diff options
Diffstat (limited to 'tools/lib/bpf/libbpf.c')
| -rw-r--r-- | tools/lib/bpf/libbpf.c | 4702 |
1 files changed, 4015 insertions, 687 deletions
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 11c25d9ea431..b20f82e58989 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -7,6 +7,7 @@ * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com> * Copyright (C) 2015 Huawei Inc. * Copyright (C) 2017 Nicira, Inc. + * Copyright (C) 2019 Isovalent, Inc. */ #ifndef _GNU_SOURCE @@ -19,6 +20,7 @@ #include <inttypes.h> #include <string.h> #include <unistd.h> +#include <endian.h> #include <fcntl.h> #include <errno.h> #include <asm/unistd.h> @@ -31,9 +33,14 @@ #include <linux/limits.h> #include <linux/perf_event.h> #include <linux/ring_buffer.h> +#include <linux/version.h> +#include <sys/epoll.h> +#include <sys/ioctl.h> +#include <sys/mman.h> #include <sys/stat.h> #include <sys/types.h> #include <sys/vfs.h> +#include <sys/utsname.h> #include <tools/libc_compat.h> #include <libelf.h> #include <gelf.h> @@ -42,7 +49,8 @@ #include "bpf.h" #include "btf.h" #include "str_error.h" -#include "libbpf_util.h" +#include "libbpf_internal.h" +#include "hashmap.h" #ifndef EM_BPF #define EM_BPF 247 @@ -52,6 +60,11 @@ #define BPF_FS_MAGIC 0xcafe4a11 #endif +/* vsprintf() in __base_pr() uses nonliteral format string. It may break + * compilation if user enables corresponding warning. Disable it explicitly. + */ +#pragma GCC diagnostic ignored "-Wformat-nonliteral" + #define __printf(a, b) __attribute__((format(printf, a, b))) static int __base_pr(enum libbpf_print_level level, const char *format, @@ -65,9 +78,12 @@ static int __base_pr(enum libbpf_print_level level, const char *format, static libbpf_print_fn_t __libbpf_pr = __base_pr; -void libbpf_set_print(libbpf_print_fn_t fn) +libbpf_print_fn_t libbpf_set_print(libbpf_print_fn_t fn) { + libbpf_print_fn_t old_print_fn = __libbpf_pr; + __libbpf_pr = fn; + return old_print_fn; } __printf(2, 3) @@ -89,7 +105,7 @@ void libbpf_print(enum libbpf_print_level level, const char *format, ...) err = action; \ if (err) \ goto out; \ -} while(0) +} while (0) /* Copied from tools/perf/util/util.h */ @@ -120,6 +136,14 @@ static inline __u64 ptr_to_u64(const void *ptr) struct bpf_capabilities { /* v4.14: kernel support for program & map names. */ __u32 name:1; + /* v5.2: kernel support for global data sections. */ + __u32 global_data:1; + /* BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO support */ + __u32 btf_func:1; + /* BTF_KIND_VAR and BTF_KIND_DATASEC support */ + __u32 btf_datasec:1; + /* BPF_F_MMAPABLE is supported for arrays */ + __u32 array_mmap:1; }; /* @@ -144,6 +168,7 @@ struct bpf_program { enum { RELO_LD64, RELO_CALL, + RELO_DATA, } type; int insn_idx; union { @@ -152,6 +177,7 @@ struct bpf_program { }; } *reloc_desc; int nr_reloc; + int log_level; struct { int nr; @@ -164,7 +190,8 @@ struct bpf_program { bpf_program_clear_priv_t clear_priv; enum bpf_attach_type expected_attach_type; - int btf_fd; + __u32 attach_btf_id; + __u32 attach_prog_fd; void *func_info; __u32 func_info_rec_size; __u32 func_info_cnt; @@ -174,12 +201,27 @@ struct bpf_program { void *line_info; __u32 line_info_rec_size; __u32 line_info_cnt; + __u32 prog_flags; +}; + +enum libbpf_map_type { + LIBBPF_MAP_UNSPEC, + LIBBPF_MAP_DATA, + LIBBPF_MAP_BSS, + LIBBPF_MAP_RODATA, +}; + +static const char * const libbpf_type_to_btf_name[] = { + [LIBBPF_MAP_DATA] = ".data", + [LIBBPF_MAP_BSS] = ".bss", + [LIBBPF_MAP_RODATA] = ".rodata", }; struct bpf_map { int fd; char *name; - size_t offset; + int sec_idx; + size_t sec_offset; int map_ifindex; int inner_map_fd; struct bpf_map_def def; @@ -187,11 +229,21 @@ struct bpf_map { __u32 btf_value_type_id; void *priv; bpf_map_clear_priv_t clear_priv; + enum libbpf_map_type libbpf_type; + char *pin_path; + bool pinned; + bool reused; +}; + +struct bpf_secdata { + void *rodata; + void *data; }; static LIST_HEAD(bpf_objects_list); struct bpf_object { + char name[BPF_OBJ_NAME_LEN]; char license[64]; __u32 kern_version; @@ -199,9 +251,12 @@ struct bpf_object { size_t nr_programs; struct bpf_map *maps; size_t nr_maps; + size_t maps_cap; + struct bpf_secdata sections; bool loaded; bool has_pseudo_calls; + bool relaxed_core_relocs; /* * Information when doing elf related work. Only valid if fd @@ -209,19 +264,26 @@ struct bpf_object { */ struct { int fd; - void *obj_buf; + const void *obj_buf; size_t obj_buf_sz; Elf *elf; GElf_Ehdr ehdr; Elf_Data *symbols; + Elf_Data *data; + Elf_Data *rodata; + Elf_Data *bss; size_t strtabidx; struct { GElf_Shdr shdr; Elf_Data *data; - } *reloc; - int nr_reloc; + } *reloc_sects; + int nr_reloc_sects; int maps_shndx; + int btf_maps_shndx; int text_shndx; + int data_shndx; + int rodata_shndx; + int bss_shndx; } efile; /* * All loaded bpf_object is linked in a list, which is @@ -257,14 +319,13 @@ void bpf_program__unload(struct bpf_program *prog) for (i = 0; i < prog->instances.nr; i++) zclose(prog->instances.fds[i]); } else if (prog->instances.nr != -1) { - pr_warning("Internal error: instances.nr is %d\n", - prog->instances.nr); + pr_warn("Internal error: instances.nr is %d\n", + prog->instances.nr); } prog->instances.nr = -1; zfree(&prog->instances.fds); - zclose(prog->btf_fd); zfree(&prog->func_info); zfree(&prog->line_info); } @@ -307,8 +368,11 @@ static int bpf_program__init(void *data, size_t size, char *section_name, int idx, struct bpf_program *prog) { - if (size < sizeof(struct bpf_insn)) { - pr_warning("corrupted section '%s'\n", section_name); + const size_t bpf_insn_sz = sizeof(struct bpf_insn); + + if (size == 0 || size % bpf_insn_sz) { + pr_warn("corrupted section '%s', size: %zu\n", + section_name, size); return -EINVAL; } @@ -316,32 +380,30 @@ bpf_program__init(void *data, size_t size, char *section_name, int idx, prog->section_name = strdup(section_name); if (!prog->section_name) { - pr_warning("failed to alloc name for prog under section(%d) %s\n", - idx, section_name); + pr_warn("failed to alloc name for prog under section(%d) %s\n", + idx, section_name); goto errout; } prog->pin_name = __bpf_program__pin_name(prog); if (!prog->pin_name) { - pr_warning("failed to alloc pin name for prog under section(%d) %s\n", - idx, section_name); + pr_warn("failed to alloc pin name for prog under section(%d) %s\n", + idx, section_name); goto errout; } prog->insns = malloc(size); if (!prog->insns) { - pr_warning("failed to alloc insns for prog under section %s\n", - section_name); + pr_warn("failed to alloc insns for prog under section %s\n", + section_name); goto errout; } - prog->insns_cnt = size / sizeof(struct bpf_insn); - memcpy(prog->insns, data, - prog->insns_cnt * sizeof(struct bpf_insn)); + prog->insns_cnt = size / bpf_insn_sz; + memcpy(prog->insns, data, size); prog->idx = idx; prog->instances.fds = NULL; prog->instances.nr = -1; prog->type = BPF_PROG_TYPE_UNSPEC; - prog->btf_fd = -1; return 0; errout: @@ -371,8 +433,8 @@ bpf_object__add_program(struct bpf_object *obj, void *data, size_t size, * is still valid, so don't need special treat for * bpf_close_object(). */ - pr_warning("failed to alloc a new program under section '%s'\n", - section_name); + pr_warn("failed to alloc a new program under section '%s'\n", + section_name); bpf_program__exit(&prog); return -ENOMEM; } @@ -412,8 +474,8 @@ bpf_object__init_prog_names(struct bpf_object *obj) obj->efile.strtabidx, sym.st_name); if (!name) { - pr_warning("failed to get sym name string for prog %s\n", - prog->section_name); + pr_warn("failed to get sym name string for prog %s\n", + prog->section_name); return -LIBBPF_ERRNO__LIBELF; } } @@ -422,15 +484,15 @@ bpf_object__init_prog_names(struct bpf_object *obj) name = ".text"; if (!name) { - pr_warning("failed to find sym for prog %s\n", - prog->section_name); + pr_warn("failed to find sym for prog %s\n", + prog->section_name); return -EINVAL; } prog->name = strdup(name); if (!prog->name) { - pr_warning("failed to allocate memory for prog sym %s\n", - name); + pr_warn("failed to allocate memory for prog sym %s\n", + name); return -ENOMEM; } } @@ -438,23 +500,47 @@ bpf_object__init_prog_names(struct bpf_object *obj) return 0; } +static __u32 get_kernel_version(void) +{ + __u32 major, minor, patch; + struct utsname info; + + uname(&info); + if (sscanf(info.release, "%u.%u.%u", &major, &minor, &patch) != 3) + return 0; + return KERNEL_VERSION(major, minor, patch); +} + static struct bpf_object *bpf_object__new(const char *path, - void *obj_buf, - size_t obj_buf_sz) + const void *obj_buf, + size_t obj_buf_sz, + const char *obj_name) { struct bpf_object *obj; + char *end; obj = calloc(1, sizeof(struct bpf_object) + strlen(path) + 1); if (!obj) { - pr_warning("alloc memory failed for %s\n", path); + pr_warn("alloc memory failed for %s\n", path); return ERR_PTR(-ENOMEM); } strcpy(obj->path, path); - obj->efile.fd = -1; + if (obj_name) { + strncpy(obj->name, obj_name, sizeof(obj->name) - 1); + obj->name[sizeof(obj->name) - 1] = 0; + } else { + /* Using basename() GNU version which doesn't modify arg. */ + strncpy(obj->name, basename((void *)path), + sizeof(obj->name) - 1); + end = strchr(obj->name, '.'); + if (end) + *end = 0; + } + obj->efile.fd = -1; /* - * Caller of this function should also calls + * Caller of this function should also call * bpf_object__elf_finish() after data collection to return * obj_buf to user. If not, we should duplicate the buffer to * avoid user freeing them before elf finish. @@ -462,7 +548,12 @@ static struct bpf_object *bpf_object__new(const char *path, obj->efile.obj_buf = obj_buf; obj->efile.obj_buf_sz = obj_buf_sz; obj->efile.maps_shndx = -1; + obj->efile.btf_maps_shndx = -1; + obj->efile.data_shndx = -1; + obj->efile.rodata_shndx = -1; + obj->efile.bss_shndx = -1; + obj->kern_version = get_kernel_version(); obj->loaded = false; INIT_LIST_HEAD(&obj->list); @@ -480,9 +571,12 @@ static void bpf_object__elf_finish(struct bpf_object *obj) obj->efile.elf = NULL; } obj->efile.symbols = NULL; + obj->efile.data = NULL; + obj->efile.rodata = NULL; + obj->efile.bss = NULL; - zfree(&obj->efile.reloc); - obj->efile.nr_reloc = 0; + zfree(&obj->efile.reloc_sects); + obj->efile.nr_reloc_sects = 0; zclose(obj->efile.fd); obj->efile.obj_buf = NULL; obj->efile.obj_buf_sz = 0; @@ -494,7 +588,7 @@ static int bpf_object__elf_init(struct bpf_object *obj) GElf_Ehdr *ep; if (obj_elf_valid(obj)) { - pr_warning("elf init: internal error\n"); + pr_warn("elf init: internal error\n"); return -LIBBPF_ERRNO__LIBELF; } @@ -503,43 +597,40 @@ static int bpf_object__elf_init(struct bpf_object *obj) * obj_buf should have been validated by * bpf_object__open_buffer(). */ - obj->efile.elf = elf_memory(obj->efile.obj_buf, + obj->efile.elf = elf_memory((char *)obj->efile.obj_buf, obj->efile.obj_buf_sz); } else { obj->efile.fd = open(obj->path, O_RDONLY); if (obj->efile.fd < 0) { - char errmsg[STRERR_BUFSIZE]; - char *cp = libbpf_strerror_r(errno, errmsg, - sizeof(errmsg)); + char errmsg[STRERR_BUFSIZE], *cp; - pr_warning("failed to open %s: %s\n", obj->path, cp); - return -errno; + err = -errno; + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); + pr_warn("failed to open %s: %s\n", obj->path, cp); + return err; } obj->efile.elf = elf_begin(obj->efile.fd, - LIBBPF_ELF_C_READ_MMAP, - NULL); + LIBBPF_ELF_C_READ_MMAP, NULL); } if (!obj->efile.elf) { - pr_warning("failed to open %s as ELF file\n", - obj->path); + pr_warn("failed to open %s as ELF file\n", obj->path); err = -LIBBPF_ERRNO__LIBELF; goto errout; } if (!gelf_getehdr(obj->efile.elf, &obj->efile.ehdr)) { - pr_warning("failed to get EHDR from %s\n", - obj->path); + pr_warn("failed to get EHDR from %s\n", obj->path); err = -LIBBPF_ERRNO__FORMAT; goto errout; } ep = &obj->efile.ehdr; /* Old LLVM set e_machine to EM_NONE */ - if ((ep->e_type != ET_REL) || (ep->e_machine && (ep->e_machine != EM_BPF))) { - pr_warning("%s is not an eBPF object file\n", - obj->path); + if (ep->e_type != ET_REL || + (ep->e_machine && ep->e_machine != EM_BPF)) { + pr_warn("%s is not an eBPF object file\n", obj->path); err = -LIBBPF_ERRNO__FORMAT; goto errout; } @@ -550,58 +641,41 @@ errout: return err; } -static int -bpf_object__check_endianness(struct bpf_object *obj) +static int bpf_object__check_endianness(struct bpf_object *obj) { - static unsigned int const endian = 1; - - switch (obj->efile.ehdr.e_ident[EI_DATA]) { - case ELFDATA2LSB: - /* We are big endian, BPF obj is little endian. */ - if (*(unsigned char const *)&endian != 1) - goto mismatch; - break; - - case ELFDATA2MSB: - /* We are little endian, BPF obj is big endian. */ - if (*(unsigned char const *)&endian != 0) - goto mismatch; - break; - default: - return -LIBBPF_ERRNO__ENDIAN; - } - - return 0; - -mismatch: - pr_warning("Error: endianness mismatch.\n"); +#if __BYTE_ORDER == __LITTLE_ENDIAN + if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2LSB) + return 0; +#elif __BYTE_ORDER == __BIG_ENDIAN + if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2MSB) + return 0; +#else +# error "Unrecognized __BYTE_ORDER__" +#endif + pr_warn("endianness mismatch.\n"); return -LIBBPF_ERRNO__ENDIAN; } static int -bpf_object__init_license(struct bpf_object *obj, - void *data, size_t size) +bpf_object__init_license(struct bpf_object *obj, void *data, size_t size) { - memcpy(obj->license, data, - min(size, sizeof(obj->license) - 1)); + memcpy(obj->license, data, min(size, sizeof(obj->license) - 1)); pr_debug("license of %s is %s\n", obj->path, obj->license); return 0; } static int -bpf_object__init_kversion(struct bpf_object *obj, - void *data, size_t size) +bpf_object__init_kversion(struct bpf_object *obj, void *data, size_t size) { __u32 kver; if (size != sizeof(kver)) { - pr_warning("invalid kver section in %s\n", obj->path); + pr_warn("invalid kver section in %s\n", obj->path); return -LIBBPF_ERRNO__FORMAT; } memcpy(&kver, data, sizeof(kver)); obj->kern_version = kver; - pr_debug("kernel version of %s is %x\n", obj->path, - obj->kern_version); + pr_debug("kernel version of %s is %x\n", obj->path, obj->kern_version); return 0; } @@ -610,7 +684,9 @@ static int compare_bpf_map(const void *_a, const void *_b) const struct bpf_map *a = _a; const struct bpf_map *b = _b; - return a->offset - b->offset; + if (a->sec_idx != b->sec_idx) + return a->sec_idx - b->sec_idx; + return a->sec_offset - b->sec_offset; } static bool bpf_map_type__is_map_in_map(enum bpf_map_type type) @@ -621,17 +697,240 @@ static bool bpf_map_type__is_map_in_map(enum bpf_map_type type) return false; } +static int bpf_object_search_section_size(const struct bpf_object *obj, + const char *name, size_t *d_size) +{ + const GElf_Ehdr *ep = &obj->efile.ehdr; + Elf *elf = obj->efile.elf; + Elf_Scn *scn = NULL; + int idx = 0; + + while ((scn = elf_nextscn(elf, scn)) != NULL) { + const char *sec_name; + Elf_Data *data; + GElf_Shdr sh; + + idx++; + if (gelf_getshdr(scn, &sh) != &sh) { + pr_warn("failed to get section(%d) header from %s\n", + idx, obj->path); + return -EIO; + } + + sec_name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name); + if (!sec_name) { + pr_warn("failed to get section(%d) name from %s\n", + idx, obj->path); + return -EIO; + } + + if (strcmp(name, sec_name)) + continue; + + data = elf_getdata(scn, 0); + if (!data) { + pr_warn("failed to get section(%d) data from %s(%s)\n", + idx, name, obj->path); + return -EIO; + } + + *d_size = data->d_size; + return 0; + } + + return -ENOENT; +} + +int bpf_object__section_size(const struct bpf_object *obj, const char *name, + __u32 *size) +{ + int ret = -ENOENT; + size_t d_size; + + *size = 0; + if (!name) { + return -EINVAL; + } else if (!strcmp(name, ".data")) { + if (obj->efile.data) + *size = obj->efile.data->d_size; + } else if (!strcmp(name, ".bss")) { + if (obj->efile.bss) + *size = obj->efile.bss->d_size; + } else if (!strcmp(name, ".rodata")) { + if (obj->efile.rodata) + *size = obj->efile.rodata->d_size; + } else { + ret = bpf_object_search_section_size(obj, name, &d_size); + if (!ret) + *size = d_size; + } + + return *size ? 0 : ret; +} + +int bpf_object__variable_offset(const struct bpf_object *obj, const char *name, + __u32 *off) +{ + Elf_Data *symbols = obj->efile.symbols; + const char *sname; + size_t si; + + if (!name || !off) + return -EINVAL; + + for (si = 0; si < symbols->d_size / sizeof(GElf_Sym); si++) { + GElf_Sym sym; + + if (!gelf_getsym(symbols, si, &sym)) + continue; + if (GELF_ST_BIND(sym.st_info) != STB_GLOBAL || + GELF_ST_TYPE(sym.st_info) != STT_OBJECT) + continue; + + sname = elf_strptr(obj->efile.elf, obj->efile.strtabidx, + sym.st_name); + if (!sname) { + pr_warn("failed to get sym name string for var %s\n", + name); + return -EIO; + } + if (strcmp(name, sname) == 0) { + *off = sym.st_value; + return 0; + } + } + + return -ENOENT; +} + +static struct bpf_map *bpf_object__add_map(struct bpf_object *obj) +{ + struct bpf_map *new_maps; + size_t new_cap; + int i; + + if (obj->nr_maps < obj->maps_cap) + return &obj->maps[obj->nr_maps++]; + + new_cap = max((size_t)4, obj->maps_cap * 3 / 2); + new_maps = realloc(obj->maps, new_cap * sizeof(*obj->maps)); + if (!new_maps) { + pr_warn("alloc maps for object failed\n"); + return ERR_PTR(-ENOMEM); + } + + obj->maps_cap = new_cap; + obj->maps = new_maps; + + /* zero out new maps */ + memset(obj->maps + obj->nr_maps, 0, + (obj->maps_cap - obj->nr_maps) * sizeof(*obj->maps)); + /* + * fill all fd with -1 so won't close incorrect fd (fd=0 is stdin) + * when failure (zclose won't close negative fd)). + */ + for (i = obj->nr_maps; i < obj->maps_cap; i++) { + obj->maps[i].fd = -1; + obj->maps[i].inner_map_fd = -1; + } + + return &obj->maps[obj->nr_maps++]; +} + static int -bpf_object__init_maps(struct bpf_object *obj, int flags) +bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, + int sec_idx, Elf_Data *data, void **data_buff) +{ + char map_name[BPF_OBJ_NAME_LEN]; + struct bpf_map_def *def; + struct bpf_map *map; + + map = bpf_object__add_map(obj); + if (IS_ERR(map)) + return PTR_ERR(map); + + map->libbpf_type = type; + map->sec_idx = sec_idx; + map->sec_offset = 0; + snprintf(map_name, sizeof(map_name), "%.8s%.7s", obj->name, + libbpf_type_to_btf_name[type]); + map->name = strdup(map_name); + if (!map->name) { + pr_warn("failed to alloc map name\n"); + return -ENOMEM; + } + + def = &map->def; + def->type = BPF_MAP_TYPE_ARRAY; + def->key_size = sizeof(int); + def->value_size = data->d_size; + def->max_entries = 1; + def->map_flags = type == LIBBPF_MAP_RODATA ? BPF_F_RDONLY_PROG : 0; + if (obj->caps.array_mmap) + def->map_flags |= BPF_F_MMAPABLE; + + pr_debug("map '%s' (global data): at sec_idx %d, offset %zu, flags %x.\n", + map_name, map->sec_idx, map->sec_offset, def->map_flags); + + if (data_buff) { + *data_buff = malloc(data->d_size); + if (!*data_buff) { + zfree(&map->name); + pr_warn("failed to alloc map content buffer\n"); + return -ENOMEM; + } + memcpy(*data_buff, data->d_buf, data->d_size); + } + + pr_debug("map %td is \"%s\"\n", map - obj->maps, map->name); + return 0; +} + +static int bpf_object__init_global_data_maps(struct bpf_object *obj) +{ + int err; + + if (!obj->caps.global_data) + return 0; + /* + * Populate obj->maps with libbpf internal maps. + */ + if (obj->efile.data_shndx >= 0) { + err = bpf_object__init_internal_map(obj, LIBBPF_MAP_DATA, + obj->efile.data_shndx, + obj->efile.data, + &obj->sections.data); + if (err) + return err; + } + if (obj->efile.rodata_shndx >= 0) { + err = bpf_object__init_internal_map(obj, LIBBPF_MAP_RODATA, + obj->efile.rodata_shndx, + obj->efile.rodata, + &obj->sections.rodata); + if (err) + return err; + } + if (obj->efile.bss_shndx >= 0) { + err = bpf_object__init_internal_map(obj, LIBBPF_MAP_BSS, + obj->efile.bss_shndx, + obj->efile.bss, NULL); + if (err) + return err; + } + return 0; +} + +static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) { - bool strict = !(flags & MAPS_RELAX_COMPAT); - int i, map_idx, map_def_sz, nr_maps = 0; - Elf_Scn *scn; - Elf_Data *data = NULL; Elf_Data *symbols = obj->efile.symbols; + int i, map_def_sz = 0, nr_maps = 0, nr_syms; + Elf_Data *data = NULL; + Elf_Scn *scn; if (obj->efile.maps_shndx < 0) - return -EINVAL; + return 0; + if (!symbols) return -EINVAL; @@ -639,8 +938,8 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) if (scn) data = elf_getdata(scn, NULL); if (!scn || !data) { - pr_warning("failed to get Elf_Data from map section %d\n", - obj->efile.maps_shndx); + pr_warn("failed to get Elf_Data from map section %d\n", + obj->efile.maps_shndx); return -EINVAL; } @@ -651,7 +950,8 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) * * TODO: Detect array of map and report error. */ - for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) { + nr_syms = symbols->d_size / sizeof(GElf_Sym); + for (i = 0; i < nr_syms; i++) { GElf_Sym sym; if (!gelf_getsym(symbols, i, &sym)) @@ -660,70 +960,58 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) continue; nr_maps++; } - - /* Alloc obj->maps and fill nr_maps. */ - pr_debug("maps in %s: %d maps in %zd bytes\n", obj->path, - nr_maps, data->d_size); - - if (!nr_maps) - return 0; - /* Assume equally sized map definitions */ - map_def_sz = data->d_size / nr_maps; - if (!data->d_size || (data->d_size % nr_maps) != 0) { - pr_warning("unable to determine map definition size " - "section %s, %d maps in %zd bytes\n", - obj->path, nr_maps, data->d_size); - return -EINVAL; - } - - obj->maps = calloc(nr_maps, sizeof(obj->maps[0])); - if (!obj->maps) { - pr_warning("alloc maps for object failed\n"); - return -ENOMEM; - } - obj->nr_maps = nr_maps; + pr_debug("maps in %s: %d maps in %zd bytes\n", + obj->path, nr_maps, data->d_size); - for (i = 0; i < nr_maps; i++) { - /* - * fill all fd with -1 so won't close incorrect - * fd (fd=0 is stdin) when failure (zclose won't close - * negative fd)). - */ - obj->maps[i].fd = -1; - obj->maps[i].inner_map_fd = -1; + if (!data->d_size || nr_maps == 0 || (data->d_size % nr_maps) != 0) { + pr_warn("unable to determine map definition size section %s, %d maps in %zd bytes\n", + obj->path, nr_maps, data->d_size); + return -EINVAL; } + map_def_sz = data->d_size / nr_maps; - /* - * Fill obj->maps using data in "maps" section. - */ - for (i = 0, map_idx = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) { + /* Fill obj->maps using data in "maps" section. */ + for (i = 0; i < nr_syms; i++) { GElf_Sym sym; const char *map_name; struct bpf_map_def *def; + struct bpf_map *map; if (!gelf_getsym(symbols, i, &sym)) continue; if (sym.st_shndx != obj->efile.maps_shndx) continue; - map_name = elf_strptr(obj->efile.elf, - obj->efile.strtabidx, + map = bpf_object__add_map(obj); + if (IS_ERR(map)) + return PTR_ERR(map); + + map_name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, sym.st_name); - obj->maps[map_idx].offset = sym.st_value; + if (!map_name) { + pr_warn("failed to get map #%d name sym string for obj %s\n", + i, obj->path); + return -LIBBPF_ERRNO__FORMAT; + } + + map->libbpf_type = LIBBPF_MAP_UNSPEC; + map->sec_idx = sym.st_shndx; + map->sec_offset = sym.st_value; + pr_debug("map '%s' (legacy): at sec_idx %d, offset %zu.\n", + map_name, map->sec_idx, map->sec_offset); if (sym.st_value + map_def_sz > data->d_size) { - pr_warning("corrupted maps section in %s: last map \"%s\" too small\n", - obj->path, map_name); + pr_warn("corrupted maps section in %s: last map \"%s\" too small\n", + obj->path, map_name); return -EINVAL; } - obj->maps[map_idx].name = strdup(map_name); - if (!obj->maps[map_idx].name) { - pr_warning("failed to alloc map name\n"); + map->name = strdup(map_name); + if (!map->name) { + pr_warn("failed to alloc map name\n"); return -ENOMEM; } - pr_debug("map %d is \"%s\"\n", map_idx, - obj->maps[map_idx].name); + pr_debug("map %d is \"%s\"\n", i, map->name); def = (struct bpf_map_def *)(data->d_buf + sym.st_value); /* * If the definition of the map in the object file fits in @@ -732,7 +1020,7 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) * calloc above. */ if (map_def_sz <= sizeof(struct bpf_map_def)) { - memcpy(&obj->maps[map_idx].def, def, map_def_sz); + memcpy(&map->def, def, map_def_sz); } else { /* * Here the map structure being read is bigger than what @@ -741,24 +1029,394 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) * incompatible. */ char *b; + for (b = ((char *)def) + sizeof(struct bpf_map_def); b < ((char *)def) + map_def_sz; b++) { if (*b != 0) { - pr_warning("maps section in %s: \"%s\" " - "has unrecognized, non-zero " - "options\n", - obj->path, map_name); + pr_warn("maps section in %s: \"%s\" has unrecognized, non-zero options\n", + obj->path, map_name); if (strict) return -EINVAL; } } - memcpy(&obj->maps[map_idx].def, def, - sizeof(struct bpf_map_def)); + memcpy(&map->def, def, sizeof(struct bpf_map_def)); + } + } + return 0; +} + +static const struct btf_type * +skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id) +{ + const struct btf_type *t = btf__type_by_id(btf, id); + + if (res_id) + *res_id = id; + + while (btf_is_mod(t) || btf_is_typedef(t)) { + if (res_id) + *res_id = t->type; + t = btf__type_by_id(btf, t->type); + } + + return t; +} + +/* + * Fetch integer attribute of BTF map definition. Such attributes are + * represented using a pointer to an array, in which dimensionality of array + * encodes specified integer value. E.g., int (*type)[BPF_MAP_TYPE_ARRAY]; + * encodes `type => BPF_MAP_TYPE_ARRAY` key/value pair completely using BTF + * type definition, while using only sizeof(void *) space in ELF data section. + */ +static bool get_map_field_int(const char *map_name, const struct btf *btf, + const struct btf_type *def, + const struct btf_member *m, __u32 *res) +{ + const struct btf_type *t = skip_mods_and_typedefs(btf, m->type, NULL); + const char *name = btf__name_by_offset(btf, m->name_off); + const struct btf_array *arr_info; + const struct btf_type *arr_t; + + if (!btf_is_ptr(t)) { + pr_warn("map '%s': attr '%s': expected PTR, got %u.\n", + map_name, name, btf_kind(t)); + return false; + } + + arr_t = btf__type_by_id(btf, t->type); + if (!arr_t) { + pr_warn("map '%s': attr '%s': type [%u] not found.\n", + map_name, name, t->type); + return false; + } + if (!btf_is_array(arr_t)) { + pr_warn("map '%s': attr '%s': expected ARRAY, got %u.\n", + map_name, name, btf_kind(arr_t)); + return false; + } + arr_info = btf_array(arr_t); + *res = arr_info->nelems; + return true; +} + +static int build_map_pin_path(struct bpf_map *map, const char *path) +{ + char buf[PATH_MAX]; + int err, len; + + if (!path) + path = "/sys/fs/bpf"; + + len = snprintf(buf, PATH_MAX, "%s/%s", path, bpf_map__name(map)); + if (len < 0) + return -EINVAL; + else if (len >= PATH_MAX) + return -ENAMETOOLONG; + + err = bpf_map__set_pin_path(map, buf); + if (err) + return err; + + return 0; +} + +static int bpf_object__init_user_btf_map(struct bpf_object *obj, + const struct btf_type *sec, + int var_idx, int sec_idx, + const Elf_Data *data, bool strict, + const char *pin_root_path) +{ + const struct btf_type *var, *def, *t; + const struct btf_var_secinfo *vi; + const struct btf_var *var_extra; + const struct btf_member *m; + const char *map_name; + struct bpf_map *map; + int vlen, i; + + vi = btf_var_secinfos(sec) + var_idx; + var = btf__type_by_id(obj->btf, vi->type); + var_extra = btf_var(var); + map_name = btf__name_by_offset(obj->btf, var->name_off); + vlen = btf_vlen(var); + + if (map_name == NULL || map_name[0] == '\0') { + pr_warn("map #%d: empty name.\n", var_idx); + return -EINVAL; + } + if ((__u64)vi->offset + vi->size > data->d_size) { + pr_warn("map '%s' BTF data is corrupted.\n", map_name); + return -EINVAL; + } + if (!btf_is_var(var)) { + pr_warn("map '%s': unexpected var kind %u.\n", + map_name, btf_kind(var)); + return -EINVAL; + } + if (var_extra->linkage != BTF_VAR_GLOBAL_ALLOCATED && + var_extra->linkage != BTF_VAR_STATIC) { + pr_warn("map '%s': unsupported var linkage %u.\n", + map_name, var_extra->linkage); + return -EOPNOTSUPP; + } + + def = skip_mods_and_typedefs(obj->btf, var->type, NULL); + if (!btf_is_struct(def)) { + pr_warn("map '%s': unexpected def kind %u.\n", + map_name, btf_kind(var)); + return -EINVAL; + } + if (def->size > vi->size) { + pr_warn("map '%s': invalid def size.\n", map_name); + return -EINVAL; + } + + map = bpf_object__add_map(obj); + if (IS_ERR(map)) + return PTR_ERR(map); + map->name = strdup(map_name); + if (!map->name) { + pr_warn("map '%s': failed to alloc map name.\n", map_name); + return -ENOMEM; + } + map->libbpf_type = LIBBPF_MAP_UNSPEC; + map->def.type = BPF_MAP_TYPE_UNSPEC; + map->sec_idx = sec_idx; + map->sec_offset = vi->offset; + pr_debug("map '%s': at sec_idx %d, offset %zu.\n", + map_name, map->sec_idx, map->sec_offset); + + vlen = btf_vlen(def); + m = btf_members(def); + for (i = 0; i < vlen; i++, m++) { + const char *name = btf__name_by_offset(obj->btf, m->name_off); + + if (!name) { + pr_warn("map '%s': invalid field #%d.\n", map_name, i); + return -EINVAL; + } + if (strcmp(name, "type") == 0) { + if (!get_map_field_int(map_name, obj->btf, def, m, + &map->def.type)) + return -EINVAL; + pr_debug("map '%s': found type = %u.\n", + map_name, map->def.type); + } else if (strcmp(name, "max_entries") == 0) { + if (!get_map_field_int(map_name, obj->btf, def, m, + &map->def.max_entries)) + return -EINVAL; + pr_debug("map '%s': found max_entries = %u.\n", + map_name, map->def.max_entries); + } else if (strcmp(name, "map_flags") == 0) { + if (!get_map_field_int(map_name, obj->btf, def, m, + &map->def.map_flags)) + return -EINVAL; + pr_debug("map '%s': found map_flags = %u.\n", + map_name, map->def.map_flags); + } else if (strcmp(name, "key_size") == 0) { + __u32 sz; + + if (!get_map_field_int(map_name, obj->btf, def, m, + &sz)) + return -EINVAL; + pr_debug("map '%s': found key_size = %u.\n", + map_name, sz); + if (map->def.key_size && map->def.key_size != sz) { + pr_warn("map '%s': conflicting key size %u != %u.\n", + map_name, map->def.key_size, sz); + return -EINVAL; + } + map->def.key_size = sz; + } else if (strcmp(name, "key") == 0) { + __s64 sz; + + t = btf__type_by_id(obj->btf, m->type); + if (!t) { + pr_warn("map '%s': key type [%d] not found.\n", + map_name, m->type); + return -EINVAL; + } + if (!btf_is_ptr(t)) { + pr_warn("map '%s': key spec is not PTR: %u.\n", + map_name, btf_kind(t)); + return -EINVAL; + } + sz = btf__resolve_size(obj->btf, t->type); + if (sz < 0) { + pr_warn("map '%s': can't determine key size for type [%u]: %lld.\n", + map_name, t->type, sz); + return sz; + } + pr_debug("map '%s': found key [%u], sz = %lld.\n", + map_name, t->type, sz); + if (map->def.key_size && map->def.key_size != sz) { + pr_warn("map '%s': conflicting key size %u != %lld.\n", + map_name, map->def.key_size, sz); + return -EINVAL; + } + map->def.key_size = sz; + map->btf_key_type_id = t->type; + } else if (strcmp(name, "value_size") == 0) { + __u32 sz; + + if (!get_map_field_int(map_name, obj->btf, def, m, + &sz)) + return -EINVAL; + pr_debug("map '%s': found value_size = %u.\n", + map_name, sz); + if (map->def.value_size && map->def.value_size != sz) { + pr_warn("map '%s': conflicting value size %u != %u.\n", + map_name, map->def.value_size, sz); + return -EINVAL; + } + map->def.value_size = sz; + } else if (strcmp(name, "value") == 0) { + __s64 sz; + + t = btf__type_by_id(obj->btf, m->type); + if (!t) { + pr_warn("map '%s': value type [%d] not found.\n", + map_name, m->type); + return -EINVAL; + } + if (!btf_is_ptr(t)) { + pr_warn("map '%s': value spec is not PTR: %u.\n", + map_name, btf_kind(t)); + return -EINVAL; + } + sz = btf__resolve_size(obj->btf, t->type); + if (sz < 0) { + pr_warn("map '%s': can't determine value size for type [%u]: %lld.\n", + map_name, t->type, sz); + return sz; + } + pr_debug("map '%s': found value [%u], sz = %lld.\n", + map_name, t->type, sz); + if (map->def.value_size && map->def.value_size != sz) { + pr_warn("map '%s': conflicting value size %u != %lld.\n", + map_name, map->def.value_size, sz); + return -EINVAL; + } + map->def.value_size = sz; + map->btf_value_type_id = t->type; + } else if (strcmp(name, "pinning") == 0) { + __u32 val; + int err; + + if (!get_map_field_int(map_name, obj->btf, def, m, + &val)) + return -EINVAL; + pr_debug("map '%s': found pinning = %u.\n", + map_name, val); + + if (val != LIBBPF_PIN_NONE && + val != LIBBPF_PIN_BY_NAME) { + pr_warn("map '%s': invalid pinning value %u.\n", + map_name, val); + return -EINVAL; + } + if (val == LIBBPF_PIN_BY_NAME) { + err = build_map_pin_path(map, pin_root_path); + if (err) { + pr_warn("map '%s': couldn't build pin path.\n", + map_name); + return err; + } + } + } else { + if (strict) { + pr_warn("map '%s': unknown field '%s'.\n", + map_name, name); + return -ENOTSUP; + } + pr_debug("map '%s': ignoring unknown field '%s'.\n", + map_name, name); + } + } + + if (map->def.type == BPF_MAP_TYPE_UNSPEC) { + pr_warn("map '%s': map type isn't specified.\n", map_name); + return -EINVAL; + } + + return 0; +} + +static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict, + const char *pin_root_path) +{ + const struct btf_type *sec = NULL; + int nr_types, i, vlen, err; + const struct btf_type *t; + const char *name; + Elf_Data *data; + Elf_Scn *scn; + + if (obj->efile.btf_maps_shndx < 0) + return 0; + + scn = elf_getscn(obj->efile.elf, obj->efile.btf_maps_shndx); + if (scn) + data = elf_getdata(scn, NULL); + if (!scn || !data) { + pr_warn("failed to get Elf_Data from map section %d (%s)\n", + obj->efile.maps_shndx, MAPS_ELF_SEC); + return -EINVAL; + } + + nr_types = btf__get_nr_types(obj->btf); + for (i = 1; i <= nr_types; i++) { + t = btf__type_by_id(obj->btf, i); + if (!btf_is_datasec(t)) + continue; + name = btf__name_by_offset(obj->btf, t->name_off); + if (strcmp(name, MAPS_ELF_SEC) == 0) { + sec = t; + break; } - map_idx++; } - qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), compare_bpf_map); + if (!sec) { + pr_warn("DATASEC '%s' not found.\n", MAPS_ELF_SEC); + return -ENOENT; + } + + vlen = btf_vlen(sec); + for (i = 0; i < vlen; i++) { + err = bpf_object__init_user_btf_map(obj, sec, i, + obj->efile.btf_maps_shndx, + data, strict, + pin_root_path); + if (err) + return err; + } + + return 0; +} + +static int bpf_object__init_maps(struct bpf_object *obj, bool relaxed_maps, + const char *pin_root_path) +{ + bool strict = !relaxed_maps; + int err; + + err = bpf_object__init_user_maps(obj, strict); + if (err) + return err; + + err = bpf_object__init_user_btf_maps(obj, strict, pin_root_path); + if (err) + return err; + + err = bpf_object__init_global_data_maps(obj); + if (err) + return err; + + if (obj->nr_maps) { + qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), + compare_bpf_map); + } return 0; } @@ -780,18 +1438,175 @@ static bool section_have_execinstr(struct bpf_object *obj, int idx) return false; } -static int bpf_object__elf_collect(struct bpf_object *obj, int flags) +static void bpf_object__sanitize_btf(struct bpf_object *obj) +{ + bool has_datasec = obj->caps.btf_datasec; + bool has_func = obj->caps.btf_func; + struct btf *btf = obj->btf; + struct btf_type *t; + int i, j, vlen; + + if (!obj->btf || (has_func && has_datasec)) + return; + + for (i = 1; i <= btf__get_nr_types(btf); i++) { + t = (struct btf_type *)btf__type_by_id(btf, i); + + if (!has_datasec && btf_is_var(t)) { + /* replace VAR with INT */ + t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0); + /* + * using size = 1 is the safest choice, 4 will be too + * big and cause kernel BTF validation failure if + * original variable took less than 4 bytes + */ + t->size = 1; + *(int *)(t + 1) = BTF_INT_ENC(0, 0, 8); + } else if (!has_datasec && btf_is_datasec(t)) { + /* replace DATASEC with STRUCT */ + const struct btf_var_secinfo *v = btf_var_secinfos(t); + struct btf_member *m = btf_members(t); + struct btf_type *vt; + char *name; + + name = (char *)btf__name_by_offset(btf, t->name_off); + while (*name) { + if (*name == '.') + *name = '_'; + name++; + } + + vlen = btf_vlen(t); + t->info = BTF_INFO_ENC(BTF_KIND_STRUCT, 0, vlen); + for (j = 0; j < vlen; j++, v++, m++) { + /* order of field assignments is important */ + m->offset = v->offset * 8; + m->type = v->type; + /* preserve variable name as member name */ + vt = (void *)btf__type_by_id(btf, v->type); + m->name_off = vt->name_off; + } + } else if (!has_func && btf_is_func_proto(t)) { + /* replace FUNC_PROTO with ENUM */ + vlen = btf_vlen(t); + t->info = BTF_INFO_ENC(BTF_KIND_ENUM, 0, vlen); + t->size = sizeof(__u32); /* kernel enforced */ + } else if (!has_func && btf_is_func(t)) { + /* replace FUNC with TYPEDEF */ + t->info = BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0); + } + } +} + +static void bpf_object__sanitize_btf_ext(struct bpf_object *obj) +{ + if (!obj->btf_ext) + return; + + if (!obj->caps.btf_func) { + btf_ext__free(obj->btf_ext); + obj->btf_ext = NULL; + } +} + +static bool bpf_object__is_btf_mandatory(const struct bpf_object *obj) +{ + return obj->efile.btf_maps_shndx >= 0; +} + +static int bpf_object__init_btf(struct bpf_object *obj, + Elf_Data *btf_data, + Elf_Data *btf_ext_data) +{ + bool btf_required = bpf_object__is_btf_mandatory(obj); + int err = 0; + + if (btf_data) { + obj->btf = btf__new(btf_data->d_buf, btf_data->d_size); + if (IS_ERR(obj->btf)) { + pr_warn("Error loading ELF section %s: %d.\n", + BTF_ELF_SEC, err); + goto out; + } + err = btf__finalize_data(obj, obj->btf); + if (err) { + pr_warn("Error finalizing %s: %d.\n", BTF_ELF_SEC, err); + goto out; + } + } + if (btf_ext_data) { + if (!obj->btf) { + pr_debug("Ignore ELF section %s because its depending ELF section %s is not found.\n", + BTF_EXT_ELF_SEC, BTF_ELF_SEC); + goto out; + } + obj->btf_ext = btf_ext__new(btf_ext_data->d_buf, + btf_ext_data->d_size); + if (IS_ERR(obj->btf_ext)) { + pr_warn("Error loading ELF section %s: %ld. Ignored and continue.\n", + BTF_EXT_ELF_SEC, PTR_ERR(obj->btf_ext)); + obj->btf_ext = NULL; + goto out; + } + } +out: + if (err || IS_ERR(obj->btf)) { + if (btf_required) + err = err ? : PTR_ERR(obj->btf); + else + err = 0; + if (!IS_ERR_OR_NULL(obj->btf)) + btf__free(obj->btf); + obj->btf = NULL; + } + if (btf_required && !obj->btf) { + pr_warn("BTF is required, but is missing or corrupted.\n"); + return err == 0 ? -ENOENT : err; + } + return 0; +} + +static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) +{ + int err = 0; + + if (!obj->btf) + return 0; + + bpf_object__sanitize_btf(obj); + bpf_object__sanitize_btf_ext(obj); + + err = btf__load(obj->btf); + if (err) { + pr_warn("Error loading %s into kernel: %d.\n", + BTF_ELF_SEC, err); + btf__free(obj->btf); + obj->btf = NULL; + /* btf_ext can't exist without btf, so free it as well */ + if (obj->btf_ext) { + btf_ext__free(obj->btf_ext); + obj->btf_ext = NULL; + } + + if (bpf_object__is_btf_mandatory(obj)) + return err; + } + return 0; +} + +static int bpf_object__elf_collect(struct bpf_object *obj, bool relaxed_maps, + const char *pin_root_path) { Elf *elf = obj->efile.elf; GElf_Ehdr *ep = &obj->efile.ehdr; Elf_Data *btf_ext_data = NULL; + Elf_Data *btf_data = NULL; Elf_Scn *scn = NULL; int idx = 0, err = 0; /* Elf is corrupted/truncated, avoid calling elf_strptr. */ if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) { - pr_warning("failed to get e_shstrndx from %s\n", - obj->path); + pr_warn("failed to get e_shstrndx from %s\n", obj->path); return -LIBBPF_ERRNO__FORMAT; } @@ -802,87 +1617,86 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) idx++; if (gelf_getshdr(scn, &sh) != &sh) { - pr_warning("failed to get section(%d) header from %s\n", - idx, obj->path); - err = -LIBBPF_ERRNO__FORMAT; - goto out; + pr_warn("failed to get section(%d) header from %s\n", + idx, obj->path); + return -LIBBPF_ERRNO__FORMAT; } name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name); if (!name) { - pr_warning("failed to get section(%d) name from %s\n", - idx, obj->path); - err = -LIBBPF_ERRNO__FORMAT; - goto out; + pr_warn("failed to get section(%d) name from %s\n", + idx, obj->path); + return -LIBBPF_ERRNO__FORMAT; } data = elf_getdata(scn, 0); if (!data) { - pr_warning("failed to get section(%d) data from %s(%s)\n", - idx, name, obj->path); - err = -LIBBPF_ERRNO__FORMAT; - goto out; + pr_warn("failed to get section(%d) data from %s(%s)\n", + idx, name, obj->path); + return -LIBBPF_ERRNO__FORMAT; } pr_debug("section(%d) %s, size %ld, link %d, flags %lx, type=%d\n", idx, name, (unsigned long)data->d_size, (int)sh.sh_link, (unsigned long)sh.sh_flags, (int)sh.sh_type); - if (strcmp(name, "license") == 0) + if (strcmp(name, "license") == 0) { err = bpf_object__init_license(obj, data->d_buf, data->d_size); - else if (strcmp(name, "version") == 0) + if (err) + return err; + } else if (strcmp(name, "version") == 0) { err = bpf_object__init_kversion(obj, data->d_buf, data->d_size); - else if (strcmp(name, "maps") == 0) + if (err) + return err; + } else if (strcmp(name, "maps") == 0) { obj->efile.maps_shndx = idx; - else if (strcmp(name, BTF_ELF_SEC) == 0) { - obj->btf = btf__new(data->d_buf, data->d_size); - if (IS_ERR(obj->btf)) { - pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n", - BTF_ELF_SEC, PTR_ERR(obj->btf)); - obj->btf = NULL; - continue; - } - err = btf__load(obj->btf); - if (err) { - pr_warning("Error loading %s into kernel: %d. Ignored and continue.\n", - BTF_ELF_SEC, err); - btf__free(obj->btf); - obj->btf = NULL; - err = 0; - } + } else if (strcmp(name, MAPS_ELF_SEC) == 0) { + obj->efile.btf_maps_shndx = idx; + } else if (strcmp(name, BTF_ELF_SEC) == 0) { + btf_data = data; } else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) { btf_ext_data = data; } else if (sh.sh_type == SHT_SYMTAB) { if (obj->efile.symbols) { - pr_warning("bpf: multiple SYMTAB in %s\n", - obj->path); - err = -LIBBPF_ERRNO__FORMAT; - } else { - obj->efile.symbols = data; - obj->efile.strtabidx = sh.sh_link; + pr_warn("bpf: multiple SYMTAB in %s\n", + obj->path); + return -LIBBPF_ERRNO__FORMAT; } - } else if ((sh.sh_type == SHT_PROGBITS) && - (sh.sh_flags & SHF_EXECINSTR) && - (data->d_size > 0)) { - if (strcmp(name, ".text") == 0) - obj->efile.text_shndx = idx; - err = bpf_object__add_program(obj, data->d_buf, - data->d_size, name, idx); - if (err) { - char errmsg[STRERR_BUFSIZE]; - char *cp = libbpf_strerror_r(-err, errmsg, - sizeof(errmsg)); - - pr_warning("failed to alloc program %s (%s): %s", - name, obj->path, cp); + obj->efile.symbols = data; + obj->efile.strtabidx = sh.sh_link; + } else if (sh.sh_type == SHT_PROGBITS && data->d_size > 0) { + if (sh.sh_flags & SHF_EXECINSTR) { + if (strcmp(name, ".text") == 0) + obj->efile.text_shndx = idx; + err = bpf_object__add_program(obj, data->d_buf, + data->d_size, + name, idx); + if (err) { + char errmsg[STRERR_BUFSIZE]; + char *cp; + + cp = libbpf_strerror_r(-err, errmsg, + sizeof(errmsg)); + pr_warn("failed to alloc program %s (%s): %s", + name, obj->path, cp); + return err; + } + } else if (strcmp(name, ".data") == 0) { + obj->efile.data = data; + obj->efile.data_shndx = idx; + } else if (strcmp(name, ".rodata") == 0) { + obj->efile.rodata = data; + obj->efile.rodata_shndx = idx; + } else { + pr_debug("skip section(%d) %s\n", idx, name); } } else if (sh.sh_type == SHT_REL) { - void *reloc = obj->efile.reloc; - int nr_reloc = obj->efile.nr_reloc + 1; + int nr_sects = obj->efile.nr_reloc_sects; + void *sects = obj->efile.reloc_sects; int sec = sh.sh_info; /* points to other section */ /* Only do relo for section with exec instructions */ @@ -892,53 +1706,37 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) continue; } - reloc = reallocarray(reloc, nr_reloc, - sizeof(*obj->efile.reloc)); - if (!reloc) { - pr_warning("realloc failed\n"); - err = -ENOMEM; - } else { - int n = nr_reloc - 1; + sects = reallocarray(sects, nr_sects + 1, + sizeof(*obj->efile.reloc_sects)); + if (!sects) { + pr_warn("reloc_sects realloc failed\n"); + return -ENOMEM; + } - obj->efile.reloc = reloc; - obj->efile.nr_reloc = nr_reloc; + obj->efile.reloc_sects = sects; + obj->efile.nr_reloc_sects++; - obj->efile.reloc[n].shdr = sh; - obj->efile.reloc[n].data = data; - } + obj->efile.reloc_sects[nr_sects].shdr = sh; + obj->efile.reloc_sects[nr_sects].data = data; + } else if (sh.sh_type == SHT_NOBITS && strcmp(name, ".bss") == 0) { + obj->efile.bss = data; + obj->efile.bss_shndx = idx; } else { pr_debug("skip section(%d) %s\n", idx, name); } - if (err) - goto out; } - if (!obj->efile.strtabidx || obj->efile.strtabidx >= idx) { - pr_warning("Corrupted ELF file: index of strtab invalid\n"); - return LIBBPF_ERRNO__FORMAT; - } - if (btf_ext_data) { - if (!obj->btf) { - pr_debug("Ignore ELF section %s because its depending ELF section %s is not found.\n", - BTF_EXT_ELF_SEC, BTF_ELF_SEC); - } else { - obj->btf_ext = btf_ext__new(btf_ext_data->d_buf, - btf_ext_data->d_size); - if (IS_ERR(obj->btf_ext)) { - pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n", - BTF_EXT_ELF_SEC, - PTR_ERR(obj->btf_ext)); - obj->btf_ext = NULL; - } - } - } - if (obj->efile.maps_shndx >= 0) { - err = bpf_object__init_maps(obj, flags); - if (err) - goto out; + if (!obj->efile.strtabidx || obj->efile.strtabidx > idx) { + pr_warn("Corrupted ELF file: index of strtab invalid\n"); + return -LIBBPF_ERRNO__FORMAT; } - err = bpf_object__init_prog_names(obj); -out: + err = bpf_object__init_btf(obj, btf_data, btf_ext_data); + if (!err) + err = bpf_object__init_maps(obj, relaxed_maps, pin_root_path); + if (!err) + err = bpf_object__sanitize_and_load_btf(obj); + if (!err) + err = bpf_object__init_prog_names(obj); return err; } @@ -957,7 +1755,8 @@ bpf_object__find_prog_by_idx(struct bpf_object *obj, int idx) } struct bpf_program * -bpf_object__find_program_by_title(struct bpf_object *obj, const char *title) +bpf_object__find_program_by_title(const struct bpf_object *obj, + const char *title) { struct bpf_program *pos; @@ -968,115 +1767,222 @@ bpf_object__find_program_by_title(struct bpf_object *obj, const char *title) return NULL; } +static bool bpf_object__shndx_is_data(const struct bpf_object *obj, + int shndx) +{ + return shndx == obj->efile.data_shndx || + shndx == obj->efile.bss_shndx || + shndx == obj->efile.rodata_shndx; +} + +static bool bpf_object__shndx_is_maps(const struct bpf_object *obj, + int shndx) +{ + return shndx == obj->efile.maps_shndx || + shndx == obj->efile.btf_maps_shndx; +} + +static enum libbpf_map_type +bpf_object__section_to_libbpf_map_type(const struct bpf_object *obj, int shndx) +{ + if (shndx == obj->efile.data_shndx) + return LIBBPF_MAP_DATA; + else if (shndx == obj->efile.bss_shndx) + return LIBBPF_MAP_BSS; + else if (shndx == obj->efile.rodata_shndx) + return LIBBPF_MAP_RODATA; + else + return LIBBPF_MAP_UNSPEC; +} + +static int bpf_program__record_reloc(struct bpf_program *prog, + struct reloc_desc *reloc_desc, + __u32 insn_idx, const char *name, + const GElf_Sym *sym, const GElf_Rel *rel) +{ + struct bpf_insn *insn = &prog->insns[insn_idx]; + size_t map_idx, nr_maps = prog->obj->nr_maps; + struct bpf_object *obj = prog->obj; + __u32 shdr_idx = sym->st_shndx; + enum libbpf_map_type type; + struct bpf_map *map; + + /* sub-program call relocation */ + if (insn->code == (BPF_JMP | BPF_CALL)) { + if (insn->src_reg != BPF_PSEUDO_CALL) { + pr_warn("incorrect bpf_call opcode\n"); + return -LIBBPF_ERRNO__RELOC; + } + /* text_shndx can be 0, if no default "main" program exists */ + if (!shdr_idx || shdr_idx != obj->efile.text_shndx) { + pr_warn("bad call relo against section %u\n", shdr_idx); + return -LIBBPF_ERRNO__RELOC; + } + if (sym->st_value % 8) { + pr_warn("bad call relo offset: %lu\n", sym->st_value); + return -LIBBPF_ERRNO__RELOC; + } + reloc_desc->type = RELO_CALL; + reloc_desc->insn_idx = insn_idx; + reloc_desc->text_off = sym->st_value / 8; + obj->has_pseudo_calls = true; + return 0; + } + + if (insn->code != (BPF_LD | BPF_IMM | BPF_DW)) { + pr_warn("invalid relo for insns[%d].code 0x%x\n", + insn_idx, insn->code); + return -LIBBPF_ERRNO__RELOC; + } + if (!shdr_idx || shdr_idx >= SHN_LORESERVE) { + pr_warn("invalid relo for \'%s\' in special section 0x%x; forgot to initialize global var?..\n", + name, shdr_idx); + return -LIBBPF_ERRNO__RELOC; + } + + type = bpf_object__section_to_libbpf_map_type(obj, shdr_idx); + + /* generic map reference relocation */ + if (type == LIBBPF_MAP_UNSPEC) { + if (!bpf_object__shndx_is_maps(obj, shdr_idx)) { + pr_warn("bad map relo against section %u\n", + shdr_idx); + return -LIBBPF_ERRNO__RELOC; + } + for (map_idx = 0; map_idx < nr_maps; map_idx++) { + map = &obj->maps[map_idx]; + if (map->libbpf_type != type || + map->sec_idx != sym->st_shndx || + map->sec_offset != sym->st_value) + continue; + pr_debug("found map %zd (%s, sec %d, off %zu) for insn %u\n", + map_idx, map->name, map->sec_idx, + map->sec_offset, insn_idx); + break; + } + if (map_idx >= nr_maps) { + pr_warn("map relo failed to find map for sec %u, off %llu\n", + shdr_idx, (__u64)sym->st_value); + return -LIBBPF_ERRNO__RELOC; + } + reloc_desc->type = RELO_LD64; + reloc_desc->insn_idx = insn_idx; + reloc_desc->map_idx = map_idx; + return 0; + } + + /* global data map relocation */ + if (!bpf_object__shndx_is_data(obj, shdr_idx)) { + pr_warn("bad data relo against section %u\n", shdr_idx); + return -LIBBPF_ERRNO__RELOC; + } + if (!obj->caps.global_data) { + pr_warn("relocation: kernel does not support global \'%s\' variable access in insns[%d]\n", + name, insn_idx); + return -LIBBPF_ERRNO__RELOC; + } + for (map_idx = 0; map_idx < nr_maps; map_idx++) { + map = &obj->maps[map_idx]; + if (map->libbpf_type != type) + continue; + pr_debug("found data map %zd (%s, sec %d, off %zu) for insn %u\n", + map_idx, map->name, map->sec_idx, map->sec_offset, + insn_idx); + break; + } + if (map_idx >= nr_maps) { + pr_warn("data relo failed to find map for sec %u\n", + shdr_idx); + return -LIBBPF_ERRNO__RELOC; + } + + reloc_desc->type = RELO_DATA; + reloc_desc->insn_idx = insn_idx; + reloc_desc->map_idx = map_idx; + return 0; +} + static int bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, Elf_Data *data, struct bpf_object *obj) { Elf_Data *symbols = obj->efile.symbols; - int text_shndx = obj->efile.text_shndx; - int maps_shndx = obj->efile.maps_shndx; - struct bpf_map *maps = obj->maps; - size_t nr_maps = obj->nr_maps; - int i, nrels; - - pr_debug("collecting relocating info for: '%s'\n", - prog->section_name); + int err, i, nrels; + + pr_debug("collecting relocating info for: '%s'\n", prog->section_name); nrels = shdr->sh_size / shdr->sh_entsize; prog->reloc_desc = malloc(sizeof(*prog->reloc_desc) * nrels); if (!prog->reloc_desc) { - pr_warning("failed to alloc memory in relocation\n"); + pr_warn("failed to alloc memory in relocation\n"); return -ENOMEM; } prog->nr_reloc = nrels; for (i = 0; i < nrels; i++) { + const char *name; + __u32 insn_idx; GElf_Sym sym; GElf_Rel rel; - unsigned int insn_idx; - struct bpf_insn *insns = prog->insns; - size_t map_idx; if (!gelf_getrel(data, i, &rel)) { - pr_warning("relocation: failed to get %d reloc\n", i); + pr_warn("relocation: failed to get %d reloc\n", i); return -LIBBPF_ERRNO__FORMAT; } - - if (!gelf_getsym(symbols, - GELF_R_SYM(rel.r_info), - &sym)) { - pr_warning("relocation: symbol %"PRIx64" not found\n", - GELF_R_SYM(rel.r_info)); + if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) { + pr_warn("relocation: symbol %"PRIx64" not found\n", + GELF_R_SYM(rel.r_info)); return -LIBBPF_ERRNO__FORMAT; } - pr_debug("relo for %lld value %lld name %d\n", - (long long) (rel.r_info >> 32), - (long long) sym.st_value, sym.st_name); - - if (sym.st_shndx != maps_shndx && sym.st_shndx != text_shndx) { - pr_warning("Program '%s' contains non-map related relo data pointing to section %u\n", - prog->section_name, sym.st_shndx); - return -LIBBPF_ERRNO__RELOC; - } + if (rel.r_offset % sizeof(struct bpf_insn)) + return -LIBBPF_ERRNO__FORMAT; insn_idx = rel.r_offset / sizeof(struct bpf_insn); - pr_debug("relocation: insn_idx=%u\n", insn_idx); - - if (insns[insn_idx].code == (BPF_JMP | BPF_CALL)) { - if (insns[insn_idx].src_reg != BPF_PSEUDO_CALL) { - pr_warning("incorrect bpf_call opcode\n"); - return -LIBBPF_ERRNO__RELOC; - } - prog->reloc_desc[i].type = RELO_CALL; - prog->reloc_desc[i].insn_idx = insn_idx; - prog->reloc_desc[i].text_off = sym.st_value; - obj->has_pseudo_calls = true; - continue; - } - - if (insns[insn_idx].code != (BPF_LD | BPF_IMM | BPF_DW)) { - pr_warning("bpf: relocation: invalid relo for insns[%d].code 0x%x\n", - insn_idx, insns[insn_idx].code); - return -LIBBPF_ERRNO__RELOC; - } - - /* TODO: 'maps' is sorted. We can use bsearch to make it faster. */ - for (map_idx = 0; map_idx < nr_maps; map_idx++) { - if (maps[map_idx].offset == sym.st_value) { - pr_debug("relocation: find map %zd (%s) for insn %u\n", - map_idx, maps[map_idx].name, insn_idx); - break; - } - } + name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, + sym.st_name) ? : "<?>"; - if (map_idx >= nr_maps) { - pr_warning("bpf relocation: map_idx %d large than %d\n", - (int)map_idx, (int)nr_maps - 1); - return -LIBBPF_ERRNO__RELOC; - } + pr_debug("relo for shdr %u, symb %llu, value %llu, type %d, bind %d, name %d (\'%s\'), insn %u\n", + (__u32)sym.st_shndx, (__u64)GELF_R_SYM(rel.r_info), + (__u64)sym.st_value, GELF_ST_TYPE(sym.st_info), + GELF_ST_BIND(sym.st_info), sym.st_name, name, + insn_idx); - prog->reloc_desc[i].type = RELO_LD64; - prog->reloc_desc[i].insn_idx = insn_idx; - prog->reloc_desc[i].map_idx = map_idx; + err = bpf_program__record_reloc(prog, &prog->reloc_desc[i], + insn_idx, name, &sym, &rel); + if (err) + return err; } return 0; } -static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf) +static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map) { struct bpf_map_def *def = &map->def; - __u32 key_type_id, value_type_id; + __u32 key_type_id = 0, value_type_id = 0; int ret; - ret = btf__get_map_kv_tids(btf, map->name, def->key_size, - def->value_size, &key_type_id, - &value_type_id); - if (ret) + /* if it's BTF-defined map, we don't need to search for type IDs */ + if (map->sec_idx == obj->efile.btf_maps_shndx) + return 0; + + if (!bpf_map__is_internal(map)) { + ret = btf__get_map_kv_tids(obj->btf, map->name, def->key_size, + def->value_size, &key_type_id, + &value_type_id); + } else { + /* + * LLVM annotates global data differently in BTF, that is, + * only as '.data', '.bss' or '.rodata'. + */ + ret = btf__find_by_name(obj->btf, + libbpf_type_to_btf_name[map->libbpf_type]); + } + if (ret < 0) return ret; map->btf_key_type_id = key_type_id; - map->btf_value_type_id = value_type_id; - + map->btf_value_type_id = bpf_map__is_internal(map) ? + ret : value_type_id; return 0; } @@ -1096,16 +2002,22 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd) return -errno; new_fd = open("/", O_RDONLY | O_CLOEXEC); - if (new_fd < 0) + if (new_fd < 0) { + err = -errno; goto err_free_new_name; + } new_fd = dup3(fd, new_fd, O_CLOEXEC); - if (new_fd < 0) + if (new_fd < 0) { + err = -errno; goto err_close_new_fd; + } err = zclose(map->fd); - if (err) + if (err) { + err = -errno; goto err_close_new_fd; + } free(map->name); map->fd = new_fd; @@ -1117,6 +2029,7 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd) map->def.map_flags = info.map_flags; map->btf_key_type_id = info.btf_key_type_id; map->btf_value_type_id = info.btf_value_type_id; + map->reused = true; return 0; @@ -1124,7 +2037,7 @@ err_close_new_fd: close(new_fd); err_free_new_name: free(new_name); - return -errno; + return err; } int bpf_map__resize(struct bpf_map *map, __u32 max_entries) @@ -1163,8 +2076,8 @@ bpf_object__probe_name(struct bpf_object *obj) ret = bpf_load_program_xattr(&attr, NULL, 0); if (ret < 0) { cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); - pr_warning("Error in %s():%s(%d). Couldn't load basic 'r0 = 0' BPF program.\n", - __func__, cp, errno); + pr_warn("Error in %s():%s(%d). Couldn't load basic 'r0 = 0' BPF program.\n", + __func__, cp, errno); return -errno; } close(ret); @@ -1182,15 +2095,239 @@ bpf_object__probe_name(struct bpf_object *obj) } static int +bpf_object__probe_global_data(struct bpf_object *obj) +{ + struct bpf_load_program_attr prg_attr; + struct bpf_create_map_attr map_attr; + char *cp, errmsg[STRERR_BUFSIZE]; + struct bpf_insn insns[] = { + BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int ret, map; + + memset(&map_attr, 0, sizeof(map_attr)); + map_attr.map_type = BPF_MAP_TYPE_ARRAY; + map_attr.key_size = sizeof(int); + map_attr.value_size = 32; + map_attr.max_entries = 1; + + map = bpf_create_map_xattr(&map_attr); + if (map < 0) { + cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n", + __func__, cp, errno); + return -errno; + } + + insns[0].imm = map; + + memset(&prg_attr, 0, sizeof(prg_attr)); + prg_attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + prg_attr.insns = insns; + prg_attr.insns_cnt = ARRAY_SIZE(insns); + prg_attr.license = "GPL"; + + ret = bpf_load_program_xattr(&prg_attr, NULL, 0); + if (ret >= 0) { + obj->caps.global_data = 1; + close(ret); + } + + close(map); + return 0; +} + +static int bpf_object__probe_btf_func(struct bpf_object *obj) +{ + static const char strs[] = "\0int\0x\0a"; + /* void x(int a) {} */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* FUNC_PROTO */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0), + BTF_PARAM_ENC(7, 1), + /* FUNC x */ /* [3] */ + BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), 2), + }; + int btf_fd; + + btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs)); + if (btf_fd >= 0) { + obj->caps.btf_func = 1; + close(btf_fd); + return 1; + } + + return 0; +} + +static int bpf_object__probe_btf_datasec(struct bpf_object *obj) +{ + static const char strs[] = "\0x\0.data"; + /* static int a; */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* VAR x */ /* [2] */ + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), + BTF_VAR_STATIC, + /* DATASEC val */ /* [3] */ + BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4), + BTF_VAR_SECINFO_ENC(2, 0, 4), + }; + int btf_fd; + + btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs)); + if (btf_fd >= 0) { + obj->caps.btf_datasec = 1; + close(btf_fd); + return 1; + } + + return 0; +} + +static int bpf_object__probe_array_mmap(struct bpf_object *obj) +{ + struct bpf_create_map_attr attr = { + .map_type = BPF_MAP_TYPE_ARRAY, + .map_flags = BPF_F_MMAPABLE, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 1, + }; + int fd; + + fd = bpf_create_map_xattr(&attr); + if (fd >= 0) { + obj->caps.array_mmap = 1; + close(fd); + return 1; + } + + return 0; +} + +static int bpf_object__probe_caps(struct bpf_object *obj) { - return bpf_object__probe_name(obj); + int (*probe_fn[])(struct bpf_object *obj) = { + bpf_object__probe_name, + bpf_object__probe_global_data, + bpf_object__probe_btf_func, + bpf_object__probe_btf_datasec, + bpf_object__probe_array_mmap, + }; + int i, ret; + + for (i = 0; i < ARRAY_SIZE(probe_fn); i++) { + ret = probe_fn[i](obj); + if (ret < 0) + pr_debug("Probe #%d failed with %d.\n", i, ret); + } + + return 0; +} + +static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd) +{ + struct bpf_map_info map_info = {}; + char msg[STRERR_BUFSIZE]; + __u32 map_info_len; + + map_info_len = sizeof(map_info); + + if (bpf_obj_get_info_by_fd(map_fd, &map_info, &map_info_len)) { + pr_warn("failed to get map info for map FD %d: %s\n", + map_fd, libbpf_strerror_r(errno, msg, sizeof(msg))); + return false; + } + + return (map_info.type == map->def.type && + map_info.key_size == map->def.key_size && + map_info.value_size == map->def.value_size && + map_info.max_entries == map->def.max_entries && + map_info.map_flags == map->def.map_flags); +} + +static int +bpf_object__reuse_map(struct bpf_map *map) +{ + char *cp, errmsg[STRERR_BUFSIZE]; + int err, pin_fd; + + pin_fd = bpf_obj_get(map->pin_path); + if (pin_fd < 0) { + err = -errno; + if (err == -ENOENT) { + pr_debug("found no pinned map to reuse at '%s'\n", + map->pin_path); + return 0; + } + + cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg)); + pr_warn("couldn't retrieve pinned map '%s': %s\n", + map->pin_path, cp); + return err; + } + + if (!map_is_reuse_compat(map, pin_fd)) { + pr_warn("couldn't reuse pinned map at '%s': parameter mismatch\n", + map->pin_path); + close(pin_fd); + return -EINVAL; + } + + err = bpf_map__reuse_fd(map, pin_fd); + if (err) { + close(pin_fd); + return err; + } + map->pinned = true; + pr_debug("reused pinned map at '%s'\n", map->pin_path); + + return 0; +} + +static int +bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map) +{ + char *cp, errmsg[STRERR_BUFSIZE]; + int err, zero = 0; + __u8 *data; + + /* Nothing to do here since kernel already zero-initializes .bss map. */ + if (map->libbpf_type == LIBBPF_MAP_BSS) + return 0; + + data = map->libbpf_type == LIBBPF_MAP_DATA ? + obj->sections.data : obj->sections.rodata; + + err = bpf_map_update_elem(map->fd, &zero, data, 0); + /* Freeze .rodata map as read-only from syscall side. */ + if (!err && map->libbpf_type == LIBBPF_MAP_RODATA) { + err = bpf_map_freeze(map->fd); + if (err) { + cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + pr_warn("Error freezing map(%s) as read-only: %s\n", + map->name, cp); + err = 0; + } + } + return err; } static int bpf_object__create_maps(struct bpf_object *obj) { struct bpf_create_map_attr create_attr = {}; + int nr_cpus = 0; unsigned int i; int err; @@ -1200,6 +2337,15 @@ bpf_object__create_maps(struct bpf_object *obj) char *cp, errmsg[STRERR_BUFSIZE]; int *pfd = &map->fd; + if (map->pin_path) { + err = bpf_object__reuse_map(map); + if (err) { + pr_warn("error reusing pinned map %s\n", + map->name); + return err; + } + } + if (map->fd >= 0) { pr_debug("skip map create (preset) %s: fd=%d\n", map->name, map->fd); @@ -1213,7 +2359,22 @@ bpf_object__create_maps(struct bpf_object *obj) create_attr.map_flags = def->map_flags; create_attr.key_size = def->key_size; create_attr.value_size = def->value_size; - create_attr.max_entries = def->max_entries; + if (def->type == BPF_MAP_TYPE_PERF_EVENT_ARRAY && + !def->max_entries) { + if (!nr_cpus) + nr_cpus = libbpf_num_possible_cpus(); + if (nr_cpus < 0) { + pr_warn("failed to determine number of system CPUs: %d\n", + nr_cpus); + err = nr_cpus; + goto err_out; + } + pr_debug("map '%s': setting size to %d\n", + map->name, nr_cpus); + create_attr.max_entries = nr_cpus; + } else { + create_attr.max_entries = def->max_entries; + } create_attr.btf_fd = 0; create_attr.btf_key_type_id = 0; create_attr.btf_value_type_id = 0; @@ -1221,17 +2382,19 @@ bpf_object__create_maps(struct bpf_object *obj) map->inner_map_fd >= 0) create_attr.inner_map_fd = map->inner_map_fd; - if (obj->btf && !bpf_map_find_btf_info(map, obj->btf)) { + if (obj->btf && !bpf_map_find_btf_info(obj, map)) { create_attr.btf_fd = btf__fd(obj->btf); create_attr.btf_key_type_id = map->btf_key_type_id; create_attr.btf_value_type_id = map->btf_value_type_id; } *pfd = bpf_create_map_xattr(&create_attr); - if (*pfd < 0 && create_attr.btf_key_type_id) { - cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); - pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n", - map->name, cp, errno); + if (*pfd < 0 && (create_attr.btf_key_type_id || + create_attr.btf_value_type_id)) { + err = -errno; + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); + pr_warn("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n", + map->name, cp, err); create_attr.btf_fd = 0; create_attr.btf_key_type_id = 0; create_attr.btf_value_type_id = 0; @@ -1243,15 +2406,34 @@ bpf_object__create_maps(struct bpf_object *obj) if (*pfd < 0) { size_t j; - err = *pfd; - cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); - pr_warning("failed to create map (name: '%s'): %s\n", - map->name, cp); + err = -errno; +err_out: + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); + pr_warn("failed to create map (name: '%s'): %s(%d)\n", + map->name, cp, err); for (j = 0; j < i; j++) zclose(obj->maps[j].fd); return err; } - pr_debug("create map %s: fd=%d\n", map->name, *pfd); + + if (bpf_map__is_internal(map)) { + err = bpf_object__populate_internal_map(obj, map); + if (err < 0) { + zclose(*pfd); + goto err_out; + } + } + + if (map->pin_path && !map->pinned) { + err = bpf_map__pin(map, NULL); + if (err) { + pr_warn("failed to auto-pin map name '%s' at '%s'\n", + map->name, map->pin_path); + return err; + } + } + + pr_debug("created map %s: fd=%d\n", map->name, *pfd); } return 0; @@ -1262,8 +2444,8 @@ check_btf_ext_reloc_err(struct bpf_program *prog, int err, void *btf_prog_info, const char *info_name) { if (err != -ENOENT) { - pr_warning("Error in loading %s for sec %s.\n", - info_name, prog->section_name); + pr_warn("Error in loading %s for sec %s.\n", + info_name, prog->section_name); return err; } @@ -1272,20 +2454,16 @@ check_btf_ext_reloc_err(struct bpf_program *prog, int err, if (btf_prog_info) { /* * Some info has already been found but has problem - * in the last btf_ext reloc. Must have to error - * out. + * in the last btf_ext reloc. Must have to error out. */ - pr_warning("Error in relocating %s for sec %s.\n", - info_name, prog->section_name); + pr_warn("Error in relocating %s for sec %s.\n", + info_name, prog->section_name); return err; } - /* - * Have problem loading the very first info. Ignore - * the rest. - */ - pr_warning("Cannot find %s for main program sec %s. Ignore all %s.\n", - info_name, prog->section_name, info_name); + /* Have problem loading the very first info. Ignore the rest. */ + pr_warn("Cannot find %s for main program sec %s. Ignore all %s.\n", + info_name, prog->section_name, info_name); return 0; } @@ -1327,12 +2505,1051 @@ bpf_program_reloc_btf_ext(struct bpf_program *prog, struct bpf_object *obj, prog->line_info_rec_size = btf_ext__line_info_rec_size(obj->btf_ext); } - if (!insn_offset) - prog->btf_fd = btf__fd(obj->btf); + return 0; +} + +#define BPF_CORE_SPEC_MAX_LEN 64 + +/* represents BPF CO-RE field or array element accessor */ +struct bpf_core_accessor { + __u32 type_id; /* struct/union type or array element type */ + __u32 idx; /* field index or array index */ + const char *name; /* field name or NULL for array accessor */ +}; + +struct bpf_core_spec { + const struct btf *btf; + /* high-level spec: named fields and array indices only */ + struct bpf_core_accessor spec[BPF_CORE_SPEC_MAX_LEN]; + /* high-level spec length */ + int len; + /* raw, low-level spec: 1-to-1 with accessor spec string */ + int raw_spec[BPF_CORE_SPEC_MAX_LEN]; + /* raw spec length */ + int raw_len; + /* field bit offset represented by spec */ + __u32 bit_offset; +}; + +static bool str_is_empty(const char *s) +{ + return !s || !s[0]; +} + +/* + * Turn bpf_field_reloc into a low- and high-level spec representation, + * validating correctness along the way, as well as calculating resulting + * field bit offset, specified by accessor string. Low-level spec captures + * every single level of nestedness, including traversing anonymous + * struct/union members. High-level one only captures semantically meaningful + * "turning points": named fields and array indicies. + * E.g., for this case: + * + * struct sample { + * int __unimportant; + * struct { + * int __1; + * int __2; + * int a[7]; + * }; + * }; + * + * struct sample *s = ...; + * + * int x = &s->a[3]; // access string = '0:1:2:3' + * + * Low-level spec has 1:1 mapping with each element of access string (it's + * just a parsed access string representation): [0, 1, 2, 3]. + * + * High-level spec will capture only 3 points: + * - intial zero-index access by pointer (&s->... is the same as &s[0]...); + * - field 'a' access (corresponds to '2' in low-level spec); + * - array element #3 access (corresponds to '3' in low-level spec). + * + */ +static int bpf_core_spec_parse(const struct btf *btf, + __u32 type_id, + const char *spec_str, + struct bpf_core_spec *spec) +{ + int access_idx, parsed_len, i; + const struct btf_type *t; + const char *name; + __u32 id; + __s64 sz; + + if (str_is_empty(spec_str) || *spec_str == ':') + return -EINVAL; + + memset(spec, 0, sizeof(*spec)); + spec->btf = btf; + + /* parse spec_str="0:1:2:3:4" into array raw_spec=[0, 1, 2, 3, 4] */ + while (*spec_str) { + if (*spec_str == ':') + ++spec_str; + if (sscanf(spec_str, "%d%n", &access_idx, &parsed_len) != 1) + return -EINVAL; + if (spec->raw_len == BPF_CORE_SPEC_MAX_LEN) + return -E2BIG; + spec_str += parsed_len; + spec->raw_spec[spec->raw_len++] = access_idx; + } + + if (spec->raw_len == 0) + return -EINVAL; + + /* first spec value is always reloc type array index */ + t = skip_mods_and_typedefs(btf, type_id, &id); + if (!t) + return -EINVAL; + + access_idx = spec->raw_spec[0]; + spec->spec[0].type_id = id; + spec->spec[0].idx = access_idx; + spec->len++; + + sz = btf__resolve_size(btf, id); + if (sz < 0) + return sz; + spec->bit_offset = access_idx * sz * 8; + + for (i = 1; i < spec->raw_len; i++) { + t = skip_mods_and_typedefs(btf, id, &id); + if (!t) + return -EINVAL; + + access_idx = spec->raw_spec[i]; + + if (btf_is_composite(t)) { + const struct btf_member *m; + __u32 bit_offset; + + if (access_idx >= btf_vlen(t)) + return -EINVAL; + + bit_offset = btf_member_bit_offset(t, access_idx); + spec->bit_offset += bit_offset; + + m = btf_members(t) + access_idx; + if (m->name_off) { + name = btf__name_by_offset(btf, m->name_off); + if (str_is_empty(name)) + return -EINVAL; + + spec->spec[spec->len].type_id = id; + spec->spec[spec->len].idx = access_idx; + spec->spec[spec->len].name = name; + spec->len++; + } + + id = m->type; + } else if (btf_is_array(t)) { + const struct btf_array *a = btf_array(t); + + t = skip_mods_and_typedefs(btf, a->type, &id); + if (!t || access_idx >= a->nelems) + return -EINVAL; + + spec->spec[spec->len].type_id = id; + spec->spec[spec->len].idx = access_idx; + spec->len++; + + sz = btf__resolve_size(btf, id); + if (sz < 0) + return sz; + spec->bit_offset += access_idx * sz * 8; + } else { + pr_warn("relo for [%u] %s (at idx %d) captures type [%d] of unexpected kind %d\n", + type_id, spec_str, i, id, btf_kind(t)); + return -EINVAL; + } + } + + return 0; +} + +static bool bpf_core_is_flavor_sep(const char *s) +{ + /* check X___Y name pattern, where X and Y are not underscores */ + return s[0] != '_' && /* X */ + s[1] == '_' && s[2] == '_' && s[3] == '_' && /* ___ */ + s[4] != '_'; /* Y */ +} + +/* Given 'some_struct_name___with_flavor' return the length of a name prefix + * before last triple underscore. Struct name part after last triple + * underscore is ignored by BPF CO-RE relocation during relocation matching. + */ +static size_t bpf_core_essential_name_len(const char *name) +{ + size_t n = strlen(name); + int i; + + for (i = n - 5; i >= 0; i--) { + if (bpf_core_is_flavor_sep(name + i)) + return i + 1; + } + return n; +} + +/* dynamically sized list of type IDs */ +struct ids_vec { + __u32 *data; + int len; +}; + +static void bpf_core_free_cands(struct ids_vec *cand_ids) +{ + free(cand_ids->data); + free(cand_ids); +} + +static struct ids_vec *bpf_core_find_cands(const struct btf *local_btf, + __u32 local_type_id, + const struct btf *targ_btf) +{ + size_t local_essent_len, targ_essent_len; + const char *local_name, *targ_name; + const struct btf_type *t; + struct ids_vec *cand_ids; + __u32 *new_ids; + int i, err, n; + + t = btf__type_by_id(local_btf, local_type_id); + if (!t) + return ERR_PTR(-EINVAL); + + local_name = btf__name_by_offset(local_btf, t->name_off); + if (str_is_empty(local_name)) + return ERR_PTR(-EINVAL); + local_essent_len = bpf_core_essential_name_len(local_name); + + cand_ids = calloc(1, sizeof(*cand_ids)); + if (!cand_ids) + return ERR_PTR(-ENOMEM); + + n = btf__get_nr_types(targ_btf); + for (i = 1; i <= n; i++) { + t = btf__type_by_id(targ_btf, i); + targ_name = btf__name_by_offset(targ_btf, t->name_off); + if (str_is_empty(targ_name)) + continue; + + targ_essent_len = bpf_core_essential_name_len(targ_name); + if (targ_essent_len != local_essent_len) + continue; + + if (strncmp(local_name, targ_name, local_essent_len) == 0) { + pr_debug("[%d] %s: found candidate [%d] %s\n", + local_type_id, local_name, i, targ_name); + new_ids = realloc(cand_ids->data, cand_ids->len + 1); + if (!new_ids) { + err = -ENOMEM; + goto err_out; + } + cand_ids->data = new_ids; + cand_ids->data[cand_ids->len++] = i; + } + } + return cand_ids; +err_out: + bpf_core_free_cands(cand_ids); + return ERR_PTR(err); +} + +/* Check two types for compatibility, skipping const/volatile/restrict and + * typedefs, to ensure we are relocating compatible entities: + * - any two STRUCTs/UNIONs are compatible and can be mixed; + * - any two FWDs are compatible, if their names match (modulo flavor suffix); + * - any two PTRs are always compatible; + * - for ENUMs, names should be the same (ignoring flavor suffix) or at + * least one of enums should be anonymous; + * - for ENUMs, check sizes, names are ignored; + * - for INT, size and signedness are ignored; + * - for ARRAY, dimensionality is ignored, element types are checked for + * compatibility recursively; + * - everything else shouldn't be ever a target of relocation. + * These rules are not set in stone and probably will be adjusted as we get + * more experience with using BPF CO-RE relocations. + */ +static int bpf_core_fields_are_compat(const struct btf *local_btf, + __u32 local_id, + const struct btf *targ_btf, + __u32 targ_id) +{ + const struct btf_type *local_type, *targ_type; + +recur: + local_type = skip_mods_and_typedefs(local_btf, local_id, &local_id); + targ_type = skip_mods_and_typedefs(targ_btf, targ_id, &targ_id); + if (!local_type || !targ_type) + return -EINVAL; + + if (btf_is_composite(local_type) && btf_is_composite(targ_type)) + return 1; + if (btf_kind(local_type) != btf_kind(targ_type)) + return 0; + + switch (btf_kind(local_type)) { + case BTF_KIND_PTR: + return 1; + case BTF_KIND_FWD: + case BTF_KIND_ENUM: { + const char *local_name, *targ_name; + size_t local_len, targ_len; + + local_name = btf__name_by_offset(local_btf, + local_type->name_off); + targ_name = btf__name_by_offset(targ_btf, targ_type->name_off); + local_len = bpf_core_essential_name_len(local_name); + targ_len = bpf_core_essential_name_len(targ_name); + /* one of them is anonymous or both w/ same flavor-less names */ + return local_len == 0 || targ_len == 0 || + (local_len == targ_len && + strncmp(local_name, targ_name, local_len) == 0); + } + case BTF_KIND_INT: + /* just reject deprecated bitfield-like integers; all other + * integers are by default compatible between each other + */ + return btf_int_offset(local_type) == 0 && + btf_int_offset(targ_type) == 0; + case BTF_KIND_ARRAY: + local_id = btf_array(local_type)->type; + targ_id = btf_array(targ_type)->type; + goto recur; + default: + pr_warn("unexpected kind %d relocated, local [%d], target [%d]\n", + btf_kind(local_type), local_id, targ_id); + return 0; + } +} + +/* + * Given single high-level named field accessor in local type, find + * corresponding high-level accessor for a target type. Along the way, + * maintain low-level spec for target as well. Also keep updating target + * bit offset. + * + * Searching is performed through recursive exhaustive enumeration of all + * fields of a struct/union. If there are any anonymous (embedded) + * structs/unions, they are recursively searched as well. If field with + * desired name is found, check compatibility between local and target types, + * before returning result. + * + * 1 is returned, if field is found. + * 0 is returned if no compatible field is found. + * <0 is returned on error. + */ +static int bpf_core_match_member(const struct btf *local_btf, + const struct bpf_core_accessor *local_acc, + const struct btf *targ_btf, + __u32 targ_id, + struct bpf_core_spec *spec, + __u32 *next_targ_id) +{ + const struct btf_type *local_type, *targ_type; + const struct btf_member *local_member, *m; + const char *local_name, *targ_name; + __u32 local_id; + int i, n, found; + + targ_type = skip_mods_and_typedefs(targ_btf, targ_id, &targ_id); + if (!targ_type) + return -EINVAL; + if (!btf_is_composite(targ_type)) + return 0; + + local_id = local_acc->type_id; + local_type = btf__type_by_id(local_btf, local_id); + local_member = btf_members(local_type) + local_acc->idx; + local_name = btf__name_by_offset(local_btf, local_member->name_off); + + n = btf_vlen(targ_type); + m = btf_members(targ_type); + for (i = 0; i < n; i++, m++) { + __u32 bit_offset; + + bit_offset = btf_member_bit_offset(targ_type, i); + + /* too deep struct/union/array nesting */ + if (spec->raw_len == BPF_CORE_SPEC_MAX_LEN) + return -E2BIG; + + /* speculate this member will be the good one */ + spec->bit_offset += bit_offset; + spec->raw_spec[spec->raw_len++] = i; + + targ_name = btf__name_by_offset(targ_btf, m->name_off); + if (str_is_empty(targ_name)) { + /* embedded struct/union, we need to go deeper */ + found = bpf_core_match_member(local_btf, local_acc, + targ_btf, m->type, + spec, next_targ_id); + if (found) /* either found or error */ + return found; + } else if (strcmp(local_name, targ_name) == 0) { + /* matching named field */ + struct bpf_core_accessor *targ_acc; + + targ_acc = &spec->spec[spec->len++]; + targ_acc->type_id = targ_id; + targ_acc->idx = i; + targ_acc->name = targ_name; + + *next_targ_id = m->type; + found = bpf_core_fields_are_compat(local_btf, + local_member->type, + targ_btf, m->type); + if (!found) + spec->len--; /* pop accessor */ + return found; + } + /* member turned out not to be what we looked for */ + spec->bit_offset -= bit_offset; + spec->raw_len--; + } return 0; } +/* + * Try to match local spec to a target type and, if successful, produce full + * target spec (high-level, low-level + bit offset). + */ +static int bpf_core_spec_match(struct bpf_core_spec *local_spec, + const struct btf *targ_btf, __u32 targ_id, + struct bpf_core_spec *targ_spec) +{ + const struct btf_type *targ_type; + const struct bpf_core_accessor *local_acc; + struct bpf_core_accessor *targ_acc; + int i, sz, matched; + + memset(targ_spec, 0, sizeof(*targ_spec)); + targ_spec->btf = targ_btf; + + local_acc = &local_spec->spec[0]; + targ_acc = &targ_spec->spec[0]; + + for (i = 0; i < local_spec->len; i++, local_acc++, targ_acc++) { + targ_type = skip_mods_and_typedefs(targ_spec->btf, targ_id, + &targ_id); + if (!targ_type) + return -EINVAL; + + if (local_acc->name) { + matched = bpf_core_match_member(local_spec->btf, + local_acc, + targ_btf, targ_id, + targ_spec, &targ_id); + if (matched <= 0) + return matched; + } else { + /* for i=0, targ_id is already treated as array element + * type (because it's the original struct), for others + * we should find array element type first + */ + if (i > 0) { + const struct btf_array *a; + + if (!btf_is_array(targ_type)) + return 0; + + a = btf_array(targ_type); + if (local_acc->idx >= a->nelems) + return 0; + if (!skip_mods_and_typedefs(targ_btf, a->type, + &targ_id)) + return -EINVAL; + } + + /* too deep struct/union/array nesting */ + if (targ_spec->raw_len == BPF_CORE_SPEC_MAX_LEN) + return -E2BIG; + + targ_acc->type_id = targ_id; + targ_acc->idx = local_acc->idx; + targ_acc->name = NULL; + targ_spec->len++; + targ_spec->raw_spec[targ_spec->raw_len] = targ_acc->idx; + targ_spec->raw_len++; + + sz = btf__resolve_size(targ_btf, targ_id); + if (sz < 0) + return sz; + targ_spec->bit_offset += local_acc->idx * sz * 8; + } + } + + return 1; +} + +static int bpf_core_calc_field_relo(const struct bpf_program *prog, + const struct bpf_field_reloc *relo, + const struct bpf_core_spec *spec, + __u32 *val, bool *validate) +{ + const struct bpf_core_accessor *acc = &spec->spec[spec->len - 1]; + const struct btf_type *t = btf__type_by_id(spec->btf, acc->type_id); + __u32 byte_off, byte_sz, bit_off, bit_sz; + const struct btf_member *m; + const struct btf_type *mt; + bool bitfield; + __s64 sz; + + /* a[n] accessor needs special handling */ + if (!acc->name) { + if (relo->kind == BPF_FIELD_BYTE_OFFSET) { + *val = spec->bit_offset / 8; + } else if (relo->kind == BPF_FIELD_BYTE_SIZE) { + sz = btf__resolve_size(spec->btf, acc->type_id); + if (sz < 0) + return -EINVAL; + *val = sz; + } else { + pr_warn("prog '%s': relo %d at insn #%d can't be applied to array access\n", + bpf_program__title(prog, false), + relo->kind, relo->insn_off / 8); + return -EINVAL; + } + if (validate) + *validate = true; + return 0; + } + + m = btf_members(t) + acc->idx; + mt = skip_mods_and_typedefs(spec->btf, m->type, NULL); + bit_off = spec->bit_offset; + bit_sz = btf_member_bitfield_size(t, acc->idx); + + bitfield = bit_sz > 0; + if (bitfield) { + byte_sz = mt->size; + byte_off = bit_off / 8 / byte_sz * byte_sz; + /* figure out smallest int size necessary for bitfield load */ + while (bit_off + bit_sz - byte_off * 8 > byte_sz * 8) { + if (byte_sz >= 8) { + /* bitfield can't be read with 64-bit read */ + pr_warn("prog '%s': relo %d at insn #%d can't be satisfied for bitfield\n", + bpf_program__title(prog, false), + relo->kind, relo->insn_off / 8); + return -E2BIG; + } + byte_sz *= 2; + byte_off = bit_off / 8 / byte_sz * byte_sz; + } + } else { + sz = btf__resolve_size(spec->btf, m->type); + if (sz < 0) + return -EINVAL; + byte_sz = sz; + byte_off = spec->bit_offset / 8; + bit_sz = byte_sz * 8; + } + + /* for bitfields, all the relocatable aspects are ambiguous and we + * might disagree with compiler, so turn off validation of expected + * value, except for signedness + */ + if (validate) + *validate = !bitfield; + + switch (relo->kind) { + case BPF_FIELD_BYTE_OFFSET: + *val = byte_off; + break; + case BPF_FIELD_BYTE_SIZE: + *val = byte_sz; + break; + case BPF_FIELD_SIGNED: + /* enums will be assumed unsigned */ + *val = btf_is_enum(mt) || + (btf_int_encoding(mt) & BTF_INT_SIGNED); + if (validate) + *validate = true; /* signedness is never ambiguous */ + break; + case BPF_FIELD_LSHIFT_U64: +#if __BYTE_ORDER == __LITTLE_ENDIAN + *val = 64 - (bit_off + bit_sz - byte_off * 8); +#else + *val = (8 - byte_sz) * 8 + (bit_off - byte_off * 8); +#endif + break; + case BPF_FIELD_RSHIFT_U64: + *val = 64 - bit_sz; + if (validate) + *validate = true; /* right shift is never ambiguous */ + break; + case BPF_FIELD_EXISTS: + default: + pr_warn("prog '%s': unknown relo %d at insn #%d\n", + bpf_program__title(prog, false), + relo->kind, relo->insn_off / 8); + return -EINVAL; + } + + return 0; +} + +/* + * Patch relocatable BPF instruction. + * + * Patched value is determined by relocation kind and target specification. + * For field existence relocation target spec will be NULL if field is not + * found. + * Expected insn->imm value is determined using relocation kind and local + * spec, and is checked before patching instruction. If actual insn->imm value + * is wrong, bail out with error. + * + * Currently three kinds of BPF instructions are supported: + * 1. rX = <imm> (assignment with immediate operand); + * 2. rX += <imm> (arithmetic operations with immediate operand); + */ +static int bpf_core_reloc_insn(struct bpf_program *prog, + const struct bpf_field_reloc *relo, + const struct bpf_core_spec *local_spec, + const struct bpf_core_spec *targ_spec) +{ + bool failed = false, validate = true; + __u32 orig_val, new_val; + struct bpf_insn *insn; + int insn_idx, err; + __u8 class; + + if (relo->insn_off % sizeof(struct bpf_insn)) + return -EINVAL; + insn_idx = relo->insn_off / sizeof(struct bpf_insn); + + if (relo->kind == BPF_FIELD_EXISTS) { + orig_val = 1; /* can't generate EXISTS relo w/o local field */ + new_val = targ_spec ? 1 : 0; + } else if (!targ_spec) { + failed = true; + new_val = (__u32)-1; + } else { + err = bpf_core_calc_field_relo(prog, relo, local_spec, + &orig_val, &validate); + if (err) + return err; + err = bpf_core_calc_field_relo(prog, relo, targ_spec, + &new_val, NULL); + if (err) + return err; + } + + insn = &prog->insns[insn_idx]; + class = BPF_CLASS(insn->code); + + if (class == BPF_ALU || class == BPF_ALU64) { + if (BPF_SRC(insn->code) != BPF_K) + return -EINVAL; + if (!failed && validate && insn->imm != orig_val) { + pr_warn("prog '%s': unexpected insn #%d value: got %u, exp %u -> %u\n", + bpf_program__title(prog, false), insn_idx, + insn->imm, orig_val, new_val); + return -EINVAL; + } + orig_val = insn->imm; + insn->imm = new_val; + pr_debug("prog '%s': patched insn #%d (ALU/ALU64)%s imm %u -> %u\n", + bpf_program__title(prog, false), insn_idx, + failed ? " w/ failed reloc" : "", orig_val, new_val); + } else { + pr_warn("prog '%s': trying to relocate unrecognized insn #%d, code:%x, src:%x, dst:%x, off:%x, imm:%x\n", + bpf_program__title(prog, false), + insn_idx, insn->code, insn->src_reg, insn->dst_reg, + insn->off, insn->imm); + return -EINVAL; + } + + return 0; +} + +static struct btf *btf_load_raw(const char *path) +{ + struct btf *btf; + size_t read_cnt; + struct stat st; + void *data; + FILE *f; + + if (stat(path, &st)) + return ERR_PTR(-errno); + + data = malloc(st.st_size); + if (!data) + return ERR_PTR(-ENOMEM); + + f = fopen(path, "rb"); + if (!f) { + btf = ERR_PTR(-errno); + goto cleanup; + } + + read_cnt = fread(data, 1, st.st_size, f); + fclose(f); + if (read_cnt < st.st_size) { + btf = ERR_PTR(-EBADF); + goto cleanup; + } + + btf = btf__new(data, read_cnt); + +cleanup: + free(data); + return btf; +} + +/* + * Probe few well-known locations for vmlinux kernel image and try to load BTF + * data out of it to use for target BTF. + */ +static struct btf *bpf_core_find_kernel_btf(void) +{ + struct { + const char *path_fmt; + bool raw_btf; + } locations[] = { + /* try canonical vmlinux BTF through sysfs first */ + { "/sys/kernel/btf/vmlinux", true /* raw BTF */ }, + /* fall back to trying to find vmlinux ELF on disk otherwise */ + { "/boot/vmlinux-%1$s" }, + { "/lib/modules/%1$s/vmlinux-%1$s" }, + { "/lib/modules/%1$s/build/vmlinux" }, + { "/usr/lib/modules/%1$s/kernel/vmlinux" }, + { "/usr/lib/debug/boot/vmlinux-%1$s" }, + { "/usr/lib/debug/boot/vmlinux-%1$s.debug" }, + { "/usr/lib/debug/lib/modules/%1$s/vmlinux" }, + }; + char path[PATH_MAX + 1]; + struct utsname buf; + struct btf *btf; + int i; + + uname(&buf); + + for (i = 0; i < ARRAY_SIZE(locations); i++) { + snprintf(path, PATH_MAX, locations[i].path_fmt, buf.release); + + if (access(path, R_OK)) + continue; + + if (locations[i].raw_btf) + btf = btf_load_raw(path); + else + btf = btf__parse_elf(path, NULL); + + pr_debug("loading kernel BTF '%s': %ld\n", + path, IS_ERR(btf) ? PTR_ERR(btf) : 0); + if (IS_ERR(btf)) + continue; + + return btf; + } + + pr_warn("failed to find valid kernel BTF\n"); + return ERR_PTR(-ESRCH); +} + +/* Output spec definition in the format: + * [<type-id>] (<type-name>) + <raw-spec> => <offset>@<spec>, + * where <spec> is a C-syntax view of recorded field access, e.g.: x.a[3].b + */ +static void bpf_core_dump_spec(int level, const struct bpf_core_spec *spec) +{ + const struct btf_type *t; + const char *s; + __u32 type_id; + int i; + + type_id = spec->spec[0].type_id; + t = btf__type_by_id(spec->btf, type_id); + s = btf__name_by_offset(spec->btf, t->name_off); + libbpf_print(level, "[%u] %s + ", type_id, s); + + for (i = 0; i < spec->raw_len; i++) + libbpf_print(level, "%d%s", spec->raw_spec[i], + i == spec->raw_len - 1 ? " => " : ":"); + + libbpf_print(level, "%u.%u @ &x", + spec->bit_offset / 8, spec->bit_offset % 8); + + for (i = 0; i < spec->len; i++) { + if (spec->spec[i].name) + libbpf_print(level, ".%s", spec->spec[i].name); + else + libbpf_print(level, "[%u]", spec->spec[i].idx); + } + +} + +static size_t bpf_core_hash_fn(const void *key, void *ctx) +{ + return (size_t)key; +} + +static bool bpf_core_equal_fn(const void *k1, const void *k2, void *ctx) +{ + return k1 == k2; +} + +static void *u32_as_hash_key(__u32 x) +{ + return (void *)(uintptr_t)x; +} + +/* + * CO-RE relocate single instruction. + * + * The outline and important points of the algorithm: + * 1. For given local type, find corresponding candidate target types. + * Candidate type is a type with the same "essential" name, ignoring + * everything after last triple underscore (___). E.g., `sample`, + * `sample___flavor_one`, `sample___flavor_another_one`, are all candidates + * for each other. Names with triple underscore are referred to as + * "flavors" and are useful, among other things, to allow to + * specify/support incompatible variations of the same kernel struct, which + * might differ between different kernel versions and/or build + * configurations. + * + * N.B. Struct "flavors" could be generated by bpftool's BTF-to-C + * converter, when deduplicated BTF of a kernel still contains more than + * one different types with the same name. In that case, ___2, ___3, etc + * are appended starting from second name conflict. But start flavors are + * also useful to be defined "locally", in BPF program, to extract same + * data from incompatible changes between different kernel + * versions/configurations. For instance, to handle field renames between + * kernel versions, one can use two flavors of the struct name with the + * same common name and use conditional relocations to extract that field, + * depending on target kernel version. + * 2. For each candidate type, try to match local specification to this + * candidate target type. Matching involves finding corresponding + * high-level spec accessors, meaning that all named fields should match, + * as well as all array accesses should be within the actual bounds. Also, + * types should be compatible (see bpf_core_fields_are_compat for details). + * 3. It is supported and expected that there might be multiple flavors + * matching the spec. As long as all the specs resolve to the same set of + * offsets across all candidates, there is no error. If there is any + * ambiguity, CO-RE relocation will fail. This is necessary to accomodate + * imprefection of BTF deduplication, which can cause slight duplication of + * the same BTF type, if some directly or indirectly referenced (by + * pointer) type gets resolved to different actual types in different + * object files. If such situation occurs, deduplicated BTF will end up + * with two (or more) structurally identical types, which differ only in + * types they refer to through pointer. This should be OK in most cases and + * is not an error. + * 4. Candidate types search is performed by linearly scanning through all + * types in target BTF. It is anticipated that this is overall more + * efficient memory-wise and not significantly worse (if not better) + * CPU-wise compared to prebuilding a map from all local type names to + * a list of candidate type names. It's also sped up by caching resolved + * list of matching candidates per each local "root" type ID, that has at + * least one bpf_field_reloc associated with it. This list is shared + * between multiple relocations for the same type ID and is updated as some + * of the candidates are pruned due to structural incompatibility. + */ +static int bpf_core_reloc_field(struct bpf_program *prog, + const struct bpf_field_reloc *relo, + int relo_idx, + const struct btf *local_btf, + const struct btf *targ_btf, + struct hashmap *cand_cache) +{ + const char *prog_name = bpf_program__title(prog, false); + struct bpf_core_spec local_spec, cand_spec, targ_spec; + const void *type_key = u32_as_hash_key(relo->type_id); + const struct btf_type *local_type, *cand_type; + const char *local_name, *cand_name; + struct ids_vec *cand_ids; + __u32 local_id, cand_id; + const char *spec_str; + int i, j, err; + + local_id = relo->type_id; + local_type = btf__type_by_id(local_btf, local_id); + if (!local_type) + return -EINVAL; + + local_name = btf__name_by_offset(local_btf, local_type->name_off); + if (str_is_empty(local_name)) + return -EINVAL; + + spec_str = btf__name_by_offset(local_btf, relo->access_str_off); + if (str_is_empty(spec_str)) + return -EINVAL; + + err = bpf_core_spec_parse(local_btf, local_id, spec_str, &local_spec); + if (err) { + pr_warn("prog '%s': relo #%d: parsing [%d] %s + %s failed: %d\n", + prog_name, relo_idx, local_id, local_name, spec_str, + err); + return -EINVAL; + } + + pr_debug("prog '%s': relo #%d: kind %d, spec is ", prog_name, relo_idx, + relo->kind); + bpf_core_dump_spec(LIBBPF_DEBUG, &local_spec); + libbpf_print(LIBBPF_DEBUG, "\n"); + + if (!hashmap__find(cand_cache, type_key, (void **)&cand_ids)) { + cand_ids = bpf_core_find_cands(local_btf, local_id, targ_btf); + if (IS_ERR(cand_ids)) { + pr_warn("prog '%s': relo #%d: target candidate search failed for [%d] %s: %ld", + prog_name, relo_idx, local_id, local_name, + PTR_ERR(cand_ids)); + return PTR_ERR(cand_ids); + } + err = hashmap__set(cand_cache, type_key, cand_ids, NULL, NULL); + if (err) { + bpf_core_free_cands(cand_ids); + return err; + } + } + + for (i = 0, j = 0; i < cand_ids->len; i++) { + cand_id = cand_ids->data[i]; + cand_type = btf__type_by_id(targ_btf, cand_id); + cand_name = btf__name_by_offset(targ_btf, cand_type->name_off); + + err = bpf_core_spec_match(&local_spec, targ_btf, + cand_id, &cand_spec); + pr_debug("prog '%s': relo #%d: matching candidate #%d %s against spec ", + prog_name, relo_idx, i, cand_name); + bpf_core_dump_spec(LIBBPF_DEBUG, &cand_spec); + libbpf_print(LIBBPF_DEBUG, ": %d\n", err); + if (err < 0) { + pr_warn("prog '%s': relo #%d: matching error: %d\n", + prog_name, relo_idx, err); + return err; + } + if (err == 0) + continue; + + if (j == 0) { + targ_spec = cand_spec; + } else if (cand_spec.bit_offset != targ_spec.bit_offset) { + /* if there are many candidates, they should all + * resolve to the same bit offset + */ + pr_warn("prog '%s': relo #%d: offset ambiguity: %u != %u\n", + prog_name, relo_idx, cand_spec.bit_offset, + targ_spec.bit_offset); + return -EINVAL; + } + + cand_ids->data[j++] = cand_spec.spec[0].type_id; + } + + /* + * For BPF_FIELD_EXISTS relo or when relaxed CO-RE reloc mode is + * requested, it's expected that we might not find any candidates. + * In this case, if field wasn't found in any candidate, the list of + * candidates shouldn't change at all, we'll just handle relocating + * appropriately, depending on relo's kind. + */ + if (j > 0) + cand_ids->len = j; + + if (j == 0 && !prog->obj->relaxed_core_relocs && + relo->kind != BPF_FIELD_EXISTS) { + pr_warn("prog '%s': relo #%d: no matching targets found for [%d] %s + %s\n", + prog_name, relo_idx, local_id, local_name, spec_str); + return -ESRCH; + } + + /* bpf_core_reloc_insn should know how to handle missing targ_spec */ + err = bpf_core_reloc_insn(prog, relo, &local_spec, + j ? &targ_spec : NULL); + if (err) { + pr_warn("prog '%s': relo #%d: failed to patch insn at offset %d: %d\n", + prog_name, relo_idx, relo->insn_off, err); + return -EINVAL; + } + + return 0; +} + +static int +bpf_core_reloc_fields(struct bpf_object *obj, const char *targ_btf_path) +{ + const struct btf_ext_info_sec *sec; + const struct bpf_field_reloc *rec; + const struct btf_ext_info *seg; + struct hashmap_entry *entry; + struct hashmap *cand_cache = NULL; + struct bpf_program *prog; + struct btf *targ_btf; + const char *sec_name; + int i, err = 0; + + if (targ_btf_path) + targ_btf = btf__parse_elf(targ_btf_path, NULL); + else + targ_btf = bpf_core_find_kernel_btf(); + if (IS_ERR(targ_btf)) { + pr_warn("failed to get target BTF: %ld\n", PTR_ERR(targ_btf)); + return PTR_ERR(targ_btf); + } + + cand_cache = hashmap__new(bpf_core_hash_fn, bpf_core_equal_fn, NULL); + if (IS_ERR(cand_cache)) { + err = PTR_ERR(cand_cache); + goto out; + } + + seg = &obj->btf_ext->field_reloc_info; + for_each_btf_ext_sec(seg, sec) { + sec_name = btf__name_by_offset(obj->btf, sec->sec_name_off); + if (str_is_empty(sec_name)) { + err = -EINVAL; + goto out; + } + prog = bpf_object__find_program_by_title(obj, sec_name); + if (!prog) { + pr_warn("failed to find program '%s' for CO-RE offset relocation\n", + sec_name); + err = -EINVAL; + goto out; + } + + pr_debug("prog '%s': performing %d CO-RE offset relocs\n", + sec_name, sec->num_info); + + for_each_btf_ext_rec(seg, sec, i, rec) { + err = bpf_core_reloc_field(prog, rec, i, obj->btf, + targ_btf, cand_cache); + if (err) { + pr_warn("prog '%s': relo #%d: failed to relocate: %d\n", + sec_name, i, err); + goto out; + } + } + } + +out: + btf__free(targ_btf); + if (!IS_ERR_OR_NULL(cand_cache)) { + hashmap__for_each_entry(cand_cache, entry, i) { + bpf_core_free_cands(entry->value); + } + hashmap__free(cand_cache); + } + return err; +} + +static int +bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path) +{ + int err = 0; + + if (obj->btf_ext->field_reloc_info.len) + err = bpf_core_reloc_fields(obj, targ_btf_path); + + return err; +} + static int bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj, struct reloc_desc *relo) @@ -1346,23 +3563,24 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj, return -LIBBPF_ERRNO__RELOC; if (prog->idx == obj->efile.text_shndx) { - pr_warning("relo in .text insn %d into off %d\n", - relo->insn_idx, relo->text_off); + pr_warn("relo in .text insn %d into off %d\n", + relo->insn_idx, relo->text_off); return -LIBBPF_ERRNO__RELOC; } if (prog->main_prog_cnt == 0) { text = bpf_object__find_prog_by_idx(obj, obj->efile.text_shndx); if (!text) { - pr_warning("no .text section found yet relo into text exist\n"); + pr_warn("no .text section found yet relo into text exist\n"); return -LIBBPF_ERRNO__RELOC; } new_cnt = prog->insns_cnt + text->insns_cnt; new_insn = reallocarray(prog->insns, new_cnt, sizeof(*insn)); if (!new_insn) { - pr_warning("oom in prog realloc\n"); + pr_warn("oom in prog realloc\n"); return -ENOMEM; } + prog->insns = new_insn; if (obj->btf_ext) { err = bpf_program_reloc_btf_ext(prog, obj, @@ -1374,7 +3592,6 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj, memcpy(new_insn + prog->insns_cnt, text->insns, text->insns_cnt * sizeof(*insn)); - prog->insns = new_insn; prog->main_prog_cnt = prog->insns_cnt; prog->insns_cnt = new_cnt; pr_debug("added %zd insn from %s to prog %s\n", @@ -1382,7 +3599,7 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj, prog->section_name); } insn = &prog->insns[relo->insn_idx]; - insn->imm += prog->main_prog_cnt - relo->insn_idx; + insn->imm += relo->text_off + prog->main_prog_cnt - relo->insn_idx; return 0; } @@ -1405,21 +3622,29 @@ bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj) return 0; for (i = 0; i < prog->nr_reloc; i++) { - if (prog->reloc_desc[i].type == RELO_LD64) { + if (prog->reloc_desc[i].type == RELO_LD64 || + prog->reloc_desc[i].type == RELO_DATA) { + bool relo_data = prog->reloc_desc[i].type == RELO_DATA; struct bpf_insn *insns = prog->insns; int insn_idx, map_idx; insn_idx = prog->reloc_desc[i].insn_idx; map_idx = prog->reloc_desc[i].map_idx; - if (insn_idx >= (int)prog->insns_cnt) { - pr_warning("relocation out of range: '%s'\n", - prog->section_name); + if (insn_idx + 1 >= (int)prog->insns_cnt) { + pr_warn("relocation out of range: '%s'\n", + prog->section_name); return -LIBBPF_ERRNO__RELOC; } - insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD; + + if (!relo_data) { + insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD; + } else { + insns[insn_idx].src_reg = BPF_PSEUDO_MAP_VALUE; + insns[insn_idx + 1].imm = insns[insn_idx].imm; + } insns[insn_idx].imm = obj->maps[map_idx].fd; - } else { + } else if (prog->reloc_desc[i].type == RELO_CALL) { err = bpf_program__reloc_text(prog, obj, &prog->reloc_desc[i]); if (err) @@ -1432,21 +3657,27 @@ bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj) return 0; } - static int -bpf_object__relocate(struct bpf_object *obj) +bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) { struct bpf_program *prog; size_t i; int err; + if (obj->btf_ext) { + err = bpf_object__relocate_core(obj, targ_btf_path); + if (err) { + pr_warn("failed to perform CO-RE relocations: %d\n", + err); + return err; + } + } for (i = 0; i < obj->nr_programs; i++) { prog = &obj->programs[i]; err = bpf_program__relocate(prog, obj); if (err) { - pr_warning("failed to relocate '%s'\n", - prog->section_name); + pr_warn("failed to relocate '%s'\n", prog->section_name); return err; } } @@ -1458,30 +3689,28 @@ static int bpf_object__collect_reloc(struct bpf_object *obj) int i, err; if (!obj_elf_valid(obj)) { - pr_warning("Internal error: elf object is closed\n"); + pr_warn("Internal error: elf object is closed\n"); return -LIBBPF_ERRNO__INTERNAL; } - for (i = 0; i < obj->efile.nr_reloc; i++) { - GElf_Shdr *shdr = &obj->efile.reloc[i].shdr; - Elf_Data *data = obj->efile.reloc[i].data; + for (i = 0; i < obj->efile.nr_reloc_sects; i++) { + GElf_Shdr *shdr = &obj->efile.reloc_sects[i].shdr; + Elf_Data *data = obj->efile.reloc_sects[i].data; int idx = shdr->sh_info; struct bpf_program *prog; if (shdr->sh_type != SHT_REL) { - pr_warning("internal error at %d\n", __LINE__); + pr_warn("internal error at %d\n", __LINE__); return -LIBBPF_ERRNO__INTERNAL; } prog = bpf_object__find_prog_by_idx(obj, idx); if (!prog) { - pr_warning("relocation failed: no section(%d)\n", idx); + pr_warn("relocation failed: no section(%d)\n", idx); return -LIBBPF_ERRNO__RELOC; } - err = bpf_program__collect_reloc(prog, - shdr, data, - obj); + err = bpf_program__collect_reloc(prog, shdr, data, obj); if (err) return err; } @@ -1494,8 +3723,12 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, { struct bpf_load_program_attr load_attr; char *cp, errmsg[STRERR_BUFSIZE]; + int log_buf_size = BPF_LOG_BUF_SIZE; char *log_buf; - int ret; + int btf_fd, ret; + + if (!insns || !insns_cnt) + return -EINVAL; memset(&load_attr, 0, sizeof(struct bpf_load_program_attr)); load_attr.prog_type = prog->type; @@ -1505,60 +3738,73 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, load_attr.insns = insns; load_attr.insns_cnt = insns_cnt; load_attr.license = license; - load_attr.kern_version = kern_version; - load_attr.prog_ifindex = prog->prog_ifindex; - load_attr.prog_btf_fd = prog->btf_fd >= 0 ? prog->btf_fd : 0; + if (prog->type == BPF_PROG_TYPE_TRACING) { + load_attr.attach_prog_fd = prog->attach_prog_fd; + load_attr.attach_btf_id = prog->attach_btf_id; + } else { + load_attr.kern_version = kern_version; + load_attr.prog_ifindex = prog->prog_ifindex; + } + /* if .BTF.ext was loaded, kernel supports associated BTF for prog */ + if (prog->obj->btf_ext) + btf_fd = bpf_object__btf_fd(prog->obj); + else + btf_fd = -1; + load_attr.prog_btf_fd = btf_fd >= 0 ? btf_fd : 0; load_attr.func_info = prog->func_info; load_attr.func_info_rec_size = prog->func_info_rec_size; load_attr.func_info_cnt = prog->func_info_cnt; load_attr.line_info = prog->line_info; load_attr.line_info_rec_size = prog->line_info_rec_size; load_attr.line_info_cnt = prog->line_info_cnt; - if (!load_attr.insns || !load_attr.insns_cnt) - return -EINVAL; + load_attr.log_level = prog->log_level; + load_attr.prog_flags = prog->prog_flags; - log_buf = malloc(BPF_LOG_BUF_SIZE); +retry_load: + log_buf = malloc(log_buf_size); if (!log_buf) - pr_warning("Alloc log buffer for bpf loader error, continue without log\n"); + pr_warn("Alloc log buffer for bpf loader error, continue without log\n"); - ret = bpf_load_program_xattr(&load_attr, log_buf, BPF_LOG_BUF_SIZE); + ret = bpf_load_program_xattr(&load_attr, log_buf, log_buf_size); if (ret >= 0) { + if (load_attr.log_level) + pr_debug("verifier log:\n%s", log_buf); *pfd = ret; ret = 0; goto out; } - ret = -LIBBPF_ERRNO__LOAD; + if (errno == ENOSPC) { + log_buf_size <<= 1; + free(log_buf); + goto retry_load; + } + ret = -errno; cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); - pr_warning("load bpf program failed: %s\n", cp); + pr_warn("load bpf program failed: %s\n", cp); if (log_buf && log_buf[0] != '\0') { ret = -LIBBPF_ERRNO__VERIFY; - pr_warning("-- BEGIN DUMP LOG ---\n"); - pr_warning("\n%s\n", log_buf); - pr_warning("-- END LOG --\n"); + pr_warn("-- BEGIN DUMP LOG ---\n"); + pr_warn("\n%s\n", log_buf); + pr_warn("-- END LOG --\n"); } else if (load_attr.insns_cnt >= BPF_MAXINSNS) { - pr_warning("Program too large (%zu insns), at most %d insns\n", - load_attr.insns_cnt, BPF_MAXINSNS); + pr_warn("Program too large (%zu insns), at most %d insns\n", + load_attr.insns_cnt, BPF_MAXINSNS); ret = -LIBBPF_ERRNO__PROG2BIG; - } else { + } else if (load_attr.prog_type != BPF_PROG_TYPE_KPROBE) { /* Wrong program type? */ - if (load_attr.prog_type != BPF_PROG_TYPE_KPROBE) { - int fd; - - load_attr.prog_type = BPF_PROG_TYPE_KPROBE; - load_attr.expected_attach_type = 0; - fd = bpf_load_program_xattr(&load_attr, NULL, 0); - if (fd >= 0) { - close(fd); - ret = -LIBBPF_ERRNO__PROGTYPE; - goto out; - } - } + int fd; - if (log_buf) - ret = -LIBBPF_ERRNO__KVER; + load_attr.prog_type = BPF_PROG_TYPE_KPROBE; + load_attr.expected_attach_type = 0; + fd = bpf_load_program_xattr(&load_attr, NULL, 0); + if (fd >= 0) { + close(fd); + ret = -LIBBPF_ERRNO__PROGTYPE; + goto out; + } } out: @@ -1574,14 +3820,14 @@ bpf_program__load(struct bpf_program *prog, if (prog->instances.nr < 0 || !prog->instances.fds) { if (prog->preprocessor) { - pr_warning("Internal error: can't load program '%s'\n", - prog->section_name); + pr_warn("Internal error: can't load program '%s'\n", + prog->section_name); return -LIBBPF_ERRNO__INTERNAL; } prog->instances.fds = malloc(sizeof(int)); if (!prog->instances.fds) { - pr_warning("Not enough memory for BPF fds\n"); + pr_warn("Not enough memory for BPF fds\n"); return -ENOMEM; } prog->instances.nr = 1; @@ -1590,8 +3836,8 @@ bpf_program__load(struct bpf_program *prog, if (!prog->preprocessor) { if (prog->instances.nr != 1) { - pr_warning("Program '%s' is inconsistent: nr(%d) != 1\n", - prog->section_name, prog->instances.nr); + pr_warn("Program '%s' is inconsistent: nr(%d) != 1\n", + prog->section_name, prog->instances.nr); } err = load_program(prog, prog->insns, prog->insns_cnt, license, kern_version, &fd); @@ -1608,8 +3854,8 @@ bpf_program__load(struct bpf_program *prog, err = preprocessor(prog, i, prog->insns, prog->insns_cnt, &result); if (err) { - pr_warning("Preprocessing the %dth instance of program '%s' failed\n", - i, prog->section_name); + pr_warn("Preprocessing the %dth instance of program '%s' failed\n", + i, prog->section_name); goto out; } @@ -1627,8 +3873,8 @@ bpf_program__load(struct bpf_program *prog, license, kern_version, &fd); if (err) { - pr_warning("Loading the %dth instance of program '%s' failed\n", - i, prog->section_name); + pr_warn("Loading the %dth instance of program '%s' failed\n", + i, prog->section_name); goto out; } @@ -1638,21 +3884,20 @@ bpf_program__load(struct bpf_program *prog, } out: if (err) - pr_warning("failed to load program '%s'\n", - prog->section_name); + pr_warn("failed to load program '%s'\n", prog->section_name); zfree(&prog->insns); prog->insns_cnt = 0; return err; } -static bool bpf_program__is_function_storage(struct bpf_program *prog, - struct bpf_object *obj) +static bool bpf_program__is_function_storage(const struct bpf_program *prog, + const struct bpf_object *obj) { return prog->idx == obj->efile.text_shndx && obj->has_pseudo_calls; } static int -bpf_object__load_progs(struct bpf_object *obj) +bpf_object__load_progs(struct bpf_object *obj, int log_level) { size_t i; int err; @@ -1660,6 +3905,7 @@ bpf_object__load_progs(struct bpf_object *obj) for (i = 0; i < obj->nr_programs; i++) { if (bpf_program__is_function_storage(&obj->programs[i], obj)) continue; + obj->programs[i].log_level |= log_level; err = bpf_program__load(&obj->programs[i], obj->license, obj->kern_version); @@ -1669,89 +3915,104 @@ bpf_object__load_progs(struct bpf_object *obj) return 0; } -static bool bpf_prog_type__needs_kver(enum bpf_prog_type type) -{ - switch (type) { - case BPF_PROG_TYPE_SOCKET_FILTER: - case BPF_PROG_TYPE_SCHED_CLS: - case BPF_PROG_TYPE_SCHED_ACT: - case BPF_PROG_TYPE_XDP: - case BPF_PROG_TYPE_CGROUP_SKB: - case BPF_PROG_TYPE_CGROUP_SOCK: - case BPF_PROG_TYPE_LWT_IN: - case BPF_PROG_TYPE_LWT_OUT: - case BPF_PROG_TYPE_LWT_XMIT: - case BPF_PROG_TYPE_LWT_SEG6LOCAL: - case BPF_PROG_TYPE_SOCK_OPS: - case BPF_PROG_TYPE_SK_SKB: - case BPF_PROG_TYPE_CGROUP_DEVICE: - case BPF_PROG_TYPE_SK_MSG: - case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: - case BPF_PROG_TYPE_LIRC_MODE2: - case BPF_PROG_TYPE_SK_REUSEPORT: - case BPF_PROG_TYPE_FLOW_DISSECTOR: - case BPF_PROG_TYPE_UNSPEC: - case BPF_PROG_TYPE_TRACEPOINT: - case BPF_PROG_TYPE_RAW_TRACEPOINT: - case BPF_PROG_TYPE_PERF_EVENT: - return false; - case BPF_PROG_TYPE_KPROBE: - default: - return true; - } -} - -static int bpf_object__validate(struct bpf_object *obj, bool needs_kver) -{ - if (needs_kver && obj->kern_version == 0) { - pr_warning("%s doesn't provide kernel version\n", - obj->path); - return -LIBBPF_ERRNO__KVERSION; - } - return 0; -} - +static int libbpf_find_attach_btf_id(const char *name, + enum bpf_attach_type attach_type, + __u32 attach_prog_fd); static struct bpf_object * -__bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz, - bool needs_kver, int flags) +__bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz, + struct bpf_object_open_opts *opts) { + const char *pin_root_path; + struct bpf_program *prog; struct bpf_object *obj; + const char *obj_name; + char tmp_name[64]; + bool relaxed_maps; + __u32 attach_prog_fd; int err; if (elf_version(EV_CURRENT) == EV_NONE) { - pr_warning("failed to init libelf for %s\n", path); + pr_warn("failed to init libelf for %s\n", + path ? : "(mem buf)"); return ERR_PTR(-LIBBPF_ERRNO__LIBELF); } - obj = bpf_object__new(path, obj_buf, obj_buf_sz); + if (!OPTS_VALID(opts, bpf_object_open_opts)) + return ERR_PTR(-EINVAL); + + obj_name = OPTS_GET(opts, object_name, NULL); + if (obj_buf) { + if (!obj_name) { + snprintf(tmp_name, sizeof(tmp_name), "%lx-%lx", + (unsigned long)obj_buf, + (unsigned long)obj_buf_sz); + obj_name = tmp_name; + } + path = obj_name; + pr_debug("loading object '%s' from buffer\n", obj_name); + } + + obj = bpf_object__new(path, obj_buf, obj_buf_sz, obj_name); if (IS_ERR(obj)) return obj; + obj->relaxed_core_relocs = OPTS_GET(opts, relaxed_core_relocs, false); + relaxed_maps = OPTS_GET(opts, relaxed_maps, false); + pin_root_path = OPTS_GET(opts, pin_root_path, NULL); + attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0); + CHECK_ERR(bpf_object__elf_init(obj), err, out); CHECK_ERR(bpf_object__check_endianness(obj), err, out); - CHECK_ERR(bpf_object__elf_collect(obj, flags), err, out); + CHECK_ERR(bpf_object__probe_caps(obj), err, out); + CHECK_ERR(bpf_object__elf_collect(obj, relaxed_maps, pin_root_path), + err, out); CHECK_ERR(bpf_object__collect_reloc(obj), err, out); - CHECK_ERR(bpf_object__validate(obj, needs_kver), err, out); - bpf_object__elf_finish(obj); + + bpf_object__for_each_program(prog, obj) { + enum bpf_prog_type prog_type; + enum bpf_attach_type attach_type; + + err = libbpf_prog_type_by_name(prog->section_name, &prog_type, + &attach_type); + if (err == -ESRCH) + /* couldn't guess, but user might manually specify */ + continue; + if (err) + goto out; + + bpf_program__set_type(prog, prog_type); + bpf_program__set_expected_attach_type(prog, attach_type); + if (prog_type == BPF_PROG_TYPE_TRACING) { + err = libbpf_find_attach_btf_id(prog->section_name, + attach_type, + attach_prog_fd); + if (err <= 0) + goto out; + prog->attach_btf_id = err; + prog->attach_prog_fd = attach_prog_fd; + } + } + return obj; out: bpf_object__close(obj); return ERR_PTR(err); } -struct bpf_object *__bpf_object__open_xattr(struct bpf_object_open_attr *attr, - int flags) +static struct bpf_object * +__bpf_object__open_xattr(struct bpf_object_open_attr *attr, int flags) { + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts, + .relaxed_maps = flags & MAPS_RELAX_COMPAT, + ); + /* param validation */ if (!attr->file) return NULL; pr_debug("loading %s\n", attr->file); - - return __bpf_object__open(attr->file, NULL, 0, - bpf_prog_type__needs_kver(attr->prog_type), - flags); + return __bpf_object__open(attr->file, NULL, 0, &opts); } struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr) @@ -1769,27 +4030,42 @@ struct bpf_object *bpf_object__open(const char *path) return bpf_object__open_xattr(&attr); } -struct bpf_object *bpf_object__open_buffer(void *obj_buf, - size_t obj_buf_sz, - const char *name) +struct bpf_object * +bpf_object__open_file(const char *path, struct bpf_object_open_opts *opts) { - char tmp_name[64]; + if (!path) + return ERR_PTR(-EINVAL); - /* param validation */ - if (!obj_buf || obj_buf_sz <= 0) - return NULL; + pr_debug("loading %s\n", path); - if (!name) { - snprintf(tmp_name, sizeof(tmp_name), "%lx-%lx", - (unsigned long)obj_buf, - (unsigned long)obj_buf_sz); - tmp_name[sizeof(tmp_name) - 1] = '\0'; - name = tmp_name; - } - pr_debug("loading object '%s' from buffer\n", - name); + return __bpf_object__open(path, NULL, 0, opts); +} - return __bpf_object__open(name, obj_buf, obj_buf_sz, true, true); +struct bpf_object * +bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz, + struct bpf_object_open_opts *opts) +{ + if (!obj_buf || obj_buf_sz == 0) + return ERR_PTR(-EINVAL); + + return __bpf_object__open(NULL, obj_buf, obj_buf_sz, opts); +} + +struct bpf_object * +bpf_object__open_buffer(const void *obj_buf, size_t obj_buf_sz, + const char *name) +{ + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts, + .object_name = name, + /* wrong default, but backwards-compatible */ + .relaxed_maps = true, + ); + + /* returning NULL is wrong, but backwards-compatible */ + if (!obj_buf || obj_buf_sz == 0) + return NULL; + + return bpf_object__open_mem(obj_buf, obj_buf_sz, &opts); } int bpf_object__unload(struct bpf_object *obj) @@ -1808,29 +4084,68 @@ int bpf_object__unload(struct bpf_object *obj) return 0; } -int bpf_object__load(struct bpf_object *obj) +int bpf_object__load_xattr(struct bpf_object_load_attr *attr) { - int err; + struct bpf_object *obj; + int err, i; + if (!attr) + return -EINVAL; + obj = attr->obj; if (!obj) return -EINVAL; if (obj->loaded) { - pr_warning("object should not be loaded twice\n"); + pr_warn("object should not be loaded twice\n"); return -EINVAL; } obj->loaded = true; - CHECK_ERR(bpf_object__probe_caps(obj), err, out); CHECK_ERR(bpf_object__create_maps(obj), err, out); - CHECK_ERR(bpf_object__relocate(obj), err, out); - CHECK_ERR(bpf_object__load_progs(obj), err, out); + CHECK_ERR(bpf_object__relocate(obj, attr->target_btf_path), err, out); + CHECK_ERR(bpf_object__load_progs(obj, attr->log_level), err, out); return 0; out: + /* unpin any maps that were auto-pinned during load */ + for (i = 0; i < obj->nr_maps; i++) + if (obj->maps[i].pinned && !obj->maps[i].reused) + bpf_map__unpin(&obj->maps[i], NULL); + bpf_object__unload(obj); - pr_warning("failed to load object '%s'\n", obj->path); + pr_warn("failed to load object '%s'\n", obj->path); + return err; +} + +int bpf_object__load(struct bpf_object *obj) +{ + struct bpf_object_load_attr attr = { + .obj = obj, + }; + + return bpf_object__load_xattr(&attr); +} + +static int make_parent_dir(const char *path) +{ + char *cp, errmsg[STRERR_BUFSIZE]; + char *dname, *dir; + int err = 0; + + dname = strdup(path); + if (dname == NULL) + return -ENOMEM; + + dir = dirname(dname); + if (mkdir(dir, 0700) && errno != EEXIST) + err = -errno; + + free(dname); + if (err) { + cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg)); + pr_warn("failed to mkdir %s: %s\n", path, cp); + } return err; } @@ -1851,13 +4166,13 @@ static int check_path(const char *path) dir = dirname(dname); if (statfs(dir, &st_fs)) { cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); - pr_warning("failed to statfs %s: %s\n", dir, cp); + pr_warn("failed to statfs %s: %s\n", dir, cp); err = -errno; } free(dname); if (!err && st_fs.f_type != BPF_FS_MAGIC) { - pr_warning("specified path %s is not on BPF FS\n", path); + pr_warn("specified path %s is not on BPF FS\n", path); err = -EINVAL; } @@ -1870,24 +4185,28 @@ int bpf_program__pin_instance(struct bpf_program *prog, const char *path, char *cp, errmsg[STRERR_BUFSIZE]; int err; + err = make_parent_dir(path); + if (err) + return err; + err = check_path(path); if (err) return err; if (prog == NULL) { - pr_warning("invalid program pointer\n"); + pr_warn("invalid program pointer\n"); return -EINVAL; } if (instance < 0 || instance >= prog->instances.nr) { - pr_warning("invalid prog instance %d of prog %s (max %d)\n", - instance, prog->section_name, prog->instances.nr); + pr_warn("invalid prog instance %d of prog %s (max %d)\n", + instance, prog->section_name, prog->instances.nr); return -EINVAL; } if (bpf_obj_pin(prog->instances.fds[instance], path)) { cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); - pr_warning("failed to pin program: %s\n", cp); + pr_warn("failed to pin program: %s\n", cp); return -errno; } pr_debug("pinned program '%s'\n", path); @@ -1905,13 +4224,13 @@ int bpf_program__unpin_instance(struct bpf_program *prog, const char *path, return err; if (prog == NULL) { - pr_warning("invalid program pointer\n"); + pr_warn("invalid program pointer\n"); return -EINVAL; } if (instance < 0 || instance >= prog->instances.nr) { - pr_warning("invalid prog instance %d of prog %s (max %d)\n", - instance, prog->section_name, prog->instances.nr); + pr_warn("invalid prog instance %d of prog %s (max %d)\n", + instance, prog->section_name, prog->instances.nr); return -EINVAL; } @@ -1923,36 +4242,25 @@ int bpf_program__unpin_instance(struct bpf_program *prog, const char *path, return 0; } -static int make_dir(const char *path) -{ - char *cp, errmsg[STRERR_BUFSIZE]; - int err = 0; - - if (mkdir(path, 0700) && errno != EEXIST) - err = -errno; - - if (err) { - cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg)); - pr_warning("failed to mkdir %s: %s\n", path, cp); - } - return err; -} - int bpf_program__pin(struct bpf_program *prog, const char *path) { int i, err; + err = make_parent_dir(path); + if (err) + return err; + err = check_path(path); if (err) return err; if (prog == NULL) { - pr_warning("invalid program pointer\n"); + pr_warn("invalid program pointer\n"); return -EINVAL; } if (prog->instances.nr <= 0) { - pr_warning("no instances of prog %s to pin\n", + pr_warn("no instances of prog %s to pin\n", prog->section_name); return -EINVAL; } @@ -1962,10 +4270,6 @@ int bpf_program__pin(struct bpf_program *prog, const char *path) return bpf_program__pin_instance(prog, path, 0); } - err = make_dir(path); - if (err) - return err; - for (i = 0; i < prog->instances.nr; i++) { char buf[PATH_MAX]; int len; @@ -2014,12 +4318,12 @@ int bpf_program__unpin(struct bpf_program *prog, const char *path) return err; if (prog == NULL) { - pr_warning("invalid program pointer\n"); + pr_warn("invalid program pointer\n"); return -EINVAL; } if (prog->instances.nr <= 0) { - pr_warning("no instances of prog %s to pin\n", + pr_warn("no instances of prog %s to pin\n", prog->section_name); return -EINVAL; } @@ -2056,47 +4360,123 @@ int bpf_map__pin(struct bpf_map *map, const char *path) char *cp, errmsg[STRERR_BUFSIZE]; int err; - err = check_path(path); - if (err) - return err; - if (map == NULL) { - pr_warning("invalid map pointer\n"); + pr_warn("invalid map pointer\n"); return -EINVAL; } - if (bpf_obj_pin(map->fd, path)) { - cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); - pr_warning("failed to pin map: %s\n", cp); - return -errno; + if (map->pin_path) { + if (path && strcmp(path, map->pin_path)) { + pr_warn("map '%s' already has pin path '%s' different from '%s'\n", + bpf_map__name(map), map->pin_path, path); + return -EINVAL; + } else if (map->pinned) { + pr_debug("map '%s' already pinned at '%s'; not re-pinning\n", + bpf_map__name(map), map->pin_path); + return 0; + } + } else { + if (!path) { + pr_warn("missing a path to pin map '%s' at\n", + bpf_map__name(map)); + return -EINVAL; + } else if (map->pinned) { + pr_warn("map '%s' already pinned\n", bpf_map__name(map)); + return -EEXIST; + } + + map->pin_path = strdup(path); + if (!map->pin_path) { + err = -errno; + goto out_err; + } } - pr_debug("pinned map '%s'\n", path); + err = make_parent_dir(map->pin_path); + if (err) + return err; + + err = check_path(map->pin_path); + if (err) + return err; + + if (bpf_obj_pin(map->fd, map->pin_path)) { + err = -errno; + goto out_err; + } + + map->pinned = true; + pr_debug("pinned map '%s'\n", map->pin_path); return 0; + +out_err: + cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg)); + pr_warn("failed to pin map: %s\n", cp); + return err; } int bpf_map__unpin(struct bpf_map *map, const char *path) { int err; - err = check_path(path); - if (err) - return err; - if (map == NULL) { - pr_warning("invalid map pointer\n"); + pr_warn("invalid map pointer\n"); + return -EINVAL; + } + + if (map->pin_path) { + if (path && strcmp(path, map->pin_path)) { + pr_warn("map '%s' already has pin path '%s' different from '%s'\n", + bpf_map__name(map), map->pin_path, path); + return -EINVAL; + } + path = map->pin_path; + } else if (!path) { + pr_warn("no path to unpin map '%s' from\n", + bpf_map__name(map)); return -EINVAL; } + err = check_path(path); + if (err) + return err; + err = unlink(path); if (err != 0) return -errno; - pr_debug("unpinned map '%s'\n", path); + + map->pinned = false; + pr_debug("unpinned map '%s' from '%s'\n", bpf_map__name(map), path); return 0; } +int bpf_map__set_pin_path(struct bpf_map *map, const char *path) +{ + char *new = NULL; + + if (path) { + new = strdup(path); + if (!new) + return -errno; + } + + free(map->pin_path); + map->pin_path = new; + return 0; +} + +const char *bpf_map__get_pin_path(const struct bpf_map *map) +{ + return map->pin_path; +} + +bool bpf_map__is_pinned(const struct bpf_map *map) +{ + return map->pinned; +} + int bpf_object__pin_maps(struct bpf_object *obj, const char *path) { struct bpf_map *map; @@ -2106,29 +4486,32 @@ int bpf_object__pin_maps(struct bpf_object *obj, const char *path) return -ENOENT; if (!obj->loaded) { - pr_warning("object not yet loaded; load it first\n"); + pr_warn("object not yet loaded; load it first\n"); return -ENOENT; } - err = make_dir(path); - if (err) - return err; - bpf_object__for_each_map(map, obj) { + char *pin_path = NULL; char buf[PATH_MAX]; - int len; - len = snprintf(buf, PATH_MAX, "%s/%s", path, - bpf_map__name(map)); - if (len < 0) { - err = -EINVAL; - goto err_unpin_maps; - } else if (len >= PATH_MAX) { - err = -ENAMETOOLONG; - goto err_unpin_maps; + if (path) { + int len; + + len = snprintf(buf, PATH_MAX, "%s/%s", path, + bpf_map__name(map)); + if (len < 0) { + err = -EINVAL; + goto err_unpin_maps; + } else if (len >= PATH_MAX) { + err = -ENAMETOOLONG; + goto err_unpin_maps; + } + pin_path = buf; + } else if (!map->pin_path) { + continue; } - err = bpf_map__pin(map, buf); + err = bpf_map__pin(map, pin_path); if (err) goto err_unpin_maps; } @@ -2137,17 +4520,10 @@ int bpf_object__pin_maps(struct bpf_object *obj, const char *path) err_unpin_maps: while ((map = bpf_map__prev(map, obj))) { - char buf[PATH_MAX]; - int len; - - len = snprintf(buf, PATH_MAX, "%s/%s", path, - bpf_map__name(map)); - if (len < 0) - continue; - else if (len >= PATH_MAX) + if (!map->pin_path) continue; - bpf_map__unpin(map, buf); + bpf_map__unpin(map, NULL); } return err; @@ -2162,17 +4538,24 @@ int bpf_object__unpin_maps(struct bpf_object *obj, const char *path) return -ENOENT; bpf_object__for_each_map(map, obj) { + char *pin_path = NULL; char buf[PATH_MAX]; - int len; - len = snprintf(buf, PATH_MAX, "%s/%s", path, - bpf_map__name(map)); - if (len < 0) - return -EINVAL; - else if (len >= PATH_MAX) - return -ENAMETOOLONG; + if (path) { + int len; + + len = snprintf(buf, PATH_MAX, "%s/%s", path, + bpf_map__name(map)); + if (len < 0) + return -EINVAL; + else if (len >= PATH_MAX) + return -ENAMETOOLONG; + pin_path = buf; + } else if (!map->pin_path) { + continue; + } - err = bpf_map__unpin(map, buf); + err = bpf_map__unpin(map, pin_path); if (err) return err; } @@ -2189,14 +4572,10 @@ int bpf_object__pin_programs(struct bpf_object *obj, const char *path) return -ENOENT; if (!obj->loaded) { - pr_warning("object not yet loaded; load it first\n"); + pr_warn("object not yet loaded; load it first\n"); return -ENOENT; } - err = make_dir(path); - if (err) - return err; - bpf_object__for_each_program(prog, obj) { char buf[PATH_MAX]; int len; @@ -2297,12 +4676,16 @@ void bpf_object__close(struct bpf_object *obj) for (i = 0; i < obj->nr_maps; i++) { zfree(&obj->maps[i].name); + zfree(&obj->maps[i].pin_path); if (obj->maps[i].clear_priv) obj->maps[i].clear_priv(&obj->maps[i], obj->maps[i].priv); obj->maps[i].priv = NULL; obj->maps[i].clear_priv = NULL; } + + zfree(&obj->sections.rodata); + zfree(&obj->sections.data); zfree(&obj->maps); obj->nr_maps = 0; @@ -2335,17 +4718,17 @@ bpf_object__next(struct bpf_object *prev) return next; } -const char *bpf_object__name(struct bpf_object *obj) +const char *bpf_object__name(const struct bpf_object *obj) { - return obj ? obj->path : ERR_PTR(-EINVAL); + return obj ? obj->name : ERR_PTR(-EINVAL); } -unsigned int bpf_object__kversion(struct bpf_object *obj) +unsigned int bpf_object__kversion(const struct bpf_object *obj) { return obj ? obj->kern_version : 0; } -struct btf *bpf_object__btf(struct bpf_object *obj) +struct btf *bpf_object__btf(const struct bpf_object *obj) { return obj ? obj->btf : NULL; } @@ -2366,13 +4749,14 @@ int bpf_object__set_priv(struct bpf_object *obj, void *priv, return 0; } -void *bpf_object__priv(struct bpf_object *obj) +void *bpf_object__priv(const struct bpf_object *obj) { return obj ? obj->priv : ERR_PTR(-EINVAL); } static struct bpf_program * -__bpf_program__iter(struct bpf_program *p, struct bpf_object *obj, bool forward) +__bpf_program__iter(const struct bpf_program *p, const struct bpf_object *obj, + bool forward) { size_t nr_programs = obj->nr_programs; ssize_t idx; @@ -2386,7 +4770,7 @@ __bpf_program__iter(struct bpf_program *p, struct bpf_object *obj, bool forward) &obj->programs[nr_programs - 1]; if (p->obj != obj) { - pr_warning("error: program handler doesn't match object\n"); + pr_warn("error: program handler doesn't match object\n"); return NULL; } @@ -2397,7 +4781,7 @@ __bpf_program__iter(struct bpf_program *p, struct bpf_object *obj, bool forward) } struct bpf_program * -bpf_program__next(struct bpf_program *prev, struct bpf_object *obj) +bpf_program__next(struct bpf_program *prev, const struct bpf_object *obj) { struct bpf_program *prog = prev; @@ -2409,7 +4793,7 @@ bpf_program__next(struct bpf_program *prev, struct bpf_object *obj) } struct bpf_program * -bpf_program__prev(struct bpf_program *next, struct bpf_object *obj) +bpf_program__prev(struct bpf_program *next, const struct bpf_object *obj) { struct bpf_program *prog = next; @@ -2431,7 +4815,7 @@ int bpf_program__set_priv(struct bpf_program *prog, void *priv, return 0; } -void *bpf_program__priv(struct bpf_program *prog) +void *bpf_program__priv(const struct bpf_program *prog) { return prog ? prog->priv : ERR_PTR(-EINVAL); } @@ -2441,7 +4825,7 @@ void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex) prog->prog_ifindex = ifindex; } -const char *bpf_program__title(struct bpf_program *prog, bool needs_copy) +const char *bpf_program__title(const struct bpf_program *prog, bool needs_copy) { const char *title; @@ -2449,7 +4833,7 @@ const char *bpf_program__title(struct bpf_program *prog, bool needs_copy) if (needs_copy) { title = strdup(title); if (!title) { - pr_warning("failed to strdup program title\n"); + pr_warn("failed to strdup program title\n"); return ERR_PTR(-ENOMEM); } } @@ -2457,11 +4841,16 @@ const char *bpf_program__title(struct bpf_program *prog, bool needs_copy) return title; } -int bpf_program__fd(struct bpf_program *prog) +int bpf_program__fd(const struct bpf_program *prog) { return bpf_program__nth_fd(prog, 0); } +size_t bpf_program__size(const struct bpf_program *prog) +{ + return prog->insns_cnt * sizeof(struct bpf_insn); +} + int bpf_program__set_prep(struct bpf_program *prog, int nr_instances, bpf_program_prep_t prep) { @@ -2471,13 +4860,13 @@ int bpf_program__set_prep(struct bpf_program *prog, int nr_instances, return -EINVAL; if (prog->instances.nr > 0 || prog->instances.fds) { - pr_warning("Can't set pre-processor after loading\n"); + pr_warn("Can't set pre-processor after loading\n"); return -EINVAL; } instances_fds = malloc(sizeof(int) * nr_instances); if (!instances_fds) { - pr_warning("alloc memory failed for fds\n"); + pr_warn("alloc memory failed for fds\n"); return -ENOMEM; } @@ -2490,7 +4879,7 @@ int bpf_program__set_prep(struct bpf_program *prog, int nr_instances, return 0; } -int bpf_program__nth_fd(struct bpf_program *prog, int n) +int bpf_program__nth_fd(const struct bpf_program *prog, int n) { int fd; @@ -2498,45 +4887,50 @@ int bpf_program__nth_fd(struct bpf_program *prog, int n) return -EINVAL; if (n >= prog->instances.nr || n < 0) { - pr_warning("Can't get the %dth fd from program %s: only %d instances\n", - n, prog->section_name, prog->instances.nr); + pr_warn("Can't get the %dth fd from program %s: only %d instances\n", + n, prog->section_name, prog->instances.nr); return -EINVAL; } fd = prog->instances.fds[n]; if (fd < 0) { - pr_warning("%dth instance of program '%s' is invalid\n", - n, prog->section_name); + pr_warn("%dth instance of program '%s' is invalid\n", + n, prog->section_name); return -ENOENT; } return fd; } +enum bpf_prog_type bpf_program__get_type(struct bpf_program *prog) +{ + return prog->type; +} + void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type) { prog->type = type; } -static bool bpf_program__is_type(struct bpf_program *prog, +static bool bpf_program__is_type(const struct bpf_program *prog, enum bpf_prog_type type) { return prog ? (prog->type == type) : false; } -#define BPF_PROG_TYPE_FNS(NAME, TYPE) \ -int bpf_program__set_##NAME(struct bpf_program *prog) \ -{ \ - if (!prog) \ - return -EINVAL; \ - bpf_program__set_type(prog, TYPE); \ - return 0; \ -} \ - \ -bool bpf_program__is_##NAME(struct bpf_program *prog) \ -{ \ - return bpf_program__is_type(prog, TYPE); \ -} \ +#define BPF_PROG_TYPE_FNS(NAME, TYPE) \ +int bpf_program__set_##NAME(struct bpf_program *prog) \ +{ \ + if (!prog) \ + return -EINVAL; \ + bpf_program__set_type(prog, TYPE); \ + return 0; \ +} \ + \ +bool bpf_program__is_##NAME(const struct bpf_program *prog) \ +{ \ + return bpf_program__is_type(prog, TYPE); \ +} \ BPF_PROG_TYPE_FNS(socket_filter, BPF_PROG_TYPE_SOCKET_FILTER); BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE); @@ -2546,6 +4940,13 @@ BPF_PROG_TYPE_FNS(tracepoint, BPF_PROG_TYPE_TRACEPOINT); BPF_PROG_TYPE_FNS(raw_tracepoint, BPF_PROG_TYPE_RAW_TRACEPOINT); BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP); BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT); +BPF_PROG_TYPE_FNS(tracing, BPF_PROG_TYPE_TRACING); + +enum bpf_attach_type +bpf_program__get_expected_attach_type(struct bpf_program *prog) +{ + return prog->expected_attach_type; +} void bpf_program__set_expected_attach_type(struct bpf_program *prog, enum bpf_attach_type type) @@ -2553,19 +4954,23 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog, prog->expected_attach_type = type; } -#define BPF_PROG_SEC_IMPL(string, ptype, eatype, is_attachable, atype) \ - { string, sizeof(string) - 1, ptype, eatype, is_attachable, atype } +#define BPF_PROG_SEC_IMPL(string, ptype, eatype, is_attachable, btf, atype) \ + { string, sizeof(string) - 1, ptype, eatype, is_attachable, btf, atype } /* Programs that can NOT be attached. */ -#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, 0, 0) +#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, 0, 0, 0) /* Programs that can be attached. */ #define BPF_APROG_SEC(string, ptype, atype) \ - BPF_PROG_SEC_IMPL(string, ptype, 0, 1, atype) + BPF_PROG_SEC_IMPL(string, ptype, 0, 1, 0, atype) /* Programs that must specify expected attach type at load time. */ #define BPF_EAPROG_SEC(string, ptype, eatype) \ - BPF_PROG_SEC_IMPL(string, ptype, eatype, 1, eatype) + BPF_PROG_SEC_IMPL(string, ptype, eatype, 1, 0, eatype) + +/* Programs that use BTF to identify attach point */ +#define BPF_PROG_BTF(string, ptype, eatype) \ + BPF_PROG_SEC_IMPL(string, ptype, eatype, 0, 1, 0) /* Programs that can be attached but attach type can't be identified by section * name. Kept for backward compatibility. @@ -2577,16 +4982,27 @@ static const struct { size_t len; enum bpf_prog_type prog_type; enum bpf_attach_type expected_attach_type; - int is_attachable; + bool is_attachable; + bool is_attach_btf; enum bpf_attach_type attach_type; } section_names[] = { BPF_PROG_SEC("socket", BPF_PROG_TYPE_SOCKET_FILTER), BPF_PROG_SEC("kprobe/", BPF_PROG_TYPE_KPROBE), + BPF_PROG_SEC("uprobe/", BPF_PROG_TYPE_KPROBE), BPF_PROG_SEC("kretprobe/", BPF_PROG_TYPE_KPROBE), + BPF_PROG_SEC("uretprobe/", BPF_PROG_TYPE_KPROBE), BPF_PROG_SEC("classifier", BPF_PROG_TYPE_SCHED_CLS), BPF_PROG_SEC("action", BPF_PROG_TYPE_SCHED_ACT), BPF_PROG_SEC("tracepoint/", BPF_PROG_TYPE_TRACEPOINT), + BPF_PROG_SEC("tp/", BPF_PROG_TYPE_TRACEPOINT), BPF_PROG_SEC("raw_tracepoint/", BPF_PROG_TYPE_RAW_TRACEPOINT), + BPF_PROG_SEC("raw_tp/", BPF_PROG_TYPE_RAW_TRACEPOINT), + BPF_PROG_BTF("tp_btf/", BPF_PROG_TYPE_TRACING, + BPF_TRACE_RAW_TP), + BPF_PROG_BTF("fentry/", BPF_PROG_TYPE_TRACING, + BPF_TRACE_FENTRY), + BPF_PROG_BTF("fexit/", BPF_PROG_TYPE_TRACING, + BPF_TRACE_FEXIT), BPF_PROG_SEC("xdp", BPF_PROG_TYPE_XDP), BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT), BPF_PROG_SEC("lwt_in", BPF_PROG_TYPE_LWT_IN), @@ -2631,6 +5047,16 @@ static const struct { BPF_CGROUP_UDP4_SENDMSG), BPF_EAPROG_SEC("cgroup/sendmsg6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_SENDMSG), + BPF_EAPROG_SEC("cgroup/recvmsg4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + BPF_CGROUP_UDP4_RECVMSG), + BPF_EAPROG_SEC("cgroup/recvmsg6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + BPF_CGROUP_UDP6_RECVMSG), + BPF_EAPROG_SEC("cgroup/sysctl", BPF_PROG_TYPE_CGROUP_SYSCTL, + BPF_CGROUP_SYSCTL), + BPF_EAPROG_SEC("cgroup/getsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT, + BPF_CGROUP_GETSOCKOPT), + BPF_EAPROG_SEC("cgroup/setsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT, + BPF_CGROUP_SETSOCKOPT), }; #undef BPF_PROG_SEC_IMPL @@ -2683,14 +5109,105 @@ int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type, *expected_attach_type = section_names[i].expected_attach_type; return 0; } - pr_warning("failed to guess program type based on ELF section name '%s'\n", name); + pr_warn("failed to guess program type from ELF section '%s'\n", name); type_names = libbpf_get_type_names(false); if (type_names != NULL) { pr_info("supported section(type) names are:%s\n", type_names); free(type_names); } - return -EINVAL; + return -ESRCH; +} + +#define BTF_PREFIX "btf_trace_" +int libbpf_find_vmlinux_btf_id(const char *name, + enum bpf_attach_type attach_type) +{ + struct btf *btf = bpf_core_find_kernel_btf(); + char raw_tp_btf[128] = BTF_PREFIX; + char *dst = raw_tp_btf + sizeof(BTF_PREFIX) - 1; + const char *btf_name; + int err = -EINVAL; + __u32 kind; + + if (IS_ERR(btf)) { + pr_warn("vmlinux BTF is not found\n"); + return -EINVAL; + } + + if (attach_type == BPF_TRACE_RAW_TP) { + /* prepend "btf_trace_" prefix per kernel convention */ + strncat(dst, name, sizeof(raw_tp_btf) - sizeof(BTF_PREFIX)); + btf_name = raw_tp_btf; + kind = BTF_KIND_TYPEDEF; + } else { + btf_name = name; + kind = BTF_KIND_FUNC; + } + err = btf__find_by_name_kind(btf, btf_name, kind); + btf__free(btf); + return err; +} + +static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd) +{ + struct bpf_prog_info_linear *info_linear; + struct bpf_prog_info *info; + struct btf *btf = NULL; + int err = -EINVAL; + + info_linear = bpf_program__get_prog_info_linear(attach_prog_fd, 0); + if (IS_ERR_OR_NULL(info_linear)) { + pr_warn("failed get_prog_info_linear for FD %d\n", + attach_prog_fd); + return -EINVAL; + } + info = &info_linear->info; + if (!info->btf_id) { + pr_warn("The target program doesn't have BTF\n"); + goto out; + } + if (btf__get_from_id(info->btf_id, &btf)) { + pr_warn("Failed to get BTF of the program\n"); + goto out; + } + err = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC); + btf__free(btf); + if (err <= 0) { + pr_warn("%s is not found in prog's BTF\n", name); + goto out; + } +out: + free(info_linear); + return err; +} + +static int libbpf_find_attach_btf_id(const char *name, + enum bpf_attach_type attach_type, + __u32 attach_prog_fd) +{ + int i, err; + + if (!name) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(section_names); i++) { + if (!section_names[i].is_attach_btf) + continue; + if (strncmp(name, section_names[i].sec, section_names[i].len)) + continue; + if (attach_prog_fd) + err = libbpf_find_prog_btf_id(name + section_names[i].len, + attach_prog_fd); + else + err = libbpf_find_vmlinux_btf_id(name + section_names[i].len, + attach_type); + if (err <= 0) + pr_warn("%s is not found in vmlinux BTF\n", name); + return err; + } + pr_warn("failed to identify btf_id based on ELF section name '%s'\n", name); + return -ESRCH; } int libbpf_attach_type_by_name(const char *name, @@ -2710,7 +5227,7 @@ int libbpf_attach_type_by_name(const char *name, *attach_type = section_names[i].attach_type; return 0; } - pr_warning("failed to guess attach type based on ELF section name '%s'\n", name); + pr_warn("failed to guess attach type based on ELF section name '%s'\n", name); type_names = libbpf_get_type_names(true); if (type_names != NULL) { pr_info("attachable section(type) names are:%s\n", type_names); @@ -2720,26 +5237,17 @@ int libbpf_attach_type_by_name(const char *name, return -EINVAL; } -static int -bpf_program__identify_section(struct bpf_program *prog, - enum bpf_prog_type *prog_type, - enum bpf_attach_type *expected_attach_type) -{ - return libbpf_prog_type_by_name(prog->section_name, prog_type, - expected_attach_type); -} - -int bpf_map__fd(struct bpf_map *map) +int bpf_map__fd(const struct bpf_map *map) { return map ? map->fd : -EINVAL; } -const struct bpf_map_def *bpf_map__def(struct bpf_map *map) +const struct bpf_map_def *bpf_map__def(const struct bpf_map *map) { return map ? &map->def : ERR_PTR(-EINVAL); } -const char *bpf_map__name(struct bpf_map *map) +const char *bpf_map__name(const struct bpf_map *map) { return map ? map->name : NULL; } @@ -2770,16 +5278,21 @@ int bpf_map__set_priv(struct bpf_map *map, void *priv, return 0; } -void *bpf_map__priv(struct bpf_map *map) +void *bpf_map__priv(const struct bpf_map *map) { return map ? map->priv : ERR_PTR(-EINVAL); } -bool bpf_map__is_offload_neutral(struct bpf_map *map) +bool bpf_map__is_offload_neutral(const struct bpf_map *map) { return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY; } +bool bpf_map__is_internal(const struct bpf_map *map) +{ + return map->libbpf_type != LIBBPF_MAP_UNSPEC; +} + void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex) { map->map_ifindex = ifindex; @@ -2788,11 +5301,11 @@ void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex) int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd) { if (!bpf_map_type__is_map_in_map(map->def.type)) { - pr_warning("error: unsupported map type\n"); + pr_warn("error: unsupported map type\n"); return -EINVAL; } if (map->inner_map_fd != -1) { - pr_warning("error: inner_map_fd already specified\n"); + pr_warn("error: inner_map_fd already specified\n"); return -EINVAL; } map->inner_map_fd = fd; @@ -2800,7 +5313,7 @@ int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd) } static struct bpf_map * -__bpf_map__iter(struct bpf_map *m, struct bpf_object *obj, int i) +__bpf_map__iter(const struct bpf_map *m, const struct bpf_object *obj, int i) { ssize_t idx; struct bpf_map *s, *e; @@ -2812,8 +5325,8 @@ __bpf_map__iter(struct bpf_map *m, struct bpf_object *obj, int i) e = obj->maps + obj->nr_maps; if ((m < s) || (m >= e)) { - pr_warning("error in %s: map handler doesn't belong to object\n", - __func__); + pr_warn("error in %s: map handler doesn't belong to object\n", + __func__); return NULL; } @@ -2824,7 +5337,7 @@ __bpf_map__iter(struct bpf_map *m, struct bpf_object *obj, int i) } struct bpf_map * -bpf_map__next(struct bpf_map *prev, struct bpf_object *obj) +bpf_map__next(const struct bpf_map *prev, const struct bpf_object *obj) { if (prev == NULL) return obj->maps; @@ -2833,7 +5346,7 @@ bpf_map__next(struct bpf_map *prev, struct bpf_object *obj) } struct bpf_map * -bpf_map__prev(struct bpf_map *next, struct bpf_object *obj) +bpf_map__prev(const struct bpf_map *next, const struct bpf_object *obj) { if (next == NULL) { if (!obj->nr_maps) @@ -2845,7 +5358,7 @@ bpf_map__prev(struct bpf_map *next, struct bpf_object *obj) } struct bpf_map * -bpf_object__find_map_by_name(struct bpf_object *obj, const char *name) +bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name) { struct bpf_map *pos; @@ -2857,7 +5370,7 @@ bpf_object__find_map_by_name(struct bpf_object *obj, const char *name) } int -bpf_object__find_map_fd_by_name(struct bpf_object *obj, const char *name) +bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name) { return bpf_map__fd(bpf_object__find_map_by_name(obj, name)); } @@ -2865,20 +5378,12 @@ bpf_object__find_map_fd_by_name(struct bpf_object *obj, const char *name) struct bpf_map * bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset) { - int i; - - for (i = 0; i < obj->nr_maps; i++) { - if (obj->maps[i].offset == offset) - return &obj->maps[i]; - } - return ERR_PTR(-ENOENT); + return ERR_PTR(-ENOTSUP); } long libbpf_get_error(const void *ptr) { - if (IS_ERR(ptr)) - return PTR_ERR(ptr); - return 0; + return PTR_ERR_OR_ZERO(ptr); } int bpf_prog_load(const char *file, enum bpf_prog_type type, @@ -2897,13 +5402,8 @@ int bpf_prog_load(const char *file, enum bpf_prog_type type, int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, struct bpf_object **pobj, int *prog_fd) { - struct bpf_object_open_attr open_attr = { - .file = attr->file, - .prog_type = attr->prog_type, - }; + struct bpf_object_open_attr open_attr = {}; struct bpf_program *prog, *first_prog = NULL; - enum bpf_attach_type expected_attach_type; - enum bpf_prog_type prog_type; struct bpf_object *obj; struct bpf_map *map; int err; @@ -2913,31 +5413,37 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, if (!attr->file) return -EINVAL; + open_attr.file = attr->file; + open_attr.prog_type = attr->prog_type; + obj = bpf_object__open_xattr(&open_attr); if (IS_ERR_OR_NULL(obj)) return -ENOENT; bpf_object__for_each_program(prog, obj) { + enum bpf_attach_type attach_type = attr->expected_attach_type; /* - * If type is not specified, try to guess it based on - * section name. + * to preserve backwards compatibility, bpf_prog_load treats + * attr->prog_type, if specified, as an override to whatever + * bpf_object__open guessed */ - prog_type = attr->prog_type; - prog->prog_ifindex = attr->ifindex; - expected_attach_type = attr->expected_attach_type; - if (prog_type == BPF_PROG_TYPE_UNSPEC) { - err = bpf_program__identify_section(prog, &prog_type, - &expected_attach_type); - if (err < 0) { - bpf_object__close(obj); - return -EINVAL; - } + if (attr->prog_type != BPF_PROG_TYPE_UNSPEC) { + bpf_program__set_type(prog, attr->prog_type); + bpf_program__set_expected_attach_type(prog, + attach_type); + } + if (bpf_program__get_type(prog) == BPF_PROG_TYPE_UNSPEC) { + /* + * we haven't guessed from section name and user + * didn't provide a fallback type, too bad... + */ + bpf_object__close(obj); + return -EINVAL; } - bpf_program__set_type(prog, prog_type); - bpf_program__set_expected_attach_type(prog, - expected_attach_type); - + prog->prog_ifindex = attr->ifindex; + prog->log_level = attr->log_level; + prog->prog_flags = attr->prog_flags; if (!first_prog) first_prog = prog; } @@ -2948,7 +5454,7 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, } if (!first_prog) { - pr_warning("object file doesn't contain bpf program\n"); + pr_warn("object file doesn't contain bpf program\n"); bpf_object__close(obj); return -ENOENT; } @@ -2964,6 +5470,402 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, return 0; } +struct bpf_link { + int (*destroy)(struct bpf_link *link); +}; + +int bpf_link__destroy(struct bpf_link *link) +{ + int err; + + if (!link) + return 0; + + err = link->destroy(link); + free(link); + + return err; +} + +struct bpf_link_fd { + struct bpf_link link; /* has to be at the top of struct */ + int fd; /* hook FD */ +}; + +static int bpf_link__destroy_perf_event(struct bpf_link *link) +{ + struct bpf_link_fd *l = (void *)link; + int err; + + err = ioctl(l->fd, PERF_EVENT_IOC_DISABLE, 0); + if (err) + err = -errno; + + close(l->fd); + return err; +} + +struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog, + int pfd) +{ + char errmsg[STRERR_BUFSIZE]; + struct bpf_link_fd *link; + int prog_fd, err; + + if (pfd < 0) { + pr_warn("program '%s': invalid perf event FD %d\n", + bpf_program__title(prog, false), pfd); + return ERR_PTR(-EINVAL); + } + prog_fd = bpf_program__fd(prog); + if (prog_fd < 0) { + pr_warn("program '%s': can't attach BPF program w/o FD (did you load it?)\n", + bpf_program__title(prog, false)); + return ERR_PTR(-EINVAL); + } + + link = malloc(sizeof(*link)); + if (!link) + return ERR_PTR(-ENOMEM); + link->link.destroy = &bpf_link__destroy_perf_event; + link->fd = pfd; + + if (ioctl(pfd, PERF_EVENT_IOC_SET_BPF, prog_fd) < 0) { + err = -errno; + free(link); + pr_warn("program '%s': failed to attach to pfd %d: %s\n", + bpf_program__title(prog, false), pfd, + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + return ERR_PTR(err); + } + if (ioctl(pfd, PERF_EVENT_IOC_ENABLE, 0) < 0) { + err = -errno; + free(link); + pr_warn("program '%s': failed to enable pfd %d: %s\n", + bpf_program__title(prog, false), pfd, + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + return ERR_PTR(err); + } + return (struct bpf_link *)link; +} + +/* + * this function is expected to parse integer in the range of [0, 2^31-1] from + * given file using scanf format string fmt. If actual parsed value is + * negative, the result might be indistinguishable from error + */ +static int parse_uint_from_file(const char *file, const char *fmt) +{ + char buf[STRERR_BUFSIZE]; + int err, ret; + FILE *f; + + f = fopen(file, "r"); + if (!f) { + err = -errno; + pr_debug("failed to open '%s': %s\n", file, + libbpf_strerror_r(err, buf, sizeof(buf))); + return err; + } + err = fscanf(f, fmt, &ret); + if (err != 1) { + err = err == EOF ? -EIO : -errno; + pr_debug("failed to parse '%s': %s\n", file, + libbpf_strerror_r(err, buf, sizeof(buf))); + fclose(f); + return err; + } + fclose(f); + return ret; +} + +static int determine_kprobe_perf_type(void) +{ + const char *file = "/sys/bus/event_source/devices/kprobe/type"; + + return parse_uint_from_file(file, "%d\n"); +} + +static int determine_uprobe_perf_type(void) +{ + const char *file = "/sys/bus/event_source/devices/uprobe/type"; + + return parse_uint_from_file(file, "%d\n"); +} + +static int determine_kprobe_retprobe_bit(void) +{ + const char *file = "/sys/bus/event_source/devices/kprobe/format/retprobe"; + + return parse_uint_from_file(file, "config:%d\n"); +} + +static int determine_uprobe_retprobe_bit(void) +{ + const char *file = "/sys/bus/event_source/devices/uprobe/format/retprobe"; + + return parse_uint_from_file(file, "config:%d\n"); +} + +static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name, + uint64_t offset, int pid) +{ + struct perf_event_attr attr = {}; + char errmsg[STRERR_BUFSIZE]; + int type, pfd, err; + + type = uprobe ? determine_uprobe_perf_type() + : determine_kprobe_perf_type(); + if (type < 0) { + pr_warn("failed to determine %s perf type: %s\n", + uprobe ? "uprobe" : "kprobe", + libbpf_strerror_r(type, errmsg, sizeof(errmsg))); + return type; + } + if (retprobe) { + int bit = uprobe ? determine_uprobe_retprobe_bit() + : determine_kprobe_retprobe_bit(); + + if (bit < 0) { + pr_warn("failed to determine %s retprobe bit: %s\n", + uprobe ? "uprobe" : "kprobe", + libbpf_strerror_r(bit, errmsg, sizeof(errmsg))); + return bit; + } + attr.config |= 1 << bit; + } + attr.size = sizeof(attr); + attr.type = type; + attr.config1 = ptr_to_u64(name); /* kprobe_func or uprobe_path */ + attr.config2 = offset; /* kprobe_addr or probe_offset */ + + /* pid filter is meaningful only for uprobes */ + pfd = syscall(__NR_perf_event_open, &attr, + pid < 0 ? -1 : pid /* pid */, + pid == -1 ? 0 : -1 /* cpu */, + -1 /* group_fd */, PERF_FLAG_FD_CLOEXEC); + if (pfd < 0) { + err = -errno; + pr_warn("%s perf_event_open() failed: %s\n", + uprobe ? "uprobe" : "kprobe", + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + return err; + } + return pfd; +} + +struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog, + bool retprobe, + const char *func_name) +{ + char errmsg[STRERR_BUFSIZE]; + struct bpf_link *link; + int pfd, err; + + pfd = perf_event_open_probe(false /* uprobe */, retprobe, func_name, + 0 /* offset */, -1 /* pid */); + if (pfd < 0) { + pr_warn("program '%s': failed to create %s '%s' perf event: %s\n", + bpf_program__title(prog, false), + retprobe ? "kretprobe" : "kprobe", func_name, + libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); + return ERR_PTR(pfd); + } + link = bpf_program__attach_perf_event(prog, pfd); + if (IS_ERR(link)) { + close(pfd); + err = PTR_ERR(link); + pr_warn("program '%s': failed to attach to %s '%s': %s\n", + bpf_program__title(prog, false), + retprobe ? "kretprobe" : "kprobe", func_name, + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + return link; + } + return link; +} + +struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog, + bool retprobe, pid_t pid, + const char *binary_path, + size_t func_offset) +{ + char errmsg[STRERR_BUFSIZE]; + struct bpf_link *link; + int pfd, err; + + pfd = perf_event_open_probe(true /* uprobe */, retprobe, + binary_path, func_offset, pid); + if (pfd < 0) { + pr_warn("program '%s': failed to create %s '%s:0x%zx' perf event: %s\n", + bpf_program__title(prog, false), + retprobe ? "uretprobe" : "uprobe", + binary_path, func_offset, + libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); + return ERR_PTR(pfd); + } + link = bpf_program__attach_perf_event(prog, pfd); + if (IS_ERR(link)) { + close(pfd); + err = PTR_ERR(link); + pr_warn("program '%s': failed to attach to %s '%s:0x%zx': %s\n", + bpf_program__title(prog, false), + retprobe ? "uretprobe" : "uprobe", + binary_path, func_offset, + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + return link; + } + return link; +} + +static int determine_tracepoint_id(const char *tp_category, + const char *tp_name) +{ + char file[PATH_MAX]; + int ret; + + ret = snprintf(file, sizeof(file), + "/sys/kernel/debug/tracing/events/%s/%s/id", + tp_category, tp_name); + if (ret < 0) + return -errno; + if (ret >= sizeof(file)) { + pr_debug("tracepoint %s/%s path is too long\n", + tp_category, tp_name); + return -E2BIG; + } + return parse_uint_from_file(file, "%d\n"); +} + +static int perf_event_open_tracepoint(const char *tp_category, + const char *tp_name) +{ + struct perf_event_attr attr = {}; + char errmsg[STRERR_BUFSIZE]; + int tp_id, pfd, err; + + tp_id = determine_tracepoint_id(tp_category, tp_name); + if (tp_id < 0) { + pr_warn("failed to determine tracepoint '%s/%s' perf event ID: %s\n", + tp_category, tp_name, + libbpf_strerror_r(tp_id, errmsg, sizeof(errmsg))); + return tp_id; + } + + attr.type = PERF_TYPE_TRACEPOINT; + attr.size = sizeof(attr); + attr.config = tp_id; + + pfd = syscall(__NR_perf_event_open, &attr, -1 /* pid */, 0 /* cpu */, + -1 /* group_fd */, PERF_FLAG_FD_CLOEXEC); + if (pfd < 0) { + err = -errno; + pr_warn("tracepoint '%s/%s' perf_event_open() failed: %s\n", + tp_category, tp_name, + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + return err; + } + return pfd; +} + +struct bpf_link *bpf_program__attach_tracepoint(struct bpf_program *prog, + const char *tp_category, + const char *tp_name) +{ + char errmsg[STRERR_BUFSIZE]; + struct bpf_link *link; + int pfd, err; + + pfd = perf_event_open_tracepoint(tp_category, tp_name); + if (pfd < 0) { + pr_warn("program '%s': failed to create tracepoint '%s/%s' perf event: %s\n", + bpf_program__title(prog, false), + tp_category, tp_name, + libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); + return ERR_PTR(pfd); + } + link = bpf_program__attach_perf_event(prog, pfd); + if (IS_ERR(link)) { + close(pfd); + err = PTR_ERR(link); + pr_warn("program '%s': failed to attach to tracepoint '%s/%s': %s\n", + bpf_program__title(prog, false), + tp_category, tp_name, + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + return link; + } + return link; +} + +static int bpf_link__destroy_fd(struct bpf_link *link) +{ + struct bpf_link_fd *l = (void *)link; + + return close(l->fd); +} + +struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog, + const char *tp_name) +{ + char errmsg[STRERR_BUFSIZE]; + struct bpf_link_fd *link; + int prog_fd, pfd; + + prog_fd = bpf_program__fd(prog); + if (prog_fd < 0) { + pr_warn("program '%s': can't attach before loaded\n", + bpf_program__title(prog, false)); + return ERR_PTR(-EINVAL); + } + + link = malloc(sizeof(*link)); + if (!link) + return ERR_PTR(-ENOMEM); + link->link.destroy = &bpf_link__destroy_fd; + + pfd = bpf_raw_tracepoint_open(tp_name, prog_fd); + if (pfd < 0) { + pfd = -errno; + free(link); + pr_warn("program '%s': failed to attach to raw tracepoint '%s': %s\n", + bpf_program__title(prog, false), tp_name, + libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); + return ERR_PTR(pfd); + } + link->fd = pfd; + return (struct bpf_link *)link; +} + +struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog) +{ + char errmsg[STRERR_BUFSIZE]; + struct bpf_link_fd *link; + int prog_fd, pfd; + + prog_fd = bpf_program__fd(prog); + if (prog_fd < 0) { + pr_warn("program '%s': can't attach before loaded\n", + bpf_program__title(prog, false)); + return ERR_PTR(-EINVAL); + } + + link = malloc(sizeof(*link)); + if (!link) + return ERR_PTR(-ENOMEM); + link->link.destroy = &bpf_link__destroy_fd; + + pfd = bpf_raw_tracepoint_open(NULL, prog_fd); + if (pfd < 0) { + pfd = -errno; + free(link); + pr_warn("program '%s': failed to attach to trace: %s\n", + bpf_program__title(prog, false), + libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); + return ERR_PTR(pfd); + } + link->fd = pfd; + return (struct bpf_link *)link; +} + enum bpf_perf_event_ret bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size, void **copy_mem, size_t *copy_size, @@ -3012,6 +5914,370 @@ bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size, return ret; } +struct perf_buffer; + +struct perf_buffer_params { + struct perf_event_attr *attr; + /* if event_cb is specified, it takes precendence */ + perf_buffer_event_fn event_cb; + /* sample_cb and lost_cb are higher-level common-case callbacks */ + perf_buffer_sample_fn sample_cb; + perf_buffer_lost_fn lost_cb; + void *ctx; + int cpu_cnt; + int *cpus; + int *map_keys; +}; + +struct perf_cpu_buf { + struct perf_buffer *pb; + void *base; /* mmap()'ed memory */ + void *buf; /* for reconstructing segmented data */ + size_t buf_size; + int fd; + int cpu; + int map_key; +}; + +struct perf_buffer { + perf_buffer_event_fn event_cb; + perf_buffer_sample_fn sample_cb; + perf_buffer_lost_fn lost_cb; + void *ctx; /* passed into callbacks */ + + size_t page_size; + size_t mmap_size; + struct perf_cpu_buf **cpu_bufs; + struct epoll_event *events; + int cpu_cnt; + int epoll_fd; /* perf event FD */ + int map_fd; /* BPF_MAP_TYPE_PERF_EVENT_ARRAY BPF map FD */ +}; + +static void perf_buffer__free_cpu_buf(struct perf_buffer *pb, + struct perf_cpu_buf *cpu_buf) +{ + if (!cpu_buf) + return; + if (cpu_buf->base && + munmap(cpu_buf->base, pb->mmap_size + pb->page_size)) + pr_warn("failed to munmap cpu_buf #%d\n", cpu_buf->cpu); + if (cpu_buf->fd >= 0) { + ioctl(cpu_buf->fd, PERF_EVENT_IOC_DISABLE, 0); + close(cpu_buf->fd); + } + free(cpu_buf->buf); + free(cpu_buf); +} + +void perf_buffer__free(struct perf_buffer *pb) +{ + int i; + + if (!pb) + return; + if (pb->cpu_bufs) { + for (i = 0; i < pb->cpu_cnt && pb->cpu_bufs[i]; i++) { + struct perf_cpu_buf *cpu_buf = pb->cpu_bufs[i]; + + bpf_map_delete_elem(pb->map_fd, &cpu_buf->map_key); + perf_buffer__free_cpu_buf(pb, cpu_buf); + } + free(pb->cpu_bufs); + } + if (pb->epoll_fd >= 0) + close(pb->epoll_fd); + free(pb->events); + free(pb); +} + +static struct perf_cpu_buf * +perf_buffer__open_cpu_buf(struct perf_buffer *pb, struct perf_event_attr *attr, + int cpu, int map_key) +{ + struct perf_cpu_buf *cpu_buf; + char msg[STRERR_BUFSIZE]; + int err; + + cpu_buf = calloc(1, sizeof(*cpu_buf)); + if (!cpu_buf) + return ERR_PTR(-ENOMEM); + + cpu_buf->pb = pb; + cpu_buf->cpu = cpu; + cpu_buf->map_key = map_key; + + cpu_buf->fd = syscall(__NR_perf_event_open, attr, -1 /* pid */, cpu, + -1, PERF_FLAG_FD_CLOEXEC); + if (cpu_buf->fd < 0) { + err = -errno; + pr_warn("failed to open perf buffer event on cpu #%d: %s\n", + cpu, libbpf_strerror_r(err, msg, sizeof(msg))); + goto error; + } + + cpu_buf->base = mmap(NULL, pb->mmap_size + pb->page_size, + PROT_READ | PROT_WRITE, MAP_SHARED, + cpu_buf->fd, 0); + if (cpu_buf->base == MAP_FAILED) { + cpu_buf->base = NULL; + err = -errno; + pr_warn("failed to mmap perf buffer on cpu #%d: %s\n", + cpu, libbpf_strerror_r(err, msg, sizeof(msg))); + goto error; + } + + if (ioctl(cpu_buf->fd, PERF_EVENT_IOC_ENABLE, 0) < 0) { + err = -errno; + pr_warn("failed to enable perf buffer event on cpu #%d: %s\n", + cpu, libbpf_strerror_r(err, msg, sizeof(msg))); + goto error; + } + + return cpu_buf; + +error: + perf_buffer__free_cpu_buf(pb, cpu_buf); + return (struct perf_cpu_buf *)ERR_PTR(err); +} + +static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, + struct perf_buffer_params *p); + +struct perf_buffer *perf_buffer__new(int map_fd, size_t page_cnt, + const struct perf_buffer_opts *opts) +{ + struct perf_buffer_params p = {}; + struct perf_event_attr attr = { 0, }; + + attr.config = PERF_COUNT_SW_BPF_OUTPUT, + attr.type = PERF_TYPE_SOFTWARE; + attr.sample_type = PERF_SAMPLE_RAW; + attr.sample_period = 1; + attr.wakeup_events = 1; + + p.attr = &attr; + p.sample_cb = opts ? opts->sample_cb : NULL; + p.lost_cb = opts ? opts->lost_cb : NULL; + p.ctx = opts ? opts->ctx : NULL; + + return __perf_buffer__new(map_fd, page_cnt, &p); +} + +struct perf_buffer * +perf_buffer__new_raw(int map_fd, size_t page_cnt, + const struct perf_buffer_raw_opts *opts) +{ + struct perf_buffer_params p = {}; + + p.attr = opts->attr; + p.event_cb = opts->event_cb; + p.ctx = opts->ctx; + p.cpu_cnt = opts->cpu_cnt; + p.cpus = opts->cpus; + p.map_keys = opts->map_keys; + + return __perf_buffer__new(map_fd, page_cnt, &p); +} + +static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, + struct perf_buffer_params *p) +{ + struct bpf_map_info map = {}; + char msg[STRERR_BUFSIZE]; + struct perf_buffer *pb; + __u32 map_info_len; + int err, i; + + if (page_cnt & (page_cnt - 1)) { + pr_warn("page count should be power of two, but is %zu\n", + page_cnt); + return ERR_PTR(-EINVAL); + } + + map_info_len = sizeof(map); + err = bpf_obj_get_info_by_fd(map_fd, &map, &map_info_len); + if (err) { + err = -errno; + pr_warn("failed to get map info for map FD %d: %s\n", + map_fd, libbpf_strerror_r(err, msg, sizeof(msg))); + return ERR_PTR(err); + } + + if (map.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) { + pr_warn("map '%s' should be BPF_MAP_TYPE_PERF_EVENT_ARRAY\n", + map.name); + return ERR_PTR(-EINVAL); + } + + pb = calloc(1, sizeof(*pb)); + if (!pb) + return ERR_PTR(-ENOMEM); + + pb->event_cb = p->event_cb; + pb->sample_cb = p->sample_cb; + pb->lost_cb = p->lost_cb; + pb->ctx = p->ctx; + + pb->page_size = getpagesize(); + pb->mmap_size = pb->page_size * page_cnt; + pb->map_fd = map_fd; + + pb->epoll_fd = epoll_create1(EPOLL_CLOEXEC); + if (pb->epoll_fd < 0) { + err = -errno; + pr_warn("failed to create epoll instance: %s\n", + libbpf_strerror_r(err, msg, sizeof(msg))); + goto error; + } + + if (p->cpu_cnt > 0) { + pb->cpu_cnt = p->cpu_cnt; + } else { + pb->cpu_cnt = libbpf_num_possible_cpus(); + if (pb->cpu_cnt < 0) { + err = pb->cpu_cnt; + goto error; + } + if (map.max_entries < pb->cpu_cnt) + pb->cpu_cnt = map.max_entries; + } + + pb->events = calloc(pb->cpu_cnt, sizeof(*pb->events)); + if (!pb->events) { + err = -ENOMEM; + pr_warn("failed to allocate events: out of memory\n"); + goto error; + } + pb->cpu_bufs = calloc(pb->cpu_cnt, sizeof(*pb->cpu_bufs)); + if (!pb->cpu_bufs) { + err = -ENOMEM; + pr_warn("failed to allocate buffers: out of memory\n"); + goto error; + } + + for (i = 0; i < pb->cpu_cnt; i++) { + struct perf_cpu_buf *cpu_buf; + int cpu, map_key; + + cpu = p->cpu_cnt > 0 ? p->cpus[i] : i; + map_key = p->cpu_cnt > 0 ? p->map_keys[i] : i; + + cpu_buf = perf_buffer__open_cpu_buf(pb, p->attr, cpu, map_key); + if (IS_ERR(cpu_buf)) { + err = PTR_ERR(cpu_buf); + goto error; + } + + pb->cpu_bufs[i] = cpu_buf; + + err = bpf_map_update_elem(pb->map_fd, &map_key, + &cpu_buf->fd, 0); + if (err) { + err = -errno; + pr_warn("failed to set cpu #%d, key %d -> perf FD %d: %s\n", + cpu, map_key, cpu_buf->fd, + libbpf_strerror_r(err, msg, sizeof(msg))); + goto error; + } + + pb->events[i].events = EPOLLIN; + pb->events[i].data.ptr = cpu_buf; + if (epoll_ctl(pb->epoll_fd, EPOLL_CTL_ADD, cpu_buf->fd, + &pb->events[i]) < 0) { + err = -errno; + pr_warn("failed to epoll_ctl cpu #%d perf FD %d: %s\n", + cpu, cpu_buf->fd, + libbpf_strerror_r(err, msg, sizeof(msg))); + goto error; + } + } + + return pb; + +error: + if (pb) + perf_buffer__free(pb); + return ERR_PTR(err); +} + +struct perf_sample_raw { + struct perf_event_header header; + uint32_t size; + char data[0]; +}; + +struct perf_sample_lost { + struct perf_event_header header; + uint64_t id; + uint64_t lost; + uint64_t sample_id; +}; + +static enum bpf_perf_event_ret +perf_buffer__process_record(struct perf_event_header *e, void *ctx) +{ + struct perf_cpu_buf *cpu_buf = ctx; + struct perf_buffer *pb = cpu_buf->pb; + void *data = e; + + /* user wants full control over parsing perf event */ + if (pb->event_cb) + return pb->event_cb(pb->ctx, cpu_buf->cpu, e); + + switch (e->type) { + case PERF_RECORD_SAMPLE: { + struct perf_sample_raw *s = data; + + if (pb->sample_cb) + pb->sample_cb(pb->ctx, cpu_buf->cpu, s->data, s->size); + break; + } + case PERF_RECORD_LOST: { + struct perf_sample_lost *s = data; + + if (pb->lost_cb) + pb->lost_cb(pb->ctx, cpu_buf->cpu, s->lost); + break; + } + default: + pr_warn("unknown perf sample type %d\n", e->type); + return LIBBPF_PERF_EVENT_ERROR; + } + return LIBBPF_PERF_EVENT_CONT; +} + +static int perf_buffer__process_records(struct perf_buffer *pb, + struct perf_cpu_buf *cpu_buf) +{ + enum bpf_perf_event_ret ret; + + ret = bpf_perf_event_read_simple(cpu_buf->base, pb->mmap_size, + pb->page_size, &cpu_buf->buf, + &cpu_buf->buf_size, + perf_buffer__process_record, cpu_buf); + if (ret != LIBBPF_PERF_EVENT_CONT) + return ret; + return 0; +} + +int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms) +{ + int i, cnt, err; + + cnt = epoll_wait(pb->epoll_fd, pb->events, pb->cpu_cnt, timeout_ms); + for (i = 0; i < cnt; i++) { + struct perf_cpu_buf *cpu_buf = pb->events[i].data.ptr; + + err = perf_buffer__process_records(pb, cpu_buf); + if (err) { + pr_warn("error while processing records: %d\n", err); + return err; + } + } + return cnt < 0 ? -errno : cnt; +} + struct bpf_prog_info_array_desc { int array_offset; /* e.g. offset of jited_prog_insns */ int count_offset; /* e.g. offset of jited_prog_len */ @@ -3069,7 +6335,8 @@ static struct bpf_prog_info_array_desc bpf_prog_info_array_desc[] = { }; -static __u32 bpf_prog_info_read_offset_u32(struct bpf_prog_info *info, int offset) +static __u32 bpf_prog_info_read_offset_u32(struct bpf_prog_info *info, + int offset) { __u32 *array = (__u32 *)info; @@ -3078,7 +6345,8 @@ static __u32 bpf_prog_info_read_offset_u32(struct bpf_prog_info *info, int offse return -(int)offset; } -static __u64 bpf_prog_info_read_offset_u64(struct bpf_prog_info *info, int offset) +static __u64 bpf_prog_info_read_offset_u64(struct bpf_prog_info *info, + int offset) { __u64 *array = (__u64 *)info; @@ -3202,13 +6470,13 @@ bpf_program__get_prog_info_linear(int fd, __u64 arrays) v2 = bpf_prog_info_read_offset_u32(&info_linear->info, desc->count_offset); if (v1 != v2) - pr_warning("%s: mismatch in element count\n", __func__); + pr_warn("%s: mismatch in element count\n", __func__); v1 = bpf_prog_info_read_offset_u32(&info, desc->size_offset); v2 = bpf_prog_info_read_offset_u32(&info_linear->info, desc->size_offset); if (v1 != v2) - pr_warning("%s: mismatch in rec size\n", __func__); + pr_warn("%s: mismatch in rec size\n", __func__); } /* step 7: update info_len and data_len */ @@ -3257,3 +6525,63 @@ void bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear) desc->array_offset, addr); } } + +int libbpf_num_possible_cpus(void) +{ + static const char *fcpu = "/sys/devices/system/cpu/possible"; + int len = 0, n = 0, il = 0, ir = 0; + unsigned int start = 0, end = 0; + int tmp_cpus = 0; + static int cpus; + char buf[128]; + int error = 0; + int fd = -1; + + tmp_cpus = READ_ONCE(cpus); + if (tmp_cpus > 0) + return tmp_cpus; + + fd = open(fcpu, O_RDONLY); + if (fd < 0) { + error = errno; + pr_warn("Failed to open file %s: %s\n", fcpu, strerror(error)); + return -error; + } + len = read(fd, buf, sizeof(buf)); + close(fd); + if (len <= 0) { + error = len ? errno : EINVAL; + pr_warn("Failed to read # of possible cpus from %s: %s\n", + fcpu, strerror(error)); + return -error; + } + if (len == sizeof(buf)) { + pr_warn("File %s size overflow\n", fcpu); + return -EOVERFLOW; + } + buf[len] = '\0'; + + for (ir = 0, tmp_cpus = 0; ir <= len; ir++) { + /* Each sub string separated by ',' has format \d+-\d+ or \d+ */ + if (buf[ir] == ',' || buf[ir] == '\0') { + buf[ir] = '\0'; + n = sscanf(&buf[il], "%u-%u", &start, &end); + if (n <= 0) { + pr_warn("Failed to get # CPUs from %s\n", + &buf[il]); + return -EINVAL; + } else if (n == 1) { + end = start; + } + tmp_cpus += end - start + 1; + il = ir + 1; + } + } + if (tmp_cpus <= 0) { + pr_warn("Invalid #CPUs %d from %s\n", tmp_cpus, fcpu); + return -EINVAL; + } + + WRITE_ONCE(cpus, tmp_cpus); + return tmp_cpus; +} |
