void *ptr; int err; - err = 0; - *btf = NULL; - btf_fd = bpf_btf_get_fd_by_id(id); - if (btf_fd < 0) - return 0; - /* we won't know btf_size until we call bpf_obj_get_info_by_fd(). so * let's start with a sane default - 4KiB here - and resize it only if * bpf_obj_get_info_by_fd() needs a bigger buffer. */ - btf_info.btf_size = 4096; - last_size = btf_info.btf_size; + last_size = 4096; ptr = malloc(last_size); - if (!ptr) { - err = -ENOMEM; - goto exit_free; - } + if (!ptr) + return ERR_PTR(-ENOMEM); - memset(ptr, 0, last_size); + memset(&btf_info, 0, sizeof(btf_info)); btf_info.btf = ptr_to_u64(ptr); + btf_info.btf_size = last_size; err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len); if (!err && btf_info.btf_size > last_size) { @@ -916,31 +1355,48 @@ int btf__get_from_id(__u32 id, struct btf **btf) last_size = btf_info.btf_size; temp_ptr = realloc(ptr, last_size); if (!temp_ptr) { - err = -ENOMEM; + btf = ERR_PTR(-ENOMEM); goto exit_free; } ptr = temp_ptr; - memset(ptr, 0, last_size); + + len = sizeof(btf_info); + memset(&btf_info, 0, sizeof(btf_info)); btf_info.btf = ptr_to_u64(ptr); + btf_info.btf_size = last_size; + err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len); } if (err || btf_info.btf_size > last_size) { - err = errno; + btf = err ? ERR_PTR(-errno) : ERR_PTR(-E2BIG); goto exit_free; } - *btf = btf__new((__u8 *)(long)btf_info.btf, btf_info.btf_size); - if (IS_ERR(*btf)) { - err = PTR_ERR(*btf); - *btf = NULL; - } + btf = btf_new(ptr, btf_info.btf_size, base_btf); exit_free: - close(btf_fd); free(ptr); + return btf; +} - return err; +int btf__get_from_id(__u32 id, struct btf **btf) +{ + struct btf *res; + int btf_fd; + + *btf = NULL; + btf_fd = bpf_btf_get_fd_by_id(id); + if (btf_fd < 0) + return -errno; + + res = btf_get_from_fd(btf_fd, NULL); + close(btf_fd); + if (IS_ERR(res)) + return PTR_ERR(res); + + *btf = res; + return 0; } int btf__get_map_kv_tids(const struct btf *btf, const char *map_name, @@ -1014,6 +1470,957 @@ int btf__get_map_kv_tids(const struct btf *btf, const char *map_name, return 0; } +static size_t strs_hash_fn(const void *key, void *ctx) +{ + const struct btf *btf = ctx; + const char *strs = *btf->strs_data_ptr; + const char *str = strs + (long)key; + + return str_hash(str); +} + +static bool strs_hash_equal_fn(const void *key1, const void *key2, void *ctx) +{ + const struct btf *btf = ctx; + const char *strs = *btf->strs_data_ptr; + const char *str1 = strs + (long)key1; + const char *str2 = strs + (long)key2; + + return strcmp(str1, str2) == 0; +} + +static void btf_invalidate_raw_data(struct btf *btf) +{ + if (btf->raw_data) { + free(btf->raw_data); + btf->raw_data = NULL; + } + if (btf->raw_data_swapped) { + free(btf->raw_data_swapped); + btf->raw_data_swapped = NULL; + } +} + +/* Ensure BTF is ready to be modified (by splitting into a three memory + * regions for header, types, and strings). Also invalidate cached + * raw_data, if any. + */ +static int btf_ensure_modifiable(struct btf *btf) +{ + void *hdr, *types, *strs, *strs_end, *s; + struct hashmap *hash = NULL; + long off; + int err; + + if (btf_is_modifiable(btf)) { + /* any BTF modification invalidates raw_data */ + btf_invalidate_raw_data(btf); + return 0; + } + + /* split raw data into three memory regions */ + hdr = malloc(btf->hdr->hdr_len); + types = malloc(btf->hdr->type_len); + strs = malloc(btf->hdr->str_len); + if (!hdr || !types || !strs) + goto err_out; + + memcpy(hdr, btf->hdr, btf->hdr->hdr_len); + memcpy(types, btf->types_data, btf->hdr->type_len); + memcpy(strs, btf->strs_data, btf->hdr->str_len); + + /* make hashmap below use btf->strs_data as a source of strings */ + btf->strs_data_ptr = &btf->strs_data; + + /* build lookup index for all strings */ + hash = hashmap__new(strs_hash_fn, strs_hash_equal_fn, btf); + if (IS_ERR(hash)) { + err = PTR_ERR(hash); + hash = NULL; + goto err_out; + } + + strs_end = strs + btf->hdr->str_len; + for (off = 0, s = strs; s < strs_end; off += strlen(s) + 1, s = strs + off) { + /* hashmap__add() returns EEXIST if string with the same + * content already is in the hash map + */ + err = hashmap__add(hash, (void *)off, (void *)off); + if (err == -EEXIST) + continue; /* duplicate */ + if (err) + goto err_out; + } + + /* only when everything was successful, update internal state */ + btf->hdr = hdr; + btf->types_data = types; + btf->types_data_cap = btf->hdr->type_len; + btf->strs_data = strs; + btf->strs_data_cap = btf->hdr->str_len; + btf->strs_hash = hash; + /* if BTF was created from scratch, all strings are guaranteed to be + * unique and deduplicated + */ + if (btf->hdr->str_len == 0) + btf->strs_deduped = true; + if (!btf->base_btf && btf->hdr->str_len == 1) + btf->strs_deduped = true; + + /* invalidate raw_data representation */ + btf_invalidate_raw_data(btf); + + return 0; + +err_out: + hashmap__free(hash); + free(hdr); + free(types); + free(strs); + return -ENOMEM; +} + +static void *btf_add_str_mem(struct btf *btf, size_t add_sz) +{ + return btf_add_mem(&btf->strs_data, &btf->strs_data_cap, 1, + btf->hdr->str_len, BTF_MAX_STR_OFFSET, add_sz); +} + +/* Find an offset in BTF string section that corresponds to a given string *s*. + * Returns: + * - >0 offset into string section, if string is found; + * - -ENOENT, if string is not in the string section; + * - <0, on any other error. + */ +int btf__find_str(struct btf *btf, const char *s) +{ + long old_off, new_off, len; + void *p; + + if (btf->base_btf) { + int ret; + + ret = btf__find_str(btf->base_btf, s); + if (ret != -ENOENT) + return ret; + } + + /* BTF needs to be in a modifiable state to build string lookup index */ + if (btf_ensure_modifiable(btf)) + return -ENOMEM; + + /* see btf__add_str() for why we do this */ + len = strlen(s) + 1; + p = btf_add_str_mem(btf, len); + if (!p) + return -ENOMEM; + + new_off = btf->hdr->str_len; + memcpy(p, s, len); + + if (hashmap__find(btf->strs_hash, (void *)new_off, (void **)&old_off)) + return btf->start_str_off + old_off; + + return -ENOENT; +} + +/* Add a string s to the BTF string section. + * Returns: + * - > 0 offset into string section, on success; + * - < 0, on error. + */ +int btf__add_str(struct btf *btf, const char *s) +{ + long old_off, new_off, len; + void *p; + int err; + + if (btf->base_btf) { + int ret; + + ret = btf__find_str(btf->base_btf, s); + if (ret != -ENOENT) + return ret; + } + + if (btf_ensure_modifiable(btf)) + return -ENOMEM; + + /* Hashmap keys are always offsets within btf->strs_data, so to even + * look up some string from the "outside", we need to first append it + * at the end, so that it can be addressed with an offset. Luckily, + * until btf->hdr->str_len is incremented, that string is just a piece + * of garbage for the rest of BTF code, so no harm, no foul. On the + * other hand, if the string is unique, it's already appended and + * ready to be used, only a simple btf->hdr->str_len increment away. + */ + len = strlen(s) + 1; + p = btf_add_str_mem(btf, len); + if (!p) + return -ENOMEM; + + new_off = btf->hdr->str_len; + memcpy(p, s, len); + + /* Now attempt to add the string, but only if the string with the same + * contents doesn't exist already (HASHMAP_ADD strategy). If such + * string exists, we'll get its offset in old_off (that's old_key). + */ + err = hashmap__insert(btf->strs_hash, (void *)new_off, (void *)new_off, + HASHMAP_ADD, (const void **)&old_off, NULL); + if (err == -EEXIST) + return btf->start_str_off + old_off; /* duplicated string, return existing offset */ + if (err) + return err; + + btf->hdr->str_len += len; /* new unique string, adjust data length */ + return btf->start_str_off + new_off; +} + +static void *btf_add_type_mem(struct btf *btf, size_t add_sz) +{ + return btf_add_mem(&btf->types_data, &btf->types_data_cap, 1, + btf->hdr->type_len, UINT_MAX, add_sz); +} + +static __u32 btf_type_info(int kind, int vlen, int kflag) +{ + return (kflag << 31) | (kind << 24) | vlen; +} + +static void btf_type_inc_vlen(struct btf_type *t) +{ + t->info = btf_type_info(btf_kind(t), btf_vlen(t) + 1, btf_kflag(t)); +} + +static int btf_commit_type(struct btf *btf, int data_sz) +{ + int err; + + err = btf_add_type_idx_entry(btf, btf->hdr->type_len); + if (err) + return err; + + btf->hdr->type_len += data_sz; + btf->hdr->str_off += data_sz; + btf->nr_types++; + return btf->start_id + btf->nr_types - 1; +} + +/* + * Append new BTF_KIND_INT type with: + * - *name* - non-empty, non-NULL type name; + * - *sz* - power-of-2 (1, 2, 4, ..) size of the type, in bytes; + * - encoding is a combination of BTF_INT_SIGNED, BTF_INT_CHAR, BTF_INT_BOOL. + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_int(struct btf *btf, const char *name, size_t byte_sz, int encoding) +{ + struct btf_type *t; + int sz, name_off; + + /* non-empty name */ + if (!name || !name[0]) + return -EINVAL; + /* byte_sz must be power of 2 */ + if (!byte_sz || (byte_sz & (byte_sz - 1)) || byte_sz > 16) + return -EINVAL; + if (encoding & ~(BTF_INT_SIGNED | BTF_INT_CHAR | BTF_INT_BOOL)) + return -EINVAL; + + /* deconstruct BTF, if necessary, and invalidate raw_data */ + if (btf_ensure_modifiable(btf)) + return -ENOMEM; + + sz = sizeof(struct btf_type) + sizeof(int); + t = btf_add_type_mem(btf, sz); + if (!t) + return -ENOMEM; + + /* if something goes wrong later, we might end up with an extra string, + * but that shouldn't be a problem, because BTF can't be constructed + * completely anyway and will most probably be just discarded + */ + name_off = btf__add_str(btf, name); + if (name_off < 0) + return name_off; + + t->name_off = name_off; + t->info = btf_type_info(BTF_KIND_INT, 0, 0); + t->size = byte_sz; + /* set INT info, we don't allow setting legacy bit offset/size */ + *(__u32 *)(t + 1) = (encoding << 24) | (byte_sz * 8); + + return btf_commit_type(btf, sz); +} + +/* it's completely legal to append BTF types with type IDs pointing forward to + * types that haven't been appended yet, so we only make sure that id looks + * sane, we can't guarantee that ID will always be valid + */ +static int validate_type_id(int id) +{ + if (id < 0 || id > BTF_MAX_NR_TYPES) + return -EINVAL; + return 0; +} + +/* generic append function for PTR, TYPEDEF, CONST/VOLATILE/RESTRICT */ +static int btf_add_ref_kind(struct btf *btf, int kind, const char *name, int ref_type_id) +{ + struct btf_type *t; + int sz, name_off = 0; + + if (validate_type_id(ref_type_id)) + return -EINVAL; + + if (btf_ensure_modifiable(btf)) + return -ENOMEM; + + sz = sizeof(struct btf_type); + t = btf_add_type_mem(btf, sz); + if (!t) + return -ENOMEM; + + if (name && name[0]) { + name_off = btf__add_str(btf, name); + if (name_off < 0) + return name_off; + } + + t->name_off = name_off; + t->info = btf_type_info(kind, 0, 0); + t->type = ref_type_id; + + return btf_commit_type(btf, sz); +} + +/* + * Append new BTF_KIND_PTR type with: + * - *ref_type_id* - referenced type ID, it might not exist yet; + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_ptr(struct btf *btf, int ref_type_id) +{ + return btf_add_ref_kind(btf, BTF_KIND_PTR, NULL, ref_type_id); +} + +/* + * Append new BTF_KIND_ARRAY type with: + * - *index_type_id* - type ID of the type describing array index; + * - *elem_type_id* - type ID of the type describing array element; + * - *nr_elems* - the size of the array; + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_array(struct btf *btf, int index_type_id, int elem_type_id, __u32 nr_elems) +{ + struct btf_type *t; + struct btf_array *a; + int sz; + + if (validate_type_id(index_type_id) || validate_type_id(elem_type_id)) + return -EINVAL; + + if (btf_ensure_modifiable(btf)) + return -ENOMEM; + + sz = sizeof(struct btf_type) + sizeof(struct btf_array); + t = btf_add_type_mem(btf, sz); + if (!t) + return -ENOMEM; + + t->name_off = 0; + t->info = btf_type_info(BTF_KIND_ARRAY, 0, 0); + t->size = 0; + + a = btf_array(t); + a->type = elem_type_id; + a->index_type = index_type_id; + a->nelems = nr_elems; + + return btf_commit_type(btf, sz); +} + +/* generic STRUCT/UNION append function */ +static int btf_add_composite(struct btf *btf, int kind, const char *name, __u32 bytes_sz) +{ + struct btf_type *t; + int sz, name_off = 0; + + if (btf_ensure_modifiable(btf)) + return -ENOMEM; + + sz = sizeof(struct btf_type); + t = btf_add_type_mem(btf, sz); + if (!t) + return -ENOMEM; + + if (name && name[0]) { + name_off = btf__add_str(btf, name); + if (name_off < 0) + return name_off; + } + + /* start out with vlen=0 and no kflag; this will be adjusted when + * adding each member + */ + t->name_off = name_off; + t->info = btf_type_info(kind, 0, 0); + t->size = bytes_sz; + + return btf_commit_type(btf, sz); +} + +/* + * Append new BTF_KIND_STRUCT type with: + * - *name* - name of the struct, can be NULL or empty for anonymous structs; + * - *byte_sz* - size of the struct, in bytes; + * + * Struct initially has no fields in it. Fields can be added by + * btf__add_field() right after btf__add_struct() succeeds. + * + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_struct(struct btf *btf, const char *name, __u32 byte_sz) +{ + return btf_add_composite(btf, BTF_KIND_STRUCT, name, byte_sz); +} + +/* + * Append new BTF_KIND_UNION type with: + * - *name* - name of the union, can be NULL or empty for anonymous union; + * - *byte_sz* - size of the union, in bytes; + * + * Union initially has no fields in it. Fields can be added by + * btf__add_field() right after btf__add_union() succeeds. All fields + * should have *bit_offset* of 0. + * + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_union(struct btf *btf, const char *name, __u32 byte_sz) +{ + return btf_add_composite(btf, BTF_KIND_UNION, name, byte_sz); +} + +static struct btf_type *btf_last_type(struct btf *btf) +{ + return btf_type_by_id(btf, btf__get_nr_types(btf)); +} + +/* + * Append new field for the current STRUCT/UNION type with: + * - *name* - name of the field, can be NULL or empty for anonymous field; + * - *type_id* - type ID for the type describing field type; + * - *bit_offset* - bit offset of the start of the field within struct/union; + * - *bit_size* - bit size of a bitfield, 0 for non-bitfield fields; + * Returns: + * - 0, on success; + * - <0, on error. + */ +int btf__add_field(struct btf *btf, const char *name, int type_id, + __u32 bit_offset, __u32 bit_size) +{ + struct btf_type *t; + struct btf_member *m; + bool is_bitfield; + int sz, name_off = 0; + + /* last type should be union/struct */ + if (btf->nr_types == 0) + return -EINVAL; + t = btf_last_type(btf); + if (!btf_is_composite(t)) + return -EINVAL; + + if (validate_type_id(type_id)) + return -EINVAL; + /* best-effort bit field offset/size enforcement */ + is_bitfield = bit_size || (bit_offset % 8 != 0); + if (is_bitfield && (bit_size == 0 || bit_size > 255 || bit_offset > 0xffffff)) + return -EINVAL; + + /* only offset 0 is allowed for unions */ + if (btf_is_union(t) && bit_offset) + return -EINVAL; + + /* decompose and invalidate raw data */ + if (btf_ensure_modifiable(btf)) + return -ENOMEM; + + sz = sizeof(struct btf_member); + m = btf_add_type_mem(btf, sz); + if (!m) + return -ENOMEM; + + if (name && name[0]) { + name_off = btf__add_str(btf, name); + if (name_off < 0) + return name_off; + } + + m->name_off = name_off; + m->type = type_id; + m->offset = bit_offset | (bit_size << 24); + + /* btf_add_type_mem can invalidate t pointer */ + t = btf_last_type(btf); + /* update parent type's vlen and kflag */ + t->info = btf_type_info(btf_kind(t), btf_vlen(t) + 1, is_bitfield || btf_kflag(t)); + + btf->hdr->type_len += sz; + btf->hdr->str_off += sz; + return 0; +} + +/* + * Append new BTF_KIND_ENUM type with: + * - *name* - name of the enum, can be NULL or empty for anonymous enums; + * - *byte_sz* - size of the enum, in bytes. + * + * Enum initially has no enum values in it (and corresponds to enum forward + * declaration). Enumerator values can be added by btf__add_enum_value() + * immediately after btf__add_enum() succeeds. + * + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_enum(struct btf *btf, const char *name, __u32 byte_sz) +{ + struct btf_type *t; + int sz, name_off = 0; + + /* byte_sz must be power of 2 */ + if (!byte_sz || (byte_sz & (byte_sz - 1)) || byte_sz > 8) + return -EINVAL; + + if (btf_ensure_modifiable(btf)) + return -ENOMEM; + + sz = sizeof(struct btf_type); + t = btf_add_type_mem(btf, sz); + if (!t) + return -ENOMEM; + + if (name && name[0]) { + name_off = btf__add_str(btf, name); + if (name_off < 0) + return name_off; + } + + /* start out with vlen=0; it will be adjusted when adding enum values */ + t->name_off = name_off; + t->info = btf_type_info(BTF_KIND_ENUM, 0, 0); + t->size = byte_sz; + + return btf_commit_type(btf, sz); +} + +/* + * Append new enum value for the current ENUM type with: + * - *name* - name of the enumerator value, can't be NULL or empty; + * - *value* - integer value corresponding to enum value *name*; + * Returns: + * - 0, on success; + * - <0, on error. + */ +int btf__add_enum_value(struct btf *btf, const char *name, __s64 value) +{ + struct btf_type *t; + struct btf_enum *v; + int sz, name_off; + + /* last type should be BTF_KIND_ENUM */ + if (btf->nr_types == 0) + return -EINVAL; + t = btf_last_type(btf); + if (!btf_is_enum(t)) + return -EINVAL; + + /* non-empty name */ + if (!name || !name[0]) + return -EINVAL; + if (value < INT_MIN || value > UINT_MAX) + return -E2BIG; + + /* decompose and invalidate raw data */ + if (btf_ensure_modifiable(btf)) + return -ENOMEM; + + sz = sizeof(struct btf_enum); + v = btf_add_type_mem(btf, sz); + if (!v) + return -ENOMEM; + + name_off = btf__add_str(btf, name); + if (name_off < 0) + return name_off; + + v->name_off = name_off; + v->val = value; + + /* update parent type's vlen */ + t = btf_last_type(btf); + btf_type_inc_vlen(t); + + btf->hdr->type_len += sz; + btf->hdr->str_off += sz; + return 0; +} + +/* + * Append new BTF_KIND_FWD type with: + * - *name*, non-empty/non-NULL name; + * - *fwd_kind*, kind of forward declaration, one of BTF_FWD_STRUCT, + * BTF_FWD_UNION, or BTF_FWD_ENUM; + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_fwd(struct btf *btf, const char *name, enum btf_fwd_kind fwd_kind) +{ + if (!name || !name[0]) + return -EINVAL; + + switch (fwd_kind) { + case BTF_FWD_STRUCT: + case BTF_FWD_UNION: { + struct btf_type *t; + int id; + + id = btf_add_ref_kind(btf, BTF_KIND_FWD, name, 0); + if (id <= 0) + return id; + t = btf_type_by_id(btf, id); + t->info = btf_type_info(BTF_KIND_FWD, 0, fwd_kind == BTF_FWD_UNION); + return id; + } + case BTF_FWD_ENUM: + /* enum forward in BTF currently is just an enum with no enum + * values; we also assume a standard 4-byte size for it + */ + return btf__add_enum(btf, name, sizeof(int)); + default: + return -EINVAL; + } +} + +/* + * Append new BTF_KING_TYPEDEF type with: + * - *name*, non-empty/non-NULL name; + * - *ref_type_id* - referenced type ID, it might not exist yet; + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_typedef(struct btf *btf, const char *name, int ref_type_id) +{ + if (!name || !name[0]) + return -EINVAL; + + return btf_add_ref_kind(btf, BTF_KIND_TYPEDEF, name, ref_type_id); +} + +/* + * Append new BTF_KIND_VOLATILE type with: + * - *ref_type_id* - referenced type ID, it might not exist yet; + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_volatile(struct btf *btf, int ref_type_id) +{ + return btf_add_ref_kind(btf, BTF_KIND_VOLATILE, NULL, ref_type_id); +} + +/* + * Append new BTF_KIND_CONST type with: + * - *ref_type_id* - referenced type ID, it might not exist yet; + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_const(struct btf *btf, int ref_type_id) +{ + return btf_add_ref_kind(btf, BTF_KIND_CONST, NULL, ref_type_id); +} + +/* + * Append new BTF_KIND_RESTRICT type with: + * - *ref_type_id* - referenced type ID, it might not exist yet; + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_restrict(struct btf *btf, int ref_type_id) +{ + return btf_add_ref_kind(btf, BTF_KIND_RESTRICT, NULL, ref_type_id); +} + +/* + * Append new BTF_KIND_FUNC type with: + * - *name*, non-empty/non-NULL name; + * - *proto_type_id* - FUNC_PROTO's type ID, it might not exist yet; + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_func(struct btf *btf, const char *name, + enum btf_func_linkage linkage, int proto_type_id) +{ + int id; + + if (!name || !name[0]) + return -EINVAL; + if (linkage != BTF_FUNC_STATIC && linkage != BTF_FUNC_GLOBAL && + linkage != BTF_FUNC_EXTERN) + return -EINVAL; + + id = btf_add_ref_kind(btf, BTF_KIND_FUNC, name, proto_type_id); + if (id > 0) { + struct btf_type *t = btf_type_by_id(btf, id); + + t->info = btf_type_info(BTF_KIND_FUNC, linkage, 0); + } + return id; +} + +/* + * Append new BTF_KIND_FUNC_PROTO with: + * - *ret_type_id* - type ID for return result of a function. + * + * Function prototype initially has no arguments, but they can be added by + * btf__add_func_param() one by one, immediately after + * btf__add_func_proto() succeeded. + * + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_func_proto(struct btf *btf, int ret_type_id) +{ + struct btf_type *t; + int sz; + + if (validate_type_id(ret_type_id)) + return -EINVAL; + + if (btf_ensure_modifiable(btf)) + return -ENOMEM; + + sz = sizeof(struct btf_type); + t = btf_add_type_mem(btf, sz); + if (!t) + return -ENOMEM; + + /* start out with vlen=0; this will be adjusted when adding enum + * values, if necessary + */ + t->name_off = 0; + t->info = btf_type_info(BTF_KIND_FUNC_PROTO, 0, 0); + t->type = ret_type_id; + + return btf_commit_type(btf, sz); +} + +/* + * Append new function parameter for current FUNC_PROTO type with: + * - *name* - parameter name, can be NULL or empty; + * - *type_id* - type ID describing the type of the parameter. + * Returns: + * - 0, on success; + * - <0, on error. + */ +int btf__add_func_param(struct btf *btf, const char *name, int type_id) +{ + struct btf_type *t; + struct btf_param *p; + int sz, name_off = 0; + + if (validate_type_id(type_id)) + return -EINVAL; + + /* last type should be BTF_KIND_FUNC_PROTO */ + if (btf->nr_types == 0) + return -EINVAL; + t = btf_last_type(btf); + if (!btf_is_func_proto(t)) + return -EINVAL; + + /* decompose and invalidate raw data */ + if (btf_ensure_modifiable(btf)) + return -ENOMEM; + + sz = sizeof(struct btf_param); + p = btf_add_type_mem(btf, sz); + if (!p) + return -ENOMEM; + + if (name && name[0]) { + name_off = btf__add_str(btf, name); + if (name_off < 0) + return name_off; + } + + p->name_off = name_off; + p->type = type_id; + + /* update parent type's vlen */ + t = btf_last_type(btf); + btf_type_inc_vlen(t); + + btf->hdr->type_len += sz; + btf->hdr->str_off += sz; + return 0; +} + +/* + * Append new BTF_KIND_VAR type with: + * - *name* - non-empty/non-NULL name; + * - *linkage* - variable linkage, one of BTF_VAR_STATIC, + * BTF_VAR_GLOBAL_ALLOCATED, or BTF_VAR_GLOBAL_EXTERN; + * - *type_id* - type ID of the type describing the type of the variable. + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_var(struct btf *btf, const char *name, int linkage, int type_id) +{ + struct btf_type *t; + struct btf_var *v; + int sz, name_off; + + /* non-empty name */ + if (!name || !name[0]) + return -EINVAL; + if (linkage != BTF_VAR_STATIC && linkage != BTF_VAR_GLOBAL_ALLOCATED && + linkage != BTF_VAR_GLOBAL_EXTERN) + return -EINVAL; + if (validate_type_id(type_id)) + return -EINVAL; + + /* deconstruct BTF, if necessary, and invalidate raw_data */ + if (btf_ensure_modifiable(btf)) + return -ENOMEM; + + sz = sizeof(struct btf_type) + sizeof(struct btf_var); + t = btf_add_type_mem(btf, sz); + if (!t) + return -ENOMEM; + + name_off = btf__add_str(btf, name); + if (name_off < 0) + return name_off; + + t->name_off = name_off; + t->info = btf_type_info(BTF_KIND_VAR, 0, 0); + t->type = type_id; + + v = btf_var(t); + v->linkage = linkage; + + return btf_commit_type(btf, sz); +} + +/* + * Append new BTF_KIND_DATASEC type with: + * - *name* - non-empty/non-NULL name; + * - *byte_sz* - data section size, in bytes. + * + * Data section is initially empty. Variables info can be added with + * btf__add_datasec_var_info() calls, after btf__add_datasec() succeeds. + * + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_datasec(struct btf *btf, const char *name, __u32 byte_sz) +{ + struct btf_type *t; + int sz, name_off; + + /* non-empty name */ + if (!name || !name[0]) + return -EINVAL; + + if (btf_ensure_modifiable(btf)) + return -ENOMEM; + + sz = sizeof(struct btf_type); + t = btf_add_type_mem(btf, sz); + if (!t) + return -ENOMEM; + + name_off = btf__add_str(btf, name); + if (name_off < 0) + return name_off; + + /* start with vlen=0, which will be update as var_secinfos are added */ + t->name_off = name_off; + t->info = btf_type_info(BTF_KIND_DATASEC, 0, 0); + t->size = byte_sz; + + return btf_commit_type(btf, sz); +} + +/* + * Append new data section variable information entry for current DATASEC type: + * - *var_type_id* - type ID, describing type of the variable; + * - *offset* - variable offset within data section, in bytes; + * - *byte_sz* - variable size, in bytes. + * + * Returns: + * - 0, on success; + * - <0, on error. + */ +int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __u32 byte_sz) +{ + struct btf_type *t; + struct btf_var_secinfo *v; + int sz; + + /* last type should be BTF_KIND_DATASEC */ + if (btf->nr_types == 0) + return -EINVAL; + t = btf_last_type(btf); + if (!btf_is_datasec(t)) + return -EINVAL; + + if (validate_type_id(var_type_id)) + return -EINVAL; + + /* decompose and invalidate raw data */ + if (btf_ensure_modifiable(btf)) + return -ENOMEM; + + sz = sizeof(struct btf_var_secinfo); + v = btf_add_type_mem(btf, sz); + if (!v) + return -ENOMEM; + + v->type = var_type_id; + v->offset = offset; + v->size = byte_sz; + + /* update parent type's vlen */ + t = btf_last_type(btf); + btf_type_inc_vlen(t); + + btf->hdr->type_len += sz; + btf->hdr->str_off += sz; + return 0; +} + struct btf_ext_sec_setup_param { __u32 off; __u32 len; @@ -1137,14 +2544,14 @@ static int btf_ext_setup_line_info(struct btf_ext *btf_ext) return btf_ext_setup_info(btf_ext, ¶m); } -static int btf_ext_setup_field_reloc(struct btf_ext *btf_ext) +static int btf_ext_setup_core_relos(struct btf_ext *btf_ext) { struct btf_ext_sec_setup_param param = { - .off = btf_ext->hdr->field_reloc_off, - .len = btf_ext->hdr->field_reloc_len, - .min_rec_size = sizeof(struct bpf_field_reloc), - .ext_info = &btf_ext->field_reloc_info, - .desc = "field_reloc", + .off = btf_ext->hdr->core_relo_off, + .len = btf_ext->hdr->core_relo_len, + .min_rec_size = sizeof(struct bpf_core_relo), + .ext_info = &btf_ext->core_relo_info, + .desc = "core_relo", }; return btf_ext_setup_info(btf_ext, ¶m); @@ -1160,7 +2567,10 @@ static int btf_ext_parse_hdr(__u8 *data, __u32 data_size) return -EINVAL; } - if (hdr->magic != BTF_MAGIC) { + if (hdr->magic == bswap_16(BTF_MAGIC)) { + pr_warn("BTF.ext in non-native endianness is not supported\n"); + return -ENOTSUP; + } else if (hdr->magic != BTF_MAGIC) { pr_debug("Invalid BTF.ext magic:%x\n", hdr->magic); return -EINVAL; } @@ -1223,10 +2633,9 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size) if (err) goto done; - if (btf_ext->hdr->hdr_len < - offsetofend(struct btf_ext_header, field_reloc_len)) + if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, core_relo_len)) goto done; - err = btf_ext_setup_field_reloc(btf_ext); + err = btf_ext_setup_core_relos(btf_ext); if (err) goto done; @@ -1326,6 +2735,7 @@ struct btf_dedup; static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext, const struct btf_dedup_opts *opts); static void btf_dedup_free(struct btf_dedup *d); +static int btf_dedup_prep(struct btf_dedup *d); static int btf_dedup_strings(struct btf_dedup *d); static int btf_dedup_prim_types(struct btf_dedup *d); static int btf_dedup_struct_types(struct btf_dedup *d); @@ -1481,6 +2891,14 @@ int btf__dedup(struct btf *btf, struct btf_ext *btf_ext, return -EINVAL; } + if (btf_ensure_modifiable(btf)) + return -ENOMEM; + + err = btf_dedup_prep(d); + if (err) { + pr_debug("btf_dedup_prep failed:%d\n", err); + goto done; + } err = btf_dedup_strings(d); if (err < 0) { pr_debug("btf_dedup_strings failed:%d\n", err); @@ -1543,21 +2961,20 @@ struct btf_dedup { __u32 *hypot_list; size_t hypot_cnt; size_t hypot_cap; + /* Whether hypothetical mapping, if successful, would need to adjust + * already canonicalized types (due to a new forward declaration to + * concrete type resolution). In such case, during split BTF dedup + * candidate type would still be considered as different, because base + * BTF is considered to be immutable. + */ + bool hypot_adjust_canon; /* Various option modifying behavior of algorithm */ struct btf_dedup_opts opts; -}; - -struct btf_str_ptr { - const char *str; - __u32 new_off; - bool used; -}; - -struct btf_str_ptrs { - struct btf_str_ptr *ptrs; - const char *data; - __u32 cnt; - __u32 cap; + /* temporary strings deduplication state */ + void *strs_data; + size_t strs_cap; + size_t strs_len; + struct hashmap* strs_hash; }; static long hash_combine(long h, long value) @@ -1581,7 +2998,7 @@ static int btf_dedup_hypot_map_add(struct btf_dedup *d, __u32 *new_list; d->hypot_cap += max((size_t)16, d->hypot_cap / 2); - new_list = realloc(d->hypot_list, sizeof(__u32) * d->hypot_cap); + new_list = libbpf_reallocarray(d->hypot_list, d->hypot_cap, sizeof(__u32)); if (!new_list) return -ENOMEM; d->hypot_list = new_list; @@ -1598,6 +3015,7 @@ static void btf_dedup_clear_hypot_map(struct btf_dedup *d) for (i = 0; i < d->hypot_cnt; i++) d->hypot_map[d->hypot_list[i]] = BTF_UNPROCESSED_ID; d->hypot_cnt = 0; + d->hypot_adjust_canon = false; } static void btf_dedup_free(struct btf_dedup *d) @@ -1637,7 +3055,7 @@ static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext, { struct btf_dedup *d = calloc(1, sizeof(struct btf_dedup)); hashmap_hash_fn hash_fn = btf_dedup_identity_hash_fn; - int i, err = 0; + int i, err = 0, type_cnt; if (!d) return ERR_PTR(-ENOMEM); @@ -1657,15 +3075,16 @@ static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext, goto done; } - d->map = malloc(sizeof(__u32) * (1 + btf->nr_types)); + type_cnt = btf__get_nr_types(btf) + 1; + d->map = malloc(sizeof(__u32) * type_cnt); if (!d->map) { err = -ENOMEM; goto done; } /* special BTF "void" type is made canonical immediately */ d->map[0] = 0; - for (i = 1; i <= btf->nr_types; i++) { - struct btf_type *t = d->btf->types[i]; + for (i = 1; i < type_cnt; i++) { + struct btf_type *t = btf_type_by_id(d->btf, i); /* VAR and DATASEC are never deduped and are self-canonical */ if (btf_is_var(t) || btf_is_datasec(t)) @@ -1674,12 +3093,12 @@ static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext, d->map[i] = BTF_UNPROCESSED_ID; } - d->hypot_map = malloc(sizeof(__u32) * (1 + btf->nr_types)); + d->hypot_map = malloc(sizeof(__u32) * type_cnt); if (!d->hypot_map) { err = -ENOMEM; goto done; } - for (i = 0; i <= btf->nr_types; i++) + for (i = 0; i < type_cnt; i++) d->hypot_map[i] = BTF_UNPROCESSED_ID; done: @@ -1703,8 +3122,8 @@ static int btf_for_each_str_off(struct btf_dedup *d, str_off_fn_t fn, void *ctx) int i, j, r, rec_size; struct btf_type *t; - for (i = 1; i <= d->btf->nr_types; i++) { - t = d->btf->types[i]; + for (i = 0; i < d->btf->nr_types; i++) { + t = btf_type_by_id(d->btf, d->btf->start_id + i); r = fn(&t->name_off, ctx); if (r) return r; @@ -1784,64 +3203,53 @@ static int btf_for_each_str_off(struct btf_dedup *d, str_off_fn_t fn, void *ctx) return 0; } -static int str_sort_by_content(const void *a1, const void *a2) -{ - const struct btf_str_ptr *p1 = a1; - const struct btf_str_ptr *p2 = a2; - - return strcmp(p1->str, p2->str); -} - -static int str_sort_by_offset(const void *a1, const void *a2) -{ - const struct btf_str_ptr *p1 = a1; - const struct btf_str_ptr *p2 = a2; - - if (p1->str != p2->str) - return p1->str < p2->str ? -1 : 1; - return 0; -} - -static int btf_dedup_str_ptr_cmp(const void *str_ptr, const void *pelem) +static int strs_dedup_remap_str_off(__u32 *str_off_ptr, void *ctx) { - const struct btf_str_ptr *p = pelem; - - if (str_ptr != p->str) - return (const char *)str_ptr < p->str ? -1 : 1; - return 0; -} - -static int btf_str_mark_as_used(__u32 *str_off_ptr, void *ctx) -{ - struct btf_str_ptrs *strs; - struct btf_str_ptr *s; + struct btf_dedup *d = ctx; + __u32 str_off = *str_off_ptr; + long old_off, new_off, len; + const char *s; + void *p; + int err; - if (*str_off_ptr == 0) + /* don't touch empty string or string in main BTF */ + if (str_off == 0 || str_off < d->btf->start_str_off) return 0; - strs = ctx; - s = bsearch(strs->data + *str_off_ptr, strs->ptrs, strs->cnt, - sizeof(struct btf_str_ptr), btf_dedup_str_ptr_cmp); - if (!s) - return -EINVAL; - s->used = true; - return 0; -} + s = btf__str_by_offset(d->btf, str_off); + if (d->btf->base_btf) { + err = btf__find_str(d->btf->base_btf, s); + if (err >= 0) { + *str_off_ptr = err; + return 0; + } + if (err != -ENOENT) + return err; + } -static int btf_str_remap_offset(__u32 *str_off_ptr, void *ctx) -{ - struct btf_str_ptrs *strs; - struct btf_str_ptr *s; + len = strlen(s) + 1; - if (*str_off_ptr == 0) - return 0; + new_off = d->strs_len; + p = btf_add_mem(&d->strs_data, &d->strs_cap, 1, new_off, BTF_MAX_STR_OFFSET, len); + if (!p) + return -ENOMEM; - strs = ctx; - s = bsearch(strs->data + *str_off_ptr, strs->ptrs, strs->cnt, - sizeof(struct btf_str_ptr), btf_dedup_str_ptr_cmp); - if (!s) - return -EINVAL; - *str_off_ptr = s->new_off; + memcpy(p, s, len); + + /* Now attempt to add the string, but only if the string with the same + * contents doesn't exist already (HASHMAP_ADD strategy). If such + * string exists, we'll get its offset in old_off (that's old_key). + */ + err = hashmap__insert(d->strs_hash, (void *)new_off, (void *)new_off, + HASHMAP_ADD, (const void **)&old_off, NULL); + if (err == -EEXIST) { + *str_off_ptr = d->btf->start_str_off + old_off; + } else if (err) { + return err; + } else { + *str_off_ptr = d->btf->start_str_off + new_off; + d->strs_len += len; + } return 0; } @@ -1858,116 +3266,71 @@ static int btf_str_remap_offset(__u32 *str_off_ptr, void *ctx) */ static int btf_dedup_strings(struct btf_dedup *d) { - const struct btf_header *hdr = d->btf->hdr; - char *start = (char *)d->btf->nohdr_data + hdr->str_off; - char *end = start + d->btf->hdr->str_len; - char *p = start, *tmp_strs = NULL; - struct btf_str_ptrs strs = { - .cnt = 0, - .cap = 0, - .ptrs = NULL, - .data = start, - }; - int i, j, err = 0, grp_idx; - bool grp_used; - - /* build index of all strings */ - while (p < end) { - if (strs.cnt + 1 > strs.cap) { - struct btf_str_ptr *new_ptrs; - - strs.cap += max(strs.cnt / 2, 16U); - new_ptrs = realloc(strs.ptrs, - sizeof(strs.ptrs[0]) * strs.cap); - if (!new_ptrs) { - err = -ENOMEM; - goto done; - } - strs.ptrs = new_ptrs; - } + char *s; + int err; - strs.ptrs[strs.cnt].str = p; - strs.ptrs[strs.cnt].used = false; + if (d->btf->strs_deduped) + return 0; - p += strlen(p) + 1; - strs.cnt++; - } + /* temporarily switch to use btf_dedup's strs_data for strings for hash + * functions; later we'll just transfer hashmap to struct btf as is, + * along the strs_data + */ + d->btf->strs_data_ptr = &d->strs_data; - /* temporary storage for deduplicated strings */ - tmp_strs = malloc(d->btf->hdr->str_len); - if (!tmp_strs) { - err = -ENOMEM; - goto done; + d->strs_hash = hashmap__new(strs_hash_fn, strs_hash_equal_fn, d->btf); + if (IS_ERR(d->strs_hash)) { + err = PTR_ERR(d->strs_hash); + d->strs_hash = NULL; + goto err_out; } - /* mark all used strings */ - strs.ptrs[0].used = true; - err = btf_for_each_str_off(d, btf_str_mark_as_used, &strs); - if (err) - goto done; - - /* sort strings by context, so that we can identify duplicates */ - qsort(strs.ptrs, strs.cnt, sizeof(strs.ptrs[0]), str_sort_by_content); - - /* - * iterate groups of equal strings and if any instance in a group was - * referenced, emit single instance and remember new offset - */ - p = tmp_strs; - grp_idx = 0; - grp_used = strs.ptrs[0].used; - /* iterate past end to avoid code duplication after loop */ - for (i = 1; i <= strs.cnt; i++) { - /* - * when i == strs.cnt, we want to skip string comparison and go - * straight to handling last group of strings (otherwise we'd - * need to handle last group after the loop w/ duplicated code) - */ - if (i < strs.cnt && - !strcmp(strs.ptrs[i].str, strs.ptrs[grp_idx].str)) { - grp_used = grp_used || strs.ptrs[i].used; - continue; - } + if (!d->btf->base_btf) { + s = btf_add_mem(&d->strs_data, &d->strs_cap, 1, d->strs_len, BTF_MAX_STR_OFFSET, 1); + if (!s) + return -ENOMEM; + /* initial empty string */ + s[0] = 0; + d->strs_len = 1; - /* - * this check would have been required after the loop to handle - * last group of strings, but due to <= condition in a loop - * we avoid that duplication + /* insert empty string; we won't be looking it up during strings + * dedup, but it's good to have it for generic BTF string lookups */ - if (grp_used) { - int new_off = p - tmp_strs; - __u32 len = strlen(strs.ptrs[grp_idx].str); - - memmove(p, strs.ptrs[grp_idx].str, len + 1); - for (j = grp_idx; j < i; j++) - strs.ptrs[j].new_off = new_off; - p += len + 1; - } - - if (i < strs.cnt) { - grp_idx = i; - grp_used = strs.ptrs[i].used; - } + err = hashmap__insert(d->strs_hash, (void *)0, (void *)0, + HASHMAP_ADD, NULL, NULL); + if (err) + goto err_out; } - /* replace original strings with deduped ones */ - d->btf->hdr->str_len = p - tmp_strs; - memmove(start, tmp_strs, d->btf->hdr->str_len); - end = start + d->btf->hdr->str_len; - - /* restore original order for further binary search lookups */ - qsort(strs.ptrs, strs.cnt, sizeof(strs.ptrs[0]), str_sort_by_offset); - /* remap string offsets */ - err = btf_for_each_str_off(d, btf_str_remap_offset, &strs); + err = btf_for_each_str_off(d, strs_dedup_remap_str_off, d); if (err) - goto done; + goto err_out; - d->btf->hdr->str_len = end - start; + /* replace BTF string data and hash with deduped ones */ + free(d->btf->strs_data); + hashmap__free(d->btf->strs_hash); + d->btf->strs_data = d->strs_data; + d->btf->strs_data_cap = d->strs_cap; + d->btf->hdr->str_len = d->strs_len; + d->btf->strs_hash = d->strs_hash; + /* now point strs_data_ptr back to btf->strs_data */ + d->btf->strs_data_ptr = &d->btf->strs_data; + + d->strs_data = d->strs_hash = NULL; + d->strs_len = d->strs_cap = 0; + d->btf->strs_deduped = true; + return 0; + +err_out: + free(d->strs_data); + hashmap__free(d->strs_hash); + d->strs_data = d->strs_hash = NULL; + d->strs_len = d->strs_cap = 0; + + /* restore strings pointer for existing d->btf->strs_hash back */ + d->btf->strs_data_ptr = &d->strs_data; -done: - free(tmp_strs); - free(strs.ptrs); return err; } @@ -2232,6 +3595,66 @@ static bool btf_compat_fnproto(struct btf_type *t1, struct btf_type *t2) return true; } +/* Prepare split BTF for deduplication by calculating hashes of base BTF's + * types and initializing the rest of the state (canonical type mapping) for + * the fixed base BTF part. + */ +static int btf_dedup_prep(struct btf_dedup *d) +{ + struct btf_type *t; + int type_id; + long h; + + if (!d->btf->base_btf) + return 0; + + for (type_id = 1; type_id < d->btf->start_id; type_id++) { + t = btf_type_by_id(d->btf, type_id); + + /* all base BTF types are self-canonical by definition */ + d->map[type_id] = type_id; + + switch (btf_kind(t)) { + case BTF_KIND_VAR: + case BTF_KIND_DATASEC: + /* VAR and DATASEC are never hash/deduplicated */ + continue; + case BTF_KIND_CONST: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_PTR: + case BTF_KIND_FWD: + case BTF_KIND_TYPEDEF: + case BTF_KIND_FUNC: + h = btf_hash_common(t); + break; + case BTF_KIND_INT: + h = btf_hash_int(t); + break; + case BTF_KIND_ENUM: + h = btf_hash_enum(t); + break; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + h = btf_hash_struct(t); + break; + case BTF_KIND_ARRAY: + h = btf_hash_array(t); + break; + case BTF_KIND_FUNC_PROTO: + h = btf_hash_fnproto(t); + break; + default: + pr_debug("unknown kind %d for type [%d]\n", btf_kind(t), type_id); + return -EINVAL; + } + if (btf_dedup_table_add(d, h, type_id)) + return -ENOMEM; + } + + return 0; +} + /* * Deduplicate primitive types, that can't reference other types, by calculating * their type signature hash and comparing them with any possible canonical @@ -2240,7 +3663,7 @@ static bool btf_compat_fnproto(struct btf_type *t1, struct btf_type *t2) */ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id) { - struct btf_type *t = d->btf->types[type_id]; + struct btf_type *t = btf_type_by_id(d->btf, type_id); struct hashmap_entry *hash_entry; struct btf_type *cand; /* if we don't find equivalent type, then we are canonical */ @@ -2267,7 +3690,7 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id) h = btf_hash_int(t); for_each_dedup_cand(d, hash_entry, h) { cand_id = (__u32)(long)hash_entry->value; - cand = d->btf->types[cand_id]; + cand = btf_type_by_id(d->btf, cand_id); if (btf_equal_int(t, cand)) { new_id = cand_id; break; @@ -2279,7 +3702,7 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id) h = btf_hash_enum(t); for_each_dedup_cand(d, hash_entry, h) { cand_id = (__u32)(long)hash_entry->value; - cand = d->btf->types[cand_id]; + cand = btf_type_by_id(d->btf, cand_id); if (btf_equal_enum(t, cand)) { new_id = cand_id; break; @@ -2302,7 +3725,7 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id) h = btf_hash_common(t); for_each_dedup_cand(d, hash_entry, h) { cand_id = (__u32)(long)hash_entry->value; - cand = d->btf->types[cand_id]; + cand = btf_type_by_id(d->btf, cand_id); if (btf_equal_common(t, cand)) { new_id = cand_id; break; @@ -2325,8 +3748,8 @@ static int btf_dedup_prim_types(struct btf_dedup *d) { int i, err; - for (i = 1; i <= d->btf->nr_types; i++) { - err = btf_dedup_prim_type(d, i); + for (i = 0; i < d->btf->nr_types; i++) { + err = btf_dedup_prim_type(d, d->btf->start_id + i); if (err) return err; } @@ -2361,13 +3784,13 @@ static uint32_t resolve_fwd_id(struct btf_dedup *d, uint32_t type_id) { __u32 orig_type_id = type_id; - if (!btf_is_fwd(d->btf->types[type_id])) + if (!btf_is_fwd(btf__type_by_id(d->btf, type_id))) return type_id; while (is_type_mapped(d, type_id) && d->map[type_id] != type_id) type_id = d->map[type_id]; - if (!btf_is_fwd(d->btf->types[type_id])) + if (!btf_is_fwd(btf__type_by_id(d->btf, type_id))) return type_id; return orig_type_id; @@ -2379,6 +3802,19 @@ static inline __u16 btf_fwd_kind(struct btf_type *t) return btf_kflag(t) ? BTF_KIND_UNION : BTF_KIND_STRUCT; } +/* Check if given two types are identical ARRAY definitions */ +static int btf_dedup_identical_arrays(struct btf_dedup *d, __u32 id1, __u32 id2) +{ + struct btf_type *t1, *t2; + + t1 = btf_type_by_id(d->btf, id1); + t2 = btf_type_by_id(d->btf, id2); + if (!btf_is_array(t1) || !btf_is_array(t2)) + return 0; + + return btf_equal_array(t1, t2); +} + /* * Check equivalence of BTF type graph formed by candidate struct/union (we'll * call it "candidate graph" in this description for brevity) to a type graph @@ -2489,14 +3925,24 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, canon_id = resolve_fwd_id(d, canon_id); hypot_type_id = d->hypot_map[canon_id]; - if (hypot_type_id <= BTF_MAX_NR_TYPES) - return hypot_type_id == cand_id; + if (hypot_type_id <= BTF_MAX_NR_TYPES) { + /* In some cases compiler will generate different DWARF types + * for *identical* array type definitions and use them for + * different fields within the *same* struct. This breaks type + * equivalence check, which makes an assumption that candidate + * types sub-graph has a consistent and deduped-by-compiler + * types within a single CU. So work around that by explicitly + * allowing identical array types here. + */ + return hypot_type_id == cand_id || + btf_dedup_identical_arrays(d, hypot_type_id, cand_id); + } if (btf_dedup_hypot_map_add(d, canon_id, cand_id)) return -ENOMEM; - cand_type = d->btf->types[cand_id]; - canon_type = d->btf->types[canon_id]; + cand_type = btf_type_by_id(d->btf, cand_id); + canon_type = btf_type_by_id(d->btf, canon_id); cand_kind = btf_kind(cand_type); canon_kind = btf_kind(canon_type); @@ -2516,6 +3962,9 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, } else { real_kind = cand_kind; fwd_kind = btf_fwd_kind(canon_type); + /* we'd need to resolve base FWD to STRUCT/UNION */ + if (fwd_kind == real_kind && canon_id < d->btf->start_id) + d->hypot_adjust_canon = true; } return fwd_kind == real_kind; } @@ -2553,8 +4002,7 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, return 0; cand_arr = btf_array(cand_type); canon_arr = btf_array(canon_type); - eq = btf_dedup_is_equiv(d, - cand_arr->index_type, canon_arr->index_type); + eq = btf_dedup_is_equiv(d, cand_arr->index_type, canon_arr->index_type); if (eq <= 0) return eq; return btf_dedup_is_equiv(d, cand_arr->type, canon_arr->type); @@ -2637,18 +4085,18 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, */ static void btf_dedup_merge_hypot_map(struct btf_dedup *d) { - __u32 cand_type_id, targ_type_id; + __u32 canon_type_id, targ_type_id; __u16 t_kind, c_kind; __u32 t_id, c_id; int i; for (i = 0; i < d->hypot_cnt; i++) { - cand_type_id = d->hypot_list[i]; - targ_type_id = d->hypot_map[cand_type_id]; + canon_type_id = d->hypot_list[i]; + targ_type_id = d->hypot_map[canon_type_id]; t_id = resolve_type_id(d, targ_type_id); - c_id = resolve_type_id(d, cand_type_id); - t_kind = btf_kind(d->btf->types[t_id]); - c_kind = btf_kind(d->btf->types[c_id]); + c_id = resolve_type_id(d, canon_type_id); + t_kind = btf_kind(btf__type_by_id(d->btf, t_id)); + c_kind = btf_kind(btf__type_by_id(d->btf, c_id)); /* * Resolve FWD into STRUCT/UNION. * It's ok to resolve FWD into STRUCT/UNION that's not yet @@ -2661,9 +4109,26 @@ static void btf_dedup_merge_hypot_map(struct btf_dedup *d) * stability is not a requirement for STRUCT/UNION equivalence * checks, though. */ + + /* if it's the split BTF case, we still need to point base FWD + * to STRUCT/UNION in a split BTF, because FWDs from split BTF + * will be resolved against base FWD. If we don't point base + * canonical FWD to the resolved STRUCT/UNION, then all the + * FWDs in split BTF won't be correctly resolved to a proper + * STRUCT/UNION. + */ if (t_kind != BTF_KIND_FWD && c_kind == BTF_KIND_FWD) d->map[c_id] = t_id; - else if (t_kind == BTF_KIND_FWD && c_kind != BTF_KIND_FWD) + + /* if graph equivalence determined that we'd need to adjust + * base canonical types, then we need to only point base FWDs + * to STRUCTs/UNIONs and do no more modifications. For all + * other purposes the type graphs were not equivalent. + */ + if (d->hypot_adjust_canon) + continue; + + if (t_kind == BTF_KIND_FWD && c_kind != BTF_KIND_FWD) d->map[t_id] = c_id; if ((t_kind == BTF_KIND_STRUCT || t_kind == BTF_KIND_UNION) && @@ -2716,7 +4181,7 @@ static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id) if (d->map[type_id] <= BTF_MAX_NR_TYPES) return 0; - t = d->btf->types[type_id]; + t = btf_type_by_id(d->btf, type_id); kind = btf_kind(t); if (kind != BTF_KIND_STRUCT && kind != BTF_KIND_UNION) @@ -2737,7 +4202,7 @@ static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id) * creating a loop (FWD -> STRUCT and STRUCT -> FWD), because * FWD and compatible STRUCT/UNION are considered equivalent. */ - cand_type = d->btf->types[cand_id]; + cand_type = btf_type_by_id(d->btf, cand_id); if (!btf_shallow_equal_struct(t, cand_type)) continue; @@ -2747,8 +4212,10 @@ static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id) return eq; if (!eq) continue; - new_id = cand_id; btf_dedup_merge_hypot_map(d); + if (d->hypot_adjust_canon) /* not really equivalent */ + continue; + new_id = cand_id; break; } @@ -2763,8 +4230,8 @@ static int btf_dedup_struct_types(struct btf_dedup *d) { int i, err; - for (i = 1; i <= d->btf->nr_types; i++) { - err = btf_dedup_struct_type(d, i); + for (i = 0; i < d->btf->nr_types; i++) { + err = btf_dedup_struct_type(d, d->btf->start_id + i); if (err) return err; } @@ -2809,7 +4276,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) if (d->map[type_id] <= BTF_MAX_NR_TYPES) return resolve_type_id(d, type_id); - t = d->btf->types[type_id]; + t = btf_type_by_id(d->btf, type_id); d->map[type_id] = BTF_IN_PROGRESS_ID; switch (btf_kind(t)) { @@ -2827,7 +4294,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) h = btf_hash_common(t); for_each_dedup_cand(d, hash_entry, h) { cand_id = (__u32)(long)hash_entry->value; - cand = d->btf->types[cand_id]; + cand = btf_type_by_id(d->btf, cand_id); if (btf_equal_common(t, cand)) { new_id = cand_id; break; @@ -2851,7 +4318,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) h = btf_hash_array(t); for_each_dedup_cand(d, hash_entry, h) { cand_id = (__u32)(long)hash_entry->value; - cand = d->btf->types[cand_id]; + cand = btf_type_by_id(d->btf, cand_id); if (btf_equal_array(t, cand)) { new_id = cand_id; break; @@ -2883,7 +4350,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) h = btf_hash_fnproto(t); for_each_dedup_cand(d, hash_entry, h) { cand_id = (__u32)(long)hash_entry->value; - cand = d->btf->types[cand_id]; + cand = btf_type_by_id(d->btf, cand_id); if (btf_equal_fnproto(t, cand)) { new_id = cand_id; break; @@ -2907,8 +4374,8 @@ static int btf_dedup_ref_types(struct btf_dedup *d) { int i, err; - for (i = 1; i <= d->btf->nr_types; i++) { - err = btf_dedup_ref_type(d, i); + for (i = 0; i < d->btf->nr_types; i++) { + err = btf_dedup_ref_type(d, d->btf->start_id + i); if (err < 0) return err; } @@ -2931,51 +4398,49 @@ static int btf_dedup_ref_types(struct btf_dedup *d) */ static int btf_dedup_compact_types(struct btf_dedup *d) { - struct btf_type **new_types; - __u32 next_type_id = 1; - char *types_start, *p; - int i, len; + __u32 *new_offs; + __u32 next_type_id = d->btf->start_id; + const struct btf_type *t; + void *p; + int i, id, len; /* we are going to reuse hypot_map to store compaction remapping */ d->hypot_map[0] = 0; - for (i = 1; i <= d->btf->nr_types; i++) - d->hypot_map[i] = BTF_UNPROCESSED_ID; + /* base BTF types are not renumbered */ + for (id = 1; id < d->btf->start_id; id++) + d->hypot_map[id] = id; + for (i = 0, id = d->btf->start_id; i < d->btf->nr_types; i++, id++) + d->hypot_map[id] = BTF_UNPROCESSED_ID; - types_start = d->btf->nohdr_data + d->btf->hdr->type_off; - p = types_start; + p = d->btf->types_data; - for (i = 1; i <= d->btf->nr_types; i++) { - if (d->map[i] != i) + for (i = 0, id = d->btf->start_id; i < d->btf->nr_types; i++, id++) { + if (d->map[id] != id) continue; - len = btf_type_size(d->btf->types[i]); + t = btf__type_by_id(d->btf, id); + len = btf_type_size(t); if (len < 0) return len; - memmove(p, d->btf->types[i], len); - d->hypot_map[i] = next_type_id; - d->btf->types[next_type_id] = (struct btf_type *)p; + memmove(p, t, len); + d->hypot_map[id] = next_type_id; + d->btf->type_offs[next_type_id - d->btf->start_id] = p - d->btf->types_data; p += len; next_type_id++; } /* shrink struct btf's internal types index and update btf_header */ - d->btf->nr_types = next_type_id - 1; - d->btf->types_size = d->btf->nr_types; - d->btf->hdr->type_len = p - types_start; - new_types = realloc(d->btf->types, - (1 + d->btf->nr_types) * sizeof(struct btf_type *)); - if (!new_types) + d->btf->nr_types = next_type_id - d->btf->start_id; + d->btf->type_offs_cap = d->btf->nr_types; + d->btf->hdr->type_len = p - d->btf->types_data; + new_offs = libbpf_reallocarray(d->btf->type_offs, d->btf->type_offs_cap, + sizeof(*new_offs)); + if (d->btf->type_offs_cap && !new_offs) return -ENOMEM; - d->btf->types = new_types; - - /* make sure string section follows type information without gaps */ - d->btf->hdr->str_off = p - (char *)d->btf->nohdr_data; - memmove(p, d->btf->strings, d->btf->hdr->str_len); - d->btf->strings = p; - p += d->btf->hdr->str_len; - - d->btf->data_size = p - (char *)d->btf->data; + d->btf->type_offs = new_offs; + d->btf->hdr->str_off = d->btf->hdr->type_len; + d->btf->raw_size = d->btf->hdr->hdr_len + d->btf->hdr->type_len + d->btf->hdr->str_len; return 0; } @@ -3008,7 +4473,7 @@ static int btf_dedup_remap_type_id(struct btf_dedup *d, __u32 type_id) */ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id) { - struct btf_type *t = d->btf->types[type_id]; + struct btf_type *t = btf_type_by_id(d->btf, type_id); int i, r; switch (btf_kind(t)) { @@ -3103,8 +4568,8 @@ static int btf_dedup_remap_types(struct btf_dedup *d) { int i, r; - for (i = 1; i <= d->btf->nr_types; i++) { - r = btf_dedup_remap_type(d, i); + for (i = 0; i < d->btf->nr_types; i++) { + r = btf_dedup_remap_type(d, d->btf->start_id + i); if (r < 0) return r; } |