From f07669df4c8df0b7134ae94be20a8b61bd157168 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Fri, 2 Apr 2021 09:26:34 +0800 Subject: libbpf: Remove redundant semi-colon Remove redundant semi-colon in finalize_btf_ext(). Signed-off-by: Yang Yingliang Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210402012634.1965453-1-yangyingliang@huawei.com --- tools/lib/bpf/linker.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/lib') diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c index 46b16cbdcda3..4e08bc07e635 100644 --- a/tools/lib/bpf/linker.c +++ b/tools/lib/bpf/linker.c @@ -1895,7 +1895,7 @@ static int finalize_btf_ext(struct bpf_linker *linker) hdr->func_info_len = funcs_sz; hdr->line_info_off = funcs_sz; hdr->line_info_len = lines_sz; - hdr->core_relo_off = funcs_sz + lines_sz;; + hdr->core_relo_off = funcs_sz + lines_sz; hdr->core_relo_len = core_relos_sz; if (funcs_sz) { -- cgit From 1e1032b0c4afaed7739a6681ff6b4cb120b82994 Mon Sep 17 00:00:00 2001 From: Hengqi Chen Date: Mon, 5 Apr 2021 12:01:19 +0800 Subject: libbpf: Fix KERNEL_VERSION macro Add missing ')' for KERNEL_VERSION macro. Signed-off-by: Hengqi Chen Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210405040119.802188-1-hengqi.chen@gmail.com --- tools/lib/bpf/bpf_helpers.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/lib') diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index cc2e51c64a54..b904128626c2 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -51,7 +51,7 @@ #endif #ifndef KERNEL_VERSION -#define KERNEL_VERSION(a,b,c) (((a) << 16) + ((b) << 8) + ((c) > 255 ? 255 : (c)) +#define KERNEL_VERSION(a, b, c) (((a) << 16) + ((b) << 8) + ((c) > 255 ? 255 : (c))) #endif /* -- cgit From b3278099b2f6e81771c6c2b70fcf9a56e9ba5d93 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 8 Apr 2021 09:13:08 +0300 Subject: libbpf: Add bpf_map__inner_map API The API gives access to inner map for map in map types (array or hash of map). It will be used to dynamically set max_entries in it. Signed-off-by: Yauheni Kaliuta Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210408061310.95877-7-yauheni.kaliuta@redhat.com --- tools/lib/bpf/libbpf.c | 10 ++++++++++ tools/lib/bpf/libbpf.h | 1 + tools/lib/bpf/libbpf.map | 1 + 3 files changed, 12 insertions(+) (limited to 'tools/lib') diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 7aad78dbb4b4..ed5586cce227 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -2194,6 +2194,7 @@ static int parse_btf_map_def(struct bpf_object *obj, map->inner_map = calloc(1, sizeof(*map->inner_map)); if (!map->inner_map) return -ENOMEM; + map->inner_map->fd = -1; map->inner_map->sec_idx = obj->efile.btf_maps_shndx; map->inner_map->name = malloc(strlen(map->name) + sizeof(".inner") + 1); @@ -3845,6 +3846,14 @@ __u32 bpf_map__max_entries(const struct bpf_map *map) return map->def.max_entries; } +struct bpf_map *bpf_map__inner_map(struct bpf_map *map) +{ + if (!bpf_map_type__is_map_in_map(map->def.type)) + return NULL; + + return map->inner_map; +} + int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries) { if (map->fd >= 0) @@ -9476,6 +9485,7 @@ int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd) pr_warn("error: inner_map_fd already specified\n"); return -EINVAL; } + zfree(&map->inner_map); map->inner_map_fd = fd; return 0; } diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index f500621d28e5..bec4e6a6e31d 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -480,6 +480,7 @@ LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path); LIBBPF_API int bpf_map__unpin(struct bpf_map *map, const char *path); LIBBPF_API int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd); +LIBBPF_API struct bpf_map *bpf_map__inner_map(struct bpf_map *map); LIBBPF_API long libbpf_get_error(const void *ptr); diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index f5990f7208ce..b9b29baf1df8 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -359,5 +359,6 @@ LIBBPF_0.4.0 { bpf_linker__finalize; bpf_linker__free; bpf_linker__new; + bpf_map__inner_map; bpf_object__set_kversion; } LIBBPF_0.3.0; -- cgit From d3d93e34bd98e4dbb002310fed08630f4b549a08 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 15 Apr 2021 07:18:17 -0700 Subject: libbpf: Remove unused field. relo->processed is set, but not used. Remove it. Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210415141817.53136-1-alexei.starovoitov@gmail.com --- tools/lib/bpf/libbpf.c | 15 +-------------- 1 file changed, 1 insertion(+), 14 deletions(-) (limited to 'tools/lib') diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index ed5586cce227..9cc2d45b0080 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -195,7 +195,6 @@ struct reloc_desc { int insn_idx; int map_idx; int sym_off; - bool processed; }; struct bpf_sec_def; @@ -3499,8 +3498,6 @@ static int bpf_program__record_reloc(struct bpf_program *prog, const char *sym_sec_name; struct bpf_map *map; - reloc_desc->processed = false; - if (!is_call_insn(insn) && !is_ldimm64_insn(insn)) { pr_warn("prog '%s': invalid relo against '%s' for insns[%d].code 0x%x\n", prog->name, sym_name, insn_idx, insn->code); @@ -6314,13 +6311,11 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog) case RELO_LD64: insn[0].src_reg = BPF_PSEUDO_MAP_FD; insn[0].imm = obj->maps[relo->map_idx].fd; - relo->processed = true; break; case RELO_DATA: insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; insn[1].imm = insn[0].imm + relo->sym_off; insn[0].imm = obj->maps[relo->map_idx].fd; - relo->processed = true; break; case RELO_EXTERN_VAR: ext = &obj->externs[relo->sym_off]; @@ -6338,13 +6333,11 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog) insn[1].imm = ext->ksym.addr >> 32; } } - relo->processed = true; break; case RELO_EXTERN_FUNC: ext = &obj->externs[relo->sym_off]; insn[0].src_reg = BPF_PSEUDO_KFUNC_CALL; insn[0].imm = ext->ksym.kernel_btf_id; - relo->processed = true; break; case RELO_SUBPROG_ADDR: insn[0].src_reg = BPF_PSEUDO_FUNC; @@ -6630,9 +6623,6 @@ bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog, * different main programs */ insn->imm = subprog->sub_insn_off - (prog->sub_insn_off + insn_idx) - 1; - if (relo) - relo->processed = true; - pr_debug("prog '%s': insn #%zu relocated, imm %d points to subprog '%s' (now at %zu offset)\n", prog->name, insn_idx, insn->imm, subprog->name, subprog->sub_insn_off); } @@ -6725,7 +6715,7 @@ static int bpf_object__relocate_calls(struct bpf_object *obj, struct bpf_program *prog) { struct bpf_program *subprog; - int i, j, err; + int i, err; /* mark all subprogs as not relocated (yet) within the context of * current main program @@ -6736,9 +6726,6 @@ bpf_object__relocate_calls(struct bpf_object *obj, struct bpf_program *prog) continue; subprog->sub_insn_off = 0; - for (j = 0; j < subprog->nr_reloc; j++) - if (subprog->reloc_desc[j].type == RELO_CALL) - subprog->reloc_desc[j].processed = false; } err = bpf_object__reloc_code(obj, prog, prog); -- cgit From 83cd92b46484aa8f64cdc0bff8ac6940d1f78519 Mon Sep 17 00:00:00 2001 From: Florent Revest Date: Mon, 19 Apr 2021 17:52:41 +0200 Subject: libbpf: Initialize the bpf_seq_printf parameters array field by field When initializing the __param array with a one liner, if all args are const, the initial array value will be placed in the rodata section but because libbpf does not support relocation in the rodata section, any pointer in this array will stay NULL. Fixes: c09add2fbc5a ("tools/libbpf: Add bpf_iter support") Signed-off-by: Florent Revest Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210419155243.1632274-5-revest@chromium.org --- tools/lib/bpf/bpf_tracing.h | 40 +++++++++++++++++++++++++++++----------- 1 file changed, 29 insertions(+), 11 deletions(-) (limited to 'tools/lib') diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h index f9ef37707888..1c2e91ee041d 100644 --- a/tools/lib/bpf/bpf_tracing.h +++ b/tools/lib/bpf/bpf_tracing.h @@ -413,20 +413,38 @@ typeof(name(0)) name(struct pt_regs *ctx) \ } \ static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args) +#define ___bpf_fill0(arr, p, x) do {} while (0) +#define ___bpf_fill1(arr, p, x) arr[p] = x +#define ___bpf_fill2(arr, p, x, args...) arr[p] = x; ___bpf_fill1(arr, p + 1, args) +#define ___bpf_fill3(arr, p, x, args...) arr[p] = x; ___bpf_fill2(arr, p + 1, args) +#define ___bpf_fill4(arr, p, x, args...) arr[p] = x; ___bpf_fill3(arr, p + 1, args) +#define ___bpf_fill5(arr, p, x, args...) arr[p] = x; ___bpf_fill4(arr, p + 1, args) +#define ___bpf_fill6(arr, p, x, args...) arr[p] = x; ___bpf_fill5(arr, p + 1, args) +#define ___bpf_fill7(arr, p, x, args...) arr[p] = x; ___bpf_fill6(arr, p + 1, args) +#define ___bpf_fill8(arr, p, x, args...) arr[p] = x; ___bpf_fill7(arr, p + 1, args) +#define ___bpf_fill9(arr, p, x, args...) arr[p] = x; ___bpf_fill8(arr, p + 1, args) +#define ___bpf_fill10(arr, p, x, args...) arr[p] = x; ___bpf_fill9(arr, p + 1, args) +#define ___bpf_fill11(arr, p, x, args...) arr[p] = x; ___bpf_fill10(arr, p + 1, args) +#define ___bpf_fill12(arr, p, x, args...) arr[p] = x; ___bpf_fill11(arr, p + 1, args) +#define ___bpf_fill(arr, args...) \ + ___bpf_apply(___bpf_fill, ___bpf_narg(args))(arr, 0, args) + /* * BPF_SEQ_PRINTF to wrap bpf_seq_printf to-be-printed values * in a structure. */ -#define BPF_SEQ_PRINTF(seq, fmt, args...) \ - ({ \ - _Pragma("GCC diagnostic push") \ - _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ - static const char ___fmt[] = fmt; \ - unsigned long long ___param[] = { args }; \ - _Pragma("GCC diagnostic pop") \ - int ___ret = bpf_seq_printf(seq, ___fmt, sizeof(___fmt), \ - ___param, sizeof(___param)); \ - ___ret; \ - }) +#define BPF_SEQ_PRINTF(seq, fmt, args...) \ +({ \ + static const char ___fmt[] = fmt; \ + unsigned long long ___param[___bpf_narg(args)]; \ + \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + ___bpf_fill(___param, args); \ + _Pragma("GCC diagnostic pop") \ + \ + bpf_seq_printf(seq, ___fmt, sizeof(___fmt), \ + ___param, sizeof(___param)); \ +}) #endif -- cgit From 58c2b1f5e0121efd698b6ec8e45e47e58ca9caee Mon Sep 17 00:00:00 2001 From: Florent Revest Date: Mon, 19 Apr 2021 17:52:42 +0200 Subject: libbpf: Introduce a BPF_SNPRINTF helper macro Similarly to BPF_SEQ_PRINTF, this macro turns variadic arguments into an array of u64, making it more natural to call the bpf_snprintf helper. Signed-off-by: Florent Revest Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210419155243.1632274-6-revest@chromium.org --- tools/lib/bpf/bpf_tracing.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'tools/lib') diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h index 1c2e91ee041d..8c954ebc0c7c 100644 --- a/tools/lib/bpf/bpf_tracing.h +++ b/tools/lib/bpf/bpf_tracing.h @@ -447,4 +447,22 @@ static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args) ___param, sizeof(___param)); \ }) +/* + * BPF_SNPRINTF wraps the bpf_snprintf helper with variadic arguments instead of + * an array of u64. + */ +#define BPF_SNPRINTF(out, out_size, fmt, args...) \ +({ \ + static const char ___fmt[] = fmt; \ + unsigned long long ___param[___bpf_narg(args)]; \ + \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + ___bpf_fill(___param, args); \ + _Pragma("GCC diagnostic pop") \ + \ + bpf_snprintf(out, out_size, ___fmt, \ + ___param, sizeof(___param)); \ +}) + #endif -- cgit From 0fec7a3cee1cf8e4f86ff563d229408ccbdc2d66 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 23 Apr 2021 11:13:33 -0700 Subject: libbpf: Suppress compiler warning when using SEC() macro with externs When used on externs SEC() macro will trigger compilation warning about inapplicable `__attribute__((used))`. That's expected for extern declarations, so suppress it with the corresponding _Pragma. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210423181348.1801389-4-andrii@kernel.org --- tools/lib/bpf/bpf_helpers.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'tools/lib') diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index b904128626c2..75c7581b304c 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -25,9 +25,16 @@ /* * Helper macro to place programs, maps, license in * different sections in elf_bpf file. Section names - * are interpreted by elf_bpf loader + * are interpreted by libbpf depending on the context (BPF programs, BPF maps, + * extern variables, etc). + * To allow use of SEC() with externs (e.g., for extern .maps declarations), + * make sure __attribute__((unused)) doesn't trigger compilation warning. */ -#define SEC(NAME) __attribute__((section(NAME), used)) +#define SEC(name) \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wignored-attributes\"") \ + __attribute__((section(name), used)) \ + _Pragma("GCC diagnostic pop") \ /* Avoid 'linux/stddef.h' definition of '__always_inline'. */ #undef __always_inline -- cgit From aea28a602fa19fb4fe66374030ab7e2c8ddf643e Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 23 Apr 2021 11:13:34 -0700 Subject: libbpf: Mark BPF subprogs with hidden visibility as static for BPF verifier Define __hidden helper macro in bpf_helpers.h, which is a short-hand for __attribute__((visibility("hidden"))). Add libbpf support to mark BPF subprograms marked with __hidden as static in BTF information to enforce BPF verifier's static function validation algorithm, which takes more information (caller's context) into account during a subprogram validation. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210423181348.1801389-5-andrii@kernel.org --- tools/lib/bpf/bpf_helpers.h | 8 ++++++++ tools/lib/bpf/btf.c | 5 ----- tools/lib/bpf/libbpf.c | 45 ++++++++++++++++++++++++++++++++++++++++- tools/lib/bpf/libbpf_internal.h | 6 ++++++ 4 files changed, 58 insertions(+), 6 deletions(-) (limited to 'tools/lib') diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index 75c7581b304c..9720dc0b4605 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -47,6 +47,14 @@ #define __weak __attribute__((weak)) #endif +/* + * Use __hidden attribute to mark a non-static BPF subprogram effectively + * static for BPF verifier's verification algorithm purposes, allowing more + * extensive and permissive BPF verification process, taking into account + * subprogram's caller context. + */ +#define __hidden __attribute__((visibility("hidden"))) + /* When utilizing vmlinux.h with BPF CO-RE, user BPF programs can't include * any system-level headers (such as stddef.h, linux/version.h, etc), and * commonly-used macros like NULL and KERNEL_VERSION aren't available through diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index d30e67e7e1e5..d57e13a13798 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -1605,11 +1605,6 @@ static void *btf_add_type_mem(struct btf *btf, size_t add_sz) btf->hdr->type_len, UINT_MAX, add_sz); } -static __u32 btf_type_info(int kind, int vlen, int kflag) -{ - return (kflag << 31) | (kind << 24) | vlen; -} - static void btf_type_inc_vlen(struct btf_type *t) { t->info = btf_type_info(btf_kind(t), btf_vlen(t) + 1, btf_kflag(t)); diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 9cc2d45b0080..8bac9c7627aa 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -71,6 +71,7 @@ static struct bpf_map *bpf_object__add_map(struct bpf_object *obj); static const struct btf_type * skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id); +static bool prog_is_subprog(const struct bpf_object *obj, const struct bpf_program *prog); static int __base_pr(enum libbpf_print_level level, const char *format, va_list args) @@ -274,6 +275,7 @@ struct bpf_program { bpf_program_clear_priv_t clear_priv; bool load; + bool mark_btf_static; enum bpf_prog_type type; enum bpf_attach_type expected_attach_type; int prog_ifindex; @@ -698,6 +700,15 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data, if (err) return err; + /* if function is a global/weak symbol, but has hidden + * visibility (STV_HIDDEN), mark its BTF FUNC as static to + * enable more permissive BPF verification mode with more + * outside context available to BPF verifier + */ + if (GELF_ST_BIND(sym.st_info) != STB_LOCAL + && GELF_ST_VISIBILITY(sym.st_other) == STV_HIDDEN) + prog->mark_btf_static = true; + nr_progs++; obj->nr_programs = nr_progs; @@ -2618,7 +2629,7 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) { struct btf *kern_btf = obj->btf; bool btf_mandatory, sanitize; - int err = 0; + int i, err = 0; if (!obj->btf) return 0; @@ -2632,6 +2643,38 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) return 0; } + /* Even though some subprogs are global/weak, user might prefer more + * permissive BPF verification process that BPF verifier performs for + * static functions, taking into account more context from the caller + * functions. In such case, they need to mark such subprogs with + * __attribute__((visibility("hidden"))) and libbpf will adjust + * corresponding FUNC BTF type to be marked as static and trigger more + * involved BPF verification process. + */ + for (i = 0; i < obj->nr_programs; i++) { + struct bpf_program *prog = &obj->programs[i]; + struct btf_type *t; + const char *name; + int j, n; + + if (!prog->mark_btf_static || !prog_is_subprog(obj, prog)) + continue; + + n = btf__get_nr_types(obj->btf); + for (j = 1; j <= n; j++) { + t = btf_type_by_id(obj->btf, j); + if (!btf_is_func(t) || btf_func_linkage(t) != BTF_FUNC_GLOBAL) + continue; + + name = btf__str_by_offset(obj->btf, t->name_off); + if (strcmp(name, prog->name) != 0) + continue; + + t->info = btf_type_info(BTF_KIND_FUNC, BTF_FUNC_STATIC, 0); + break; + } + } + sanitize = btf_needs_sanitization(obj); if (sanitize) { const void *raw_data; diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 6017902c687e..92b7eae10c6d 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -19,6 +19,7 @@ #pragma GCC poison reallocarray #include "libbpf.h" +#include "btf.h" #ifndef EM_BPF #define EM_BPF 247 @@ -132,6 +133,11 @@ struct btf_type; struct btf_type *btf_type_by_id(struct btf *btf, __u32 type_id); +static inline __u32 btf_type_info(int kind, int vlen, int kflag) +{ + return (kflag << 31) | (kind << 24) | vlen; +} + void *libbpf_add_mem(void **data, size_t *cap_cnt, size_t elem_sz, size_t cur_cnt, size_t max_cnt, size_t add_cnt); int libbpf_ensure_mem(void **data, size_t *cap_cnt, size_t elem_sz, size_t need_cnt); -- cgit From 6245947c1b3c6783976e3af113bac30250d0a93e Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 23 Apr 2021 11:13:35 -0700 Subject: libbpf: Allow gaps in BPF program sections to support overriden weak functions Currently libbpf is very strict about parsing BPF program instruction sections. No gaps are allowed between sequential BPF programs within a given ELF section. Libbpf enforced that by keeping track of the next section offset that should start a new BPF (sub)program and cross-checks that by searching for a corresponding STT_FUNC ELF symbol. But this is too restrictive once we allow to have weak BPF programs and link together two or more BPF object files. In such case, some weak BPF programs might be "overridden" by either non-weak BPF program with the same name and signature, or even by another weak BPF program that just happened to be linked first. That, in turn, leaves BPF instructions of the "lost" BPF (sub)program intact, but there is no corresponding ELF symbol, because no one is going to be referencing it. Libbpf already correctly handles such cases in the sense that it won't append such dead code to actual BPF programs loaded into kernel. So the only change that needs to be done is to relax the logic of parsing BPF instruction sections. Instead of assuming next BPF (sub)program section offset, iterate available STT_FUNC ELF symbols to discover all available BPF subprograms and programs. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210423181348.1801389-6-andrii@kernel.org --- tools/lib/bpf/libbpf.c | 58 +++++++++++++++++++------------------------------- 1 file changed, 22 insertions(+), 36 deletions(-) (limited to 'tools/lib') diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 8bac9c7627aa..198d6e149beb 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -502,8 +502,6 @@ static Elf_Scn *elf_sec_by_name(const struct bpf_object *obj, const char *name); static int elf_sec_hdr(const struct bpf_object *obj, Elf_Scn *scn, GElf_Shdr *hdr); static const char *elf_sec_name(const struct bpf_object *obj, Elf_Scn *scn); static Elf_Data *elf_sec_data(const struct bpf_object *obj, Elf_Scn *scn); -static int elf_sym_by_sec_off(const struct bpf_object *obj, size_t sec_idx, - size_t off, __u32 sym_type, GElf_Sym *sym); void bpf_program__unload(struct bpf_program *prog) { @@ -644,25 +642,29 @@ static int bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data, const char *sec_name, int sec_idx) { + Elf_Data *symbols = obj->efile.symbols; struct bpf_program *prog, *progs; void *data = sec_data->d_buf; - size_t sec_sz = sec_data->d_size, sec_off, prog_sz; - int nr_progs, err; + size_t sec_sz = sec_data->d_size, sec_off, prog_sz, nr_syms; + int nr_progs, err, i; const char *name; GElf_Sym sym; progs = obj->programs; nr_progs = obj->nr_programs; + nr_syms = symbols->d_size / sizeof(GElf_Sym); sec_off = 0; - while (sec_off < sec_sz) { - if (elf_sym_by_sec_off(obj, sec_idx, sec_off, STT_FUNC, &sym)) { - pr_warn("sec '%s': failed to find program symbol at offset %zu\n", - sec_name, sec_off); - return -LIBBPF_ERRNO__FORMAT; - } + for (i = 0; i < nr_syms; i++) { + if (!gelf_getsym(symbols, i, &sym)) + continue; + if (sym.st_shndx != sec_idx) + continue; + if (GELF_ST_TYPE(sym.st_info) != STT_FUNC) + continue; prog_sz = sym.st_size; + sec_off = sym.st_value; name = elf_sym_str(obj, sym.st_name); if (!name) { @@ -711,8 +713,6 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data, nr_progs++; obj->nr_programs = nr_progs; - - sec_off += prog_sz; } return 0; @@ -2825,26 +2825,6 @@ static Elf_Data *elf_sec_data(const struct bpf_object *obj, Elf_Scn *scn) return data; } -static int elf_sym_by_sec_off(const struct bpf_object *obj, size_t sec_idx, - size_t off, __u32 sym_type, GElf_Sym *sym) -{ - Elf_Data *symbols = obj->efile.symbols; - size_t n = symbols->d_size / sizeof(GElf_Sym); - int i; - - for (i = 0; i < n; i++) { - if (!gelf_getsym(symbols, i, sym)) - continue; - if (sym->st_shndx != sec_idx || sym->st_value != off) - continue; - if (GELF_ST_TYPE(sym->st_info) != sym_type) - continue; - return 0; - } - - return -ENOENT; -} - static bool is_sec_name_dwarf(const char *name) { /* approximation, but the actual list is too long */ @@ -3723,11 +3703,16 @@ bpf_object__collect_prog_relos(struct bpf_object *obj, GElf_Shdr *shdr, Elf_Data int err, i, nrels; const char *sym_name; __u32 insn_idx; + Elf_Scn *scn; + Elf_Data *scn_data; GElf_Sym sym; GElf_Rel rel; + scn = elf_sec_by_idx(obj, sec_idx); + scn_data = elf_sec_data(obj, scn); + relo_sec_name = elf_sec_str(obj, shdr->sh_name); - sec_name = elf_sec_name(obj, elf_sec_by_idx(obj, sec_idx)); + sec_name = elf_sec_name(obj, scn); if (!relo_sec_name || !sec_name) return -EINVAL; @@ -3745,7 +3730,8 @@ bpf_object__collect_prog_relos(struct bpf_object *obj, GElf_Shdr *shdr, Elf_Data relo_sec_name, (size_t)GELF_R_SYM(rel.r_info), i); return -LIBBPF_ERRNO__FORMAT; } - if (rel.r_offset % BPF_INSN_SZ) { + + if (rel.r_offset % BPF_INSN_SZ || rel.r_offset >= scn_data->d_size) { pr_warn("sec '%s': invalid offset 0x%zx for relo #%d\n", relo_sec_name, (size_t)GELF_R_SYM(rel.r_info), i); return -LIBBPF_ERRNO__FORMAT; @@ -3769,9 +3755,9 @@ bpf_object__collect_prog_relos(struct bpf_object *obj, GElf_Shdr *shdr, Elf_Data prog = find_prog_by_sec_insn(obj, sec_idx, insn_idx); if (!prog) { - pr_warn("sec '%s': relo #%d: program not found in section '%s' for insn #%u\n", + pr_debug("sec '%s': relo #%d: couldn't find program in section '%s' for insn #%u, probably overridden weak function, skipping...\n", relo_sec_name, i, sec_name, insn_idx); - return -LIBBPF_ERRNO__RELOC; + continue; } relos = libbpf_reallocarray(prog->reloc_desc, -- cgit From c7ef5ec9573f05535370d8716576263681cabec7 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 23 Apr 2021 11:13:36 -0700 Subject: libbpf: Refactor BTF map definition parsing Refactor BTF-defined maps parsing logic to allow it to be nicely reused by BPF static linker. Further, at least for BPF static linker, it's important to know which attributes of a BPF map were defined explicitly, so provide a bit set for each known portion of BTF map definition. This allows BPF static linker to do a simple check when dealing with extern map declarations. The same capabilities allow to distinguish attributes explicitly set to zero (e.g., __uint(max_entries, 0)) vs the case of not specifying it at all (no max_entries attribute at all). Libbpf is currently not utilizing that, but it could be useful for backwards compatibility reasons later. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210423181348.1801389-7-andrii@kernel.org --- tools/lib/bpf/libbpf.c | 257 +++++++++++++++++++++++----------------- tools/lib/bpf/libbpf_internal.h | 32 +++++ 2 files changed, 178 insertions(+), 111 deletions(-) (limited to 'tools/lib') diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 198d6e149beb..4f8335fc0bc9 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -2025,255 +2025,262 @@ static int build_map_pin_path(struct bpf_map *map, const char *path) return bpf_map__set_pin_path(map, buf); } - -static int parse_btf_map_def(struct bpf_object *obj, - struct bpf_map *map, - const struct btf_type *def, - bool strict, bool is_inner, - const char *pin_root_path) +int parse_btf_map_def(const char *map_name, struct btf *btf, + const struct btf_type *def_t, bool strict, + struct btf_map_def *map_def, struct btf_map_def *inner_def) { const struct btf_type *t; const struct btf_member *m; + bool is_inner = inner_def == NULL; int vlen, i; - vlen = btf_vlen(def); - m = btf_members(def); + vlen = btf_vlen(def_t); + m = btf_members(def_t); for (i = 0; i < vlen; i++, m++) { - const char *name = btf__name_by_offset(obj->btf, m->name_off); + const char *name = btf__name_by_offset(btf, m->name_off); if (!name) { - pr_warn("map '%s': invalid field #%d.\n", map->name, i); + 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, m, - &map->def.type)) + if (!get_map_field_int(map_name, btf, m, &map_def->map_type)) return -EINVAL; - pr_debug("map '%s': found type = %u.\n", - map->name, map->def.type); + map_def->parts |= MAP_DEF_MAP_TYPE; } else if (strcmp(name, "max_entries") == 0) { - if (!get_map_field_int(map->name, obj->btf, m, - &map->def.max_entries)) + if (!get_map_field_int(map_name, btf, m, &map_def->max_entries)) return -EINVAL; - pr_debug("map '%s': found max_entries = %u.\n", - map->name, map->def.max_entries); + map_def->parts |= MAP_DEF_MAX_ENTRIES; } else if (strcmp(name, "map_flags") == 0) { - if (!get_map_field_int(map->name, obj->btf, m, - &map->def.map_flags)) + if (!get_map_field_int(map_name, btf, m, &map_def->map_flags)) return -EINVAL; - pr_debug("map '%s': found map_flags = %u.\n", - map->name, map->def.map_flags); + map_def->parts |= MAP_DEF_MAP_FLAGS; } else if (strcmp(name, "numa_node") == 0) { - if (!get_map_field_int(map->name, obj->btf, m, &map->numa_node)) + if (!get_map_field_int(map_name, btf, m, &map_def->numa_node)) return -EINVAL; - pr_debug("map '%s': found numa_node = %u.\n", map->name, map->numa_node); + map_def->parts |= MAP_DEF_NUMA_NODE; } else if (strcmp(name, "key_size") == 0) { __u32 sz; - if (!get_map_field_int(map->name, obj->btf, m, &sz)) + if (!get_map_field_int(map_name, btf, 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) { + 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); + map_name, map_def->key_size, sz); return -EINVAL; } - map->def.key_size = sz; + map_def->key_size = sz; + map_def->parts |= MAP_DEF_KEY_SIZE; } else if (strcmp(name, "key") == 0) { __s64 sz; - t = btf__type_by_id(obj->btf, m->type); + t = btf__type_by_id(btf, m->type); if (!t) { pr_warn("map '%s': key type [%d] not found.\n", - map->name, m->type); + map_name, m->type); return -EINVAL; } if (!btf_is_ptr(t)) { pr_warn("map '%s': key spec is not PTR: %s.\n", - map->name, btf_kind_str(t)); + map_name, btf_kind_str(t)); return -EINVAL; } - sz = btf__resolve_size(obj->btf, t->type); + sz = btf__resolve_size(btf, t->type); if (sz < 0) { pr_warn("map '%s': can't determine key size for type [%u]: %zd.\n", - map->name, t->type, (ssize_t)sz); + map_name, t->type, (ssize_t)sz); return sz; } - pr_debug("map '%s': found key [%u], sz = %zd.\n", - map->name, t->type, (ssize_t)sz); - if (map->def.key_size && map->def.key_size != sz) { + if (map_def->key_size && map_def->key_size != sz) { pr_warn("map '%s': conflicting key size %u != %zd.\n", - map->name, map->def.key_size, (ssize_t)sz); + map_name, map_def->key_size, (ssize_t)sz); return -EINVAL; } - map->def.key_size = sz; - map->btf_key_type_id = t->type; + map_def->key_size = sz; + map_def->key_type_id = t->type; + map_def->parts |= MAP_DEF_KEY_SIZE | MAP_DEF_KEY_TYPE; } else if (strcmp(name, "value_size") == 0) { __u32 sz; - if (!get_map_field_int(map->name, obj->btf, m, &sz)) + if (!get_map_field_int(map_name, btf, 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) { + 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); + map_name, map_def->value_size, sz); return -EINVAL; } - map->def.value_size = sz; + map_def->value_size = sz; + map_def->parts |= MAP_DEF_VALUE_SIZE; } else if (strcmp(name, "value") == 0) { __s64 sz; - t = btf__type_by_id(obj->btf, m->type); + t = btf__type_by_id(btf, m->type); if (!t) { pr_warn("map '%s': value type [%d] not found.\n", - map->name, m->type); + map_name, m->type); return -EINVAL; } if (!btf_is_ptr(t)) { pr_warn("map '%s': value spec is not PTR: %s.\n", - map->name, btf_kind_str(t)); + map_name, btf_kind_str(t)); return -EINVAL; } - sz = btf__resolve_size(obj->btf, t->type); + sz = btf__resolve_size(btf, t->type); if (sz < 0) { pr_warn("map '%s': can't determine value size for type [%u]: %zd.\n", - map->name, t->type, (ssize_t)sz); + map_name, t->type, (ssize_t)sz); return sz; } - pr_debug("map '%s': found value [%u], sz = %zd.\n", - map->name, t->type, (ssize_t)sz); - if (map->def.value_size && map->def.value_size != sz) { + if (map_def->value_size && map_def->value_size != sz) { pr_warn("map '%s': conflicting value size %u != %zd.\n", - map->name, map->def.value_size, (ssize_t)sz); + map_name, map_def->value_size, (ssize_t)sz); return -EINVAL; } - map->def.value_size = sz; - map->btf_value_type_id = t->type; + map_def->value_size = sz; + map_def->value_type_id = t->type; + map_def->parts |= MAP_DEF_VALUE_SIZE | MAP_DEF_VALUE_TYPE; } else if (strcmp(name, "values") == 0) { + char inner_map_name[128]; int err; if (is_inner) { pr_warn("map '%s': multi-level inner maps not supported.\n", - map->name); + map_name); return -ENOTSUP; } if (i != vlen - 1) { pr_warn("map '%s': '%s' member should be last.\n", - map->name, name); + map_name, name); return -EINVAL; } - if (!bpf_map_type__is_map_in_map(map->def.type)) { + if (!bpf_map_type__is_map_in_map(map_def->map_type)) { pr_warn("map '%s': should be map-in-map.\n", - map->name); + map_name); return -ENOTSUP; } - if (map->def.value_size && map->def.value_size != 4) { + if (map_def->value_size && map_def->value_size != 4) { pr_warn("map '%s': conflicting value size %u != 4.\n", - map->name, map->def.value_size); + map_name, map_def->value_size); return -EINVAL; } - map->def.value_size = 4; - t = btf__type_by_id(obj->btf, m->type); + map_def->value_size = 4; + t = btf__type_by_id(btf, m->type); if (!t) { pr_warn("map '%s': map-in-map inner type [%d] not found.\n", - map->name, m->type); + map_name, m->type); return -EINVAL; } if (!btf_is_array(t) || btf_array(t)->nelems) { pr_warn("map '%s': map-in-map inner spec is not a zero-sized array.\n", - map->name); + map_name); return -EINVAL; } - t = skip_mods_and_typedefs(obj->btf, btf_array(t)->type, - NULL); + t = skip_mods_and_typedefs(btf, btf_array(t)->type, NULL); if (!btf_is_ptr(t)) { pr_warn("map '%s': map-in-map inner def is of unexpected kind %s.\n", - map->name, btf_kind_str(t)); + map_name, btf_kind_str(t)); return -EINVAL; } - t = skip_mods_and_typedefs(obj->btf, t->type, NULL); + t = skip_mods_and_typedefs(btf, t->type, NULL); if (!btf_is_struct(t)) { pr_warn("map '%s': map-in-map inner def is of unexpected kind %s.\n", - map->name, btf_kind_str(t)); + map_name, btf_kind_str(t)); return -EINVAL; } - map->inner_map = calloc(1, sizeof(*map->inner_map)); - if (!map->inner_map) - return -ENOMEM; - map->inner_map->fd = -1; - map->inner_map->sec_idx = obj->efile.btf_maps_shndx; - map->inner_map->name = malloc(strlen(map->name) + - sizeof(".inner") + 1); - if (!map->inner_map->name) - return -ENOMEM; - sprintf(map->inner_map->name, "%s.inner", map->name); - - err = parse_btf_map_def(obj, map->inner_map, t, strict, - true /* is_inner */, NULL); + snprintf(inner_map_name, sizeof(inner_map_name), "%s.inner", map_name); + err = parse_btf_map_def(inner_map_name, btf, t, strict, inner_def, NULL); if (err) return err; + + map_def->parts |= MAP_DEF_INNER_MAP; } else if (strcmp(name, "pinning") == 0) { __u32 val; - int err; if (is_inner) { - pr_debug("map '%s': inner def can't be pinned.\n", - map->name); + pr_warn("map '%s': inner def can't be pinned.\n", map_name); return -EINVAL; } - if (!get_map_field_int(map->name, obj->btf, m, &val)) + if (!get_map_field_int(map_name, btf, 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) { + if (val != LIBBPF_PIN_NONE && val != LIBBPF_PIN_BY_NAME) { pr_warn("map '%s': invalid pinning value %u.\n", - map->name, val); + 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; - } - } + map_def->pinning = val; + map_def->parts |= MAP_DEF_PINNING; } else { if (strict) { - pr_warn("map '%s': unknown field '%s'.\n", - map->name, name); + 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); + 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); + if (map_def->map_type == BPF_MAP_TYPE_UNSPEC) { + pr_warn("map '%s': map type isn't specified.\n", map_name); return -EINVAL; } return 0; } +static void fill_map_from_def(struct bpf_map *map, const struct btf_map_def *def) +{ + map->def.type = def->map_type; + map->def.key_size = def->key_size; + map->def.value_size = def->value_size; + map->def.max_entries = def->max_entries; + map->def.map_flags = def->map_flags; + + map->numa_node = def->numa_node; + map->btf_key_type_id = def->key_type_id; + map->btf_value_type_id = def->value_type_id; + + if (def->parts & MAP_DEF_MAP_TYPE) + pr_debug("map '%s': found type = %u.\n", map->name, def->map_type); + + if (def->parts & MAP_DEF_KEY_TYPE) + pr_debug("map '%s': found key [%u], sz = %u.\n", + map->name, def->key_type_id, def->key_size); + else if (def->parts & MAP_DEF_KEY_SIZE) + pr_debug("map '%s': found key_size = %u.\n", map->name, def->key_size); + + if (def->parts & MAP_DEF_VALUE_TYPE) + pr_debug("map '%s': found value [%u], sz = %u.\n", + map->name, def->value_type_id, def->value_size); + else if (def->parts & MAP_DEF_VALUE_SIZE) + pr_debug("map '%s': found value_size = %u.\n", map->name, def->value_size); + + if (def->parts & MAP_DEF_MAX_ENTRIES) + pr_debug("map '%s': found max_entries = %u.\n", map->name, def->max_entries); + if (def->parts & MAP_DEF_MAP_FLAGS) + pr_debug("map '%s': found map_flags = %u.\n", map->name, def->map_flags); + if (def->parts & MAP_DEF_PINNING) + pr_debug("map '%s': found pinning = %u.\n", map->name, def->pinning); + if (def->parts & MAP_DEF_NUMA_NODE) + pr_debug("map '%s': found numa_node = %u.\n", map->name, def->numa_node); + + if (def->parts & MAP_DEF_INNER_MAP) + pr_debug("map '%s': found inner map definition.\n", map->name); +} + 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) { + struct btf_map_def map_def = {}, inner_def = {}; const struct btf_type *var, *def; const struct btf_var_secinfo *vi; const struct btf_var *var_extra; const char *map_name; struct bpf_map *map; + int err; vi = btf_var_secinfos(sec) + var_idx; var = btf__type_by_id(obj->btf, vi->type); @@ -2327,7 +2334,35 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, pr_debug("map '%s': at sec_idx %d, offset %zu.\n", map_name, map->sec_idx, map->sec_offset); - return parse_btf_map_def(obj, map, def, strict, false, pin_root_path); + err = parse_btf_map_def(map->name, obj->btf, def, strict, &map_def, &inner_def); + if (err) + return err; + + fill_map_from_def(map, &map_def); + + if (map_def.pinning == 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; + } + } + + if (map_def.parts & MAP_DEF_INNER_MAP) { + map->inner_map = calloc(1, sizeof(*map->inner_map)); + if (!map->inner_map) + return -ENOMEM; + map->inner_map->fd = -1; + map->inner_map->sec_idx = sec_idx; + map->inner_map->name = malloc(strlen(map_name) + sizeof(".inner") + 1); + if (!map->inner_map->name) + return -ENOMEM; + sprintf(map->inner_map->name, "%s.inner", map_name); + + fill_map_from_def(map->inner_map, &inner_def); + } + + return 0; } static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict, diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 92b7eae10c6d..17883073710c 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -138,6 +138,38 @@ static inline __u32 btf_type_info(int kind, int vlen, int kflag) return (kflag << 31) | (kind << 24) | vlen; } +enum map_def_parts { + MAP_DEF_MAP_TYPE = 0x001, + MAP_DEF_KEY_TYPE = 0x002, + MAP_DEF_KEY_SIZE = 0x004, + MAP_DEF_VALUE_TYPE = 0x008, + MAP_DEF_VALUE_SIZE = 0x010, + MAP_DEF_MAX_ENTRIES = 0x020, + MAP_DEF_MAP_FLAGS = 0x040, + MAP_DEF_NUMA_NODE = 0x080, + MAP_DEF_PINNING = 0x100, + MAP_DEF_INNER_MAP = 0x200, + + MAP_DEF_ALL = 0x3ff, /* combination of all above */ +}; + +struct btf_map_def { + enum map_def_parts parts; + __u32 map_type; + __u32 key_type_id; + __u32 key_size; + __u32 value_type_id; + __u32 value_size; + __u32 max_entries; + __u32 map_flags; + __u32 numa_node; + __u32 pinning; +}; + +int parse_btf_map_def(const char *map_name, struct btf *btf, + const struct btf_type *def_t, bool strict, + struct btf_map_def *map_def, struct btf_map_def *inner_def); + void *libbpf_add_mem(void **data, size_t *cap_cnt, size_t elem_sz, size_t cur_cnt, size_t max_cnt, size_t add_cnt); int libbpf_ensure_mem(void **data, size_t *cap_cnt, size_t elem_sz, size_t need_cnt); -- cgit From beaa3711ada4e4a0c8e03a78fec72330185213bf Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 23 Apr 2021 11:13:37 -0700 Subject: libbpf: Factor out symtab and relos sanity checks Factor out logic for sanity checking SHT_SYMTAB and SHT_REL sections into separate sections. They are already quite extensive and are suffering from too deep indentation. Subsequent changes will extend SYMTAB sanity checking further, so it's better to factor each into a separate function. No functional changes are intended. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210423181348.1801389-8-andrii@kernel.org --- tools/lib/bpf/linker.c | 233 +++++++++++++++++++++++++++---------------------- 1 file changed, 127 insertions(+), 106 deletions(-) (limited to 'tools/lib') diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c index 4e08bc07e635..0bb927226370 100644 --- a/tools/lib/bpf/linker.c +++ b/tools/lib/bpf/linker.c @@ -131,6 +131,8 @@ static int init_output_elf(struct bpf_linker *linker, const char *file); static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, struct src_obj *obj); static int linker_sanity_check_elf(struct src_obj *obj); +static int linker_sanity_check_elf_symtab(struct src_obj *obj, struct src_sec *sec); +static int linker_sanity_check_elf_relos(struct src_obj *obj, struct src_sec *sec); static int linker_sanity_check_btf(struct src_obj *obj); static int linker_sanity_check_btf_ext(struct src_obj *obj); static int linker_fixup_btf(struct src_obj *obj); @@ -663,8 +665,8 @@ static bool is_pow_of_2(size_t x) static int linker_sanity_check_elf(struct src_obj *obj) { - struct src_sec *sec, *link_sec; - int i, j, n; + struct src_sec *sec; + int i, err; if (!obj->symtab_sec_idx) { pr_warn("ELF is missing SYMTAB section in %s\n", obj->filename); @@ -692,43 +694,11 @@ static int linker_sanity_check_elf(struct src_obj *obj) return -EINVAL; switch (sec->shdr->sh_type) { - case SHT_SYMTAB: { - Elf64_Sym *sym; - - if (sec->shdr->sh_entsize != sizeof(Elf64_Sym)) - return -EINVAL; - if (sec->shdr->sh_size % sec->shdr->sh_entsize != 0) - return -EINVAL; - - if (!sec->shdr->sh_link || sec->shdr->sh_link >= obj->sec_cnt) { - pr_warn("ELF SYMTAB section #%zu points to missing STRTAB section #%zu in %s\n", - sec->sec_idx, (size_t)sec->shdr->sh_link, obj->filename); - return -EINVAL; - } - link_sec = &obj->secs[sec->shdr->sh_link]; - if (link_sec->shdr->sh_type != SHT_STRTAB) { - pr_warn("ELF SYMTAB section #%zu points to invalid STRTAB section #%zu in %s\n", - sec->sec_idx, (size_t)sec->shdr->sh_link, obj->filename); - return -EINVAL; - } - - n = sec->shdr->sh_size / sec->shdr->sh_entsize; - sym = sec->data->d_buf; - for (j = 0; j < n; j++, sym++) { - if (sym->st_shndx - && sym->st_shndx < SHN_LORESERVE - && sym->st_shndx >= obj->sec_cnt) { - pr_warn("ELF sym #%d in section #%zu points to missing section #%zu in %s\n", - j, sec->sec_idx, (size_t)sym->st_shndx, obj->filename); - return -EINVAL; - } - if (ELF64_ST_TYPE(sym->st_info) == STT_SECTION) { - if (sym->st_value != 0) - return -EINVAL; - } - } + case SHT_SYMTAB: + err = linker_sanity_check_elf_symtab(obj, sec); + if (err) + return err; break; - } case SHT_STRTAB: break; case SHT_PROGBITS: @@ -739,87 +709,138 @@ static int linker_sanity_check_elf(struct src_obj *obj) break; case SHT_NOBITS: break; - case SHT_REL: { - Elf64_Rel *relo; - struct src_sec *sym_sec; + case SHT_REL: + err = linker_sanity_check_elf_relos(obj, sec); + if (err) + return err; + break; + case SHT_LLVM_ADDRSIG: + break; + default: + pr_warn("ELF section #%zu (%s) has unrecognized type %zu in %s\n", + sec->sec_idx, sec->sec_name, (size_t)sec->shdr->sh_type, obj->filename); + return -EINVAL; + } + } - if (sec->shdr->sh_entsize != sizeof(Elf64_Rel)) - return -EINVAL; - if (sec->shdr->sh_size % sec->shdr->sh_entsize != 0) - return -EINVAL; + return 0; +} - /* SHT_REL's sh_link should point to SYMTAB */ - if (sec->shdr->sh_link != obj->symtab_sec_idx) { - pr_warn("ELF relo section #%zu points to invalid SYMTAB section #%zu in %s\n", - sec->sec_idx, (size_t)sec->shdr->sh_link, obj->filename); - return -EINVAL; - } +static int linker_sanity_check_elf_symtab(struct src_obj *obj, struct src_sec *sec) +{ + struct src_sec *link_sec; + Elf64_Sym *sym; + int i, n; - /* SHT_REL's sh_info points to relocated section */ - if (!sec->shdr->sh_info || sec->shdr->sh_info >= obj->sec_cnt) { - pr_warn("ELF relo section #%zu points to missing section #%zu in %s\n", - sec->sec_idx, (size_t)sec->shdr->sh_info, obj->filename); - return -EINVAL; - } - link_sec = &obj->secs[sec->shdr->sh_info]; + if (sec->shdr->sh_entsize != sizeof(Elf64_Sym)) + return -EINVAL; + if (sec->shdr->sh_size % sec->shdr->sh_entsize != 0) + return -EINVAL; + + if (!sec->shdr->sh_link || sec->shdr->sh_link >= obj->sec_cnt) { + pr_warn("ELF SYMTAB section #%zu points to missing STRTAB section #%zu in %s\n", + sec->sec_idx, (size_t)sec->shdr->sh_link, obj->filename); + return -EINVAL; + } + link_sec = &obj->secs[sec->shdr->sh_link]; + if (link_sec->shdr->sh_type != SHT_STRTAB) { + pr_warn("ELF SYMTAB section #%zu points to invalid STRTAB section #%zu in %s\n", + sec->sec_idx, (size_t)sec->shdr->sh_link, obj->filename); + return -EINVAL; + } - /* .rel -> pattern is followed */ - if (strncmp(sec->sec_name, ".rel", sizeof(".rel") - 1) != 0 - || strcmp(sec->sec_name + sizeof(".rel") - 1, link_sec->sec_name) != 0) { - pr_warn("ELF relo section #%zu name has invalid name in %s\n", - sec->sec_idx, obj->filename); + n = sec->shdr->sh_size / sec->shdr->sh_entsize; + sym = sec->data->d_buf; + for (i = 0; i < n; i++, sym++) { + if (sym->st_shndx + && sym->st_shndx < SHN_LORESERVE + && sym->st_shndx >= obj->sec_cnt) { + pr_warn("ELF sym #%d in section #%zu points to missing section #%zu in %s\n", + i, sec->sec_idx, (size_t)sym->st_shndx, obj->filename); + return -EINVAL; + } + if (ELF64_ST_TYPE(sym->st_info) == STT_SECTION) { + if (sym->st_value != 0) return -EINVAL; - } + continue; + } + } - /* don't further validate relocations for ignored sections */ - if (link_sec->skipped) - break; + return 0; +} - /* relocatable section is data or instructions */ - if (link_sec->shdr->sh_type != SHT_PROGBITS - && link_sec->shdr->sh_type != SHT_NOBITS) { - pr_warn("ELF relo section #%zu points to invalid section #%zu in %s\n", - sec->sec_idx, (size_t)sec->shdr->sh_info, obj->filename); - return -EINVAL; - } +static int linker_sanity_check_elf_relos(struct src_obj *obj, struct src_sec *sec) +{ + struct src_sec *link_sec, *sym_sec; + Elf64_Rel *relo; + int i, n; - /* check sanity of each relocation */ - n = sec->shdr->sh_size / sec->shdr->sh_entsize; - relo = sec->data->d_buf; - sym_sec = &obj->secs[obj->symtab_sec_idx]; - for (j = 0; j < n; j++, relo++) { - size_t sym_idx = ELF64_R_SYM(relo->r_info); - size_t sym_type = ELF64_R_TYPE(relo->r_info); - - if (sym_type != R_BPF_64_64 && sym_type != R_BPF_64_32) { - pr_warn("ELF relo #%d in section #%zu has unexpected type %zu in %s\n", - j, sec->sec_idx, sym_type, obj->filename); - return -EINVAL; - } + if (sec->shdr->sh_entsize != sizeof(Elf64_Rel)) + return -EINVAL; + if (sec->shdr->sh_size % sec->shdr->sh_entsize != 0) + return -EINVAL; - if (!sym_idx || sym_idx * sizeof(Elf64_Sym) >= sym_sec->shdr->sh_size) { - pr_warn("ELF relo #%d in section #%zu points to invalid symbol #%zu in %s\n", - j, sec->sec_idx, sym_idx, obj->filename); - return -EINVAL; - } + /* SHT_REL's sh_link should point to SYMTAB */ + if (sec->shdr->sh_link != obj->symtab_sec_idx) { + pr_warn("ELF relo section #%zu points to invalid SYMTAB section #%zu in %s\n", + sec->sec_idx, (size_t)sec->shdr->sh_link, obj->filename); + return -EINVAL; + } - if (link_sec->shdr->sh_flags & SHF_EXECINSTR) { - if (relo->r_offset % sizeof(struct bpf_insn) != 0) { - pr_warn("ELF relo #%d in section #%zu points to missing symbol #%zu in %s\n", - j, sec->sec_idx, sym_idx, obj->filename); - return -EINVAL; - } - } - } - break; + /* SHT_REL's sh_info points to relocated section */ + if (!sec->shdr->sh_info || sec->shdr->sh_info >= obj->sec_cnt) { + pr_warn("ELF relo section #%zu points to missing section #%zu in %s\n", + sec->sec_idx, (size_t)sec->shdr->sh_info, obj->filename); + return -EINVAL; + } + link_sec = &obj->secs[sec->shdr->sh_info]; + + /* .rel -> pattern is followed */ + if (strncmp(sec->sec_name, ".rel", sizeof(".rel") - 1) != 0 + || strcmp(sec->sec_name + sizeof(".rel") - 1, link_sec->sec_name) != 0) { + pr_warn("ELF relo section #%zu name has invalid name in %s\n", + sec->sec_idx, obj->filename); + return -EINVAL; + } + + /* don't further validate relocations for ignored sections */ + if (link_sec->skipped) + return 0; + + /* relocatable section is data or instructions */ + if (link_sec->shdr->sh_type != SHT_PROGBITS && link_sec->shdr->sh_type != SHT_NOBITS) { + pr_warn("ELF relo section #%zu points to invalid section #%zu in %s\n", + sec->sec_idx, (size_t)sec->shdr->sh_info, obj->filename); + return -EINVAL; + } + + /* check sanity of each relocation */ + n = sec->shdr->sh_size / sec->shdr->sh_entsize; + relo = sec->data->d_buf; + sym_sec = &obj->secs[obj->symtab_sec_idx]; + for (i = 0; i < n; i++, relo++) { + size_t sym_idx = ELF64_R_SYM(relo->r_info); + size_t sym_type = ELF64_R_TYPE(relo->r_info); + + if (sym_type != R_BPF_64_64 && sym_type != R_BPF_64_32) { + pr_warn("ELF relo #%d in section #%zu has unexpected type %zu in %s\n", + i, sec->sec_idx, sym_type, obj->filename); + return -EINVAL; } - case SHT_LLVM_ADDRSIG: - break; - default: - pr_warn("ELF section #%zu (%s) has unrecognized type %zu in %s\n", - sec->sec_idx, sec->sec_name, (size_t)sec->shdr->sh_type, obj->filename); + + if (!sym_idx || sym_idx * sizeof(Elf64_Sym) >= sym_sec->shdr->sh_size) { + pr_warn("ELF relo #%d in section #%zu points to invalid symbol #%zu in %s\n", + i, sec->sec_idx, sym_idx, obj->filename); return -EINVAL; } + + if (link_sec->shdr->sh_flags & SHF_EXECINSTR) { + if (relo->r_offset % sizeof(struct bpf_insn) != 0) { + pr_warn("ELF relo #%d in section #%zu points to missing symbol #%zu in %s\n", + i, sec->sec_idx, sym_idx, obj->filename); + return -EINVAL; + } + } } return 0; -- cgit From 42869d28527695a75346c988ceeedbba7e3880b7 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 23 Apr 2021 11:13:38 -0700 Subject: libbpf: Make few internal helpers available outside of libbpf.c Make skip_mods_and_typedefs(), btf_kind_str(), and btf_func_linkage() helpers available outside of libbpf.c, to be used by static linker code. Also do few cleanups (error code fixes, comment clean up, etc) that don't deserve their own commit. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210423181348.1801389-9-andrii@kernel.org --- tools/lib/bpf/libbpf.c | 13 +++---------- tools/lib/bpf/libbpf_internal.h | 7 +++++++ tools/lib/bpf/linker.c | 14 ++++++-------- 3 files changed, 16 insertions(+), 18 deletions(-) (limited to 'tools/lib') diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 4f8335fc0bc9..a1cddd17af7d 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -69,8 +69,6 @@ #define __printf(a, b) __attribute__((format(printf, a, b))) static struct bpf_map *bpf_object__add_map(struct bpf_object *obj); -static const struct btf_type * -skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id); static bool prog_is_subprog(const struct bpf_object *obj, const struct bpf_program *prog); static int __base_pr(enum libbpf_print_level level, const char *format, @@ -1906,7 +1904,7 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) return 0; } -static const struct btf_type * +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); @@ -1961,16 +1959,11 @@ static const char *__btf_kind_str(__u16 kind) } } -static const char *btf_kind_str(const struct btf_type *t) +const char *btf_kind_str(const struct btf_type *t) { return __btf_kind_str(btf_kind(t)); } -static enum btf_func_linkage btf_func_linkage(const struct btf_type *t) -{ - return (enum btf_func_linkage)BTF_INFO_VLEN(t->info); -} - /* * Fetch integer attribute of BTF map definition. Such attributes are * represented using a pointer to an array, in which dimensionality of array @@ -7036,7 +7029,7 @@ static bool insn_is_helper_call(struct bpf_insn *insn, enum bpf_func_id *func_id return false; } -static int bpf_object__sanitize_prog(struct bpf_object* obj, struct bpf_program *prog) +static int bpf_object__sanitize_prog(struct bpf_object *obj, struct bpf_program *prog) { struct bpf_insn *insn = prog->insns; enum bpf_func_id func_id; diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 17883073710c..ee426226928f 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -132,6 +132,13 @@ struct btf; struct btf_type; struct btf_type *btf_type_by_id(struct btf *btf, __u32 type_id); +const char *btf_kind_str(const struct btf_type *t); +const struct btf_type *skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id); + +static inline enum btf_func_linkage btf_func_linkage(const struct btf_type *t) +{ + return (enum btf_func_linkage)(int)btf_vlen(t); +} static inline __u32 btf_type_info(int kind, int vlen, int kflag) { diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c index 0bb927226370..1263641e8b97 100644 --- a/tools/lib/bpf/linker.c +++ b/tools/lib/bpf/linker.c @@ -123,9 +123,7 @@ struct bpf_linker { }; #define pr_warn_elf(fmt, ...) \ -do { \ - libbpf_print(LIBBPF_WARN, "libbpf: " fmt ": %s\n", ##__VA_ARGS__, elf_errmsg(-1)); \ -} while (0) + libbpf_print(LIBBPF_WARN, "libbpf: " fmt ": %s\n", ##__VA_ARGS__, elf_errmsg(-1)) static int init_output_elf(struct bpf_linker *linker, const char *file); @@ -284,7 +282,7 @@ static int init_output_elf(struct bpf_linker *linker, const char *file) /* ELF header */ linker->elf_hdr = elf64_newehdr(linker->elf); - if (!linker->elf_hdr){ + if (!linker->elf_hdr) { pr_warn_elf("failed to create ELF header"); return -EINVAL; } @@ -925,13 +923,13 @@ static int init_sec(struct bpf_linker *linker, struct dst_sec *dst_sec, struct s scn = elf_newscn(linker->elf); if (!scn) - return -1; + return -ENOMEM; data = elf_newdata(scn); if (!data) - return -1; + return -ENOMEM; shdr = elf64_getshdr(scn); if (!shdr) - return -1; + return -ENOMEM; dst_sec->scn = scn; dst_sec->shdr = shdr; @@ -1221,7 +1219,7 @@ static int linker_append_elf_relos(struct bpf_linker *linker, struct src_obj *ob return err; } } else if (!secs_match(dst_sec, src_sec)) { - pr_warn("Secs %s are not compatible\n", src_sec->sec_name); + pr_warn("sections %s are not compatible\n", src_sec->sec_name); return -1; } -- cgit From 386b1d241e1b975a239d33be836bc183a52ab18c Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 23 Apr 2021 11:13:39 -0700 Subject: libbpf: Extend sanity checking ELF symbols with externs validation Add logic to validate extern symbols, plus some other minor extra checks, like ELF symbol #0 validation, general symbol visibility and binding validations. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210423181348.1801389-10-andrii@kernel.org --- tools/lib/bpf/linker.c | 49 ++++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 40 insertions(+), 9 deletions(-) (limited to 'tools/lib') diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c index 1263641e8b97..b0e038480300 100644 --- a/tools/lib/bpf/linker.c +++ b/tools/lib/bpf/linker.c @@ -750,14 +750,45 @@ static int linker_sanity_check_elf_symtab(struct src_obj *obj, struct src_sec *s n = sec->shdr->sh_size / sec->shdr->sh_entsize; sym = sec->data->d_buf; for (i = 0; i < n; i++, sym++) { - if (sym->st_shndx - && sym->st_shndx < SHN_LORESERVE - && sym->st_shndx >= obj->sec_cnt) { + int sym_type = ELF64_ST_TYPE(sym->st_info); + int sym_bind = ELF64_ST_BIND(sym->st_info); + int sym_vis = ELF64_ST_VISIBILITY(sym->st_other); + + if (i == 0) { + if (sym->st_name != 0 || sym->st_info != 0 + || sym->st_other != 0 || sym->st_shndx != 0 + || sym->st_value != 0 || sym->st_size != 0) { + pr_warn("ELF sym #0 is invalid in %s\n", obj->filename); + return -EINVAL; + } + continue; + } + if (sym_bind != STB_LOCAL && sym_bind != STB_GLOBAL && sym_bind != STB_WEAK) { + pr_warn("ELF sym #%d in section #%zu has unsupported symbol binding %d\n", + i, sec->sec_idx, sym_bind); + return -EINVAL; + } + if (sym_vis != STV_DEFAULT && sym_vis != STV_HIDDEN) { + pr_warn("ELF sym #%d in section #%zu has unsupported symbol visibility %d\n", + i, sec->sec_idx, sym_vis); + return -EINVAL; + } + if (sym->st_shndx == 0) { + if (sym_type != STT_NOTYPE || sym_bind == STB_LOCAL + || sym->st_value != 0 || sym->st_size != 0) { + pr_warn("ELF sym #%d is invalid extern symbol in %s\n", + i, obj->filename); + + return -EINVAL; + } + continue; + } + if (sym->st_shndx < SHN_LORESERVE && sym->st_shndx >= obj->sec_cnt) { pr_warn("ELF sym #%d in section #%zu points to missing section #%zu in %s\n", i, sec->sec_idx, (size_t)sym->st_shndx, obj->filename); return -EINVAL; } - if (ELF64_ST_TYPE(sym->st_info) == STT_SECTION) { + if (sym_type == STT_SECTION) { if (sym->st_value != 0) return -EINVAL; continue; @@ -1135,16 +1166,16 @@ static int linker_append_elf_syms(struct bpf_linker *linker, struct src_obj *obj size_t dst_sym_idx; int name_off; - /* we already have all-zero initial symbol */ - if (sym->st_name == 0 && sym->st_info == 0 && - sym->st_other == 0 && sym->st_shndx == SHN_UNDEF && - sym->st_value == 0 && sym->st_size ==0) + /* We already validated all-zero symbol #0 and we already + * appended it preventively to the final SYMTAB, so skip it. + */ + if (i == 0) continue; sym_name = elf_strptr(obj->elf, str_sec_idx, sym->st_name); if (!sym_name) { pr_warn("can't fetch symbol name for symbol #%d in '%s'\n", i, obj->filename); - return -1; + return -EINVAL; } if (sym->st_shndx && sym->st_shndx < SHN_LORESERVE) { -- cgit From 83a157279f2125ce1c4d6d93750440853746dff0 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 23 Apr 2021 11:13:40 -0700 Subject: libbpf: Tighten BTF type ID rewriting with error checking It should never fail, but if it does, it's better to know about this rather than end up with nonsensical type IDs. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210423181348.1801389-11-andrii@kernel.org --- tools/lib/bpf/linker.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'tools/lib') diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c index b0e038480300..5505c85e8b7b 100644 --- a/tools/lib/bpf/linker.c +++ b/tools/lib/bpf/linker.c @@ -1429,6 +1429,13 @@ static int linker_fixup_btf(struct src_obj *obj) static int remap_type_id(__u32 *type_id, void *ctx) { int *id_map = ctx; + int new_id = id_map[*type_id]; + + /* Error out if the type wasn't remapped. Ignore VOID which stays VOID. */ + if (new_id == 0 && *type_id != 0) { + pr_warn("failed to find new ID mapping for original BTF type ID %u\n", *type_id); + return -EINVAL; + } *type_id = id_map[*type_id]; -- cgit From a46349227cd832b33c12f74b85712ea67de3c6c4 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 23 Apr 2021 11:13:41 -0700 Subject: libbpf: Add linker extern resolution support for functions and global variables Add BPF static linker logic to resolve extern variables and functions across multiple linked together BPF object files. For that, linker maintains a separate list of struct glob_sym structures, which keeps track of few pieces of metadata (is it extern or resolved global, is it a weak symbol, which ELF section it belongs to, etc) and ties together BTF type info and ELF symbol information and keeps them in sync. With adding support for extern variables/funcs, it's now possible for some sections to contain both extern and non-extern definitions. This means that some sections may start out as ephemeral (if only externs are present and thus there is not corresponding ELF section), but will be "upgraded" to actual ELF section as symbols are resolved or new non-extern definitions are appended. Additional care is taken to not duplicate extern entries in sections like .kconfig and .ksyms. Given libbpf requires BTF type to always be present for .kconfig/.ksym externs, linker extends this requirement to all the externs, even those that are supposed to be resolved during static linking and which won't be visible to libbpf. With BTF information always present, static linker will check not just ELF symbol matches, but entire BTF type signature match as well. That logic is stricter that BPF CO-RE checks. It probably should be re-used by .ksym resolution logic in libbpf as well, but that's left for follow up patches. To make it unnecessary to rewrite ELF symbols and minimize BTF type rewriting/removal, ELF symbols that correspond to externs initially will be updated in place once they are resolved. Similarly for BTF type info, VAR/FUNC and var_secinfo's (sec_vars in struct bpf_linker) are staying stable, but types they point to might get replaced when extern is resolved. This might leave some left-over types (even though we try to minimize this for common cases of having extern funcs with not argument names vs concrete function with names properly specified). That can be addresses later with a generic BTF garbage collection. That's left for a follow up as well. Given BTF type appending phase is separate from ELF symbol appending/resolution, special struct glob_sym->underlying_btf_id variable is used to communicate resolution and rewrite decisions. 0 means underlying_btf_id needs to be appended (it's not yet in final linker->btf), <0 values are used for temporary storage of source BTF type ID (not yet rewritten), so -glob_sym->underlying_btf_id is BTF type id in obj-btf. But by the end of linker_append_btf() phase, that underlying_btf_id will be remapped and will always be > 0. This is the uglies part of the whole process, but keeps the other parts much simpler due to stability of sec_var and VAR/FUNC types, as well as ELF symbol, so please keep that in mind while reviewing. BTF-defined maps require some extra custom logic and is addressed separate in the next patch, so that to keep this one smaller and easier to review. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210423181348.1801389-12-andrii@kernel.org --- tools/lib/bpf/linker.c | 849 +++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 790 insertions(+), 59 deletions(-) (limited to 'tools/lib') diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c index 5505c85e8b7b..23f49945dc7a 100644 --- a/tools/lib/bpf/linker.c +++ b/tools/lib/bpf/linker.c @@ -22,6 +22,8 @@ #include "libbpf_internal.h" #include "strset.h" +#define BTF_EXTERN_SEC ".extern" + struct src_sec { const char *sec_name; /* positional (not necessarily ELF) index in an array of sections */ @@ -74,11 +76,36 @@ struct btf_ext_sec_data { void *recs; }; +struct glob_sym { + /* ELF symbol index */ + int sym_idx; + /* associated section id for .ksyms, .kconfig, etc, but not .extern */ + int sec_id; + /* extern name offset in STRTAB */ + int name_off; + /* optional associated BTF type ID */ + int btf_id; + /* BTF type ID to which VAR/FUNC type is pointing to; used for + * rewriting types when extern VAR/FUNC is resolved to a concrete + * definition + */ + int underlying_btf_id; + /* sec_var index in the corresponding dst_sec, if exists */ + int var_idx; + + /* extern or resolved/global symbol */ + bool is_extern; + /* weak or strong symbol, never goes back from strong to weak */ + bool is_weak; +}; + struct dst_sec { char *sec_name; /* positional (not necessarily ELF) index in an array of sections */ int id; + bool ephemeral; + /* ELF info */ size_t sec_idx; Elf_Scn *scn; @@ -120,6 +147,10 @@ struct bpf_linker { struct btf *btf; struct btf_ext *btf_ext; + + /* global (including extern) ELF symbols */ + int glob_sym_cnt; + struct glob_sym *glob_syms; }; #define pr_warn_elf(fmt, ...) \ @@ -136,6 +167,8 @@ static int linker_sanity_check_btf_ext(struct src_obj *obj); static int linker_fixup_btf(struct src_obj *obj); static int linker_append_sec_data(struct bpf_linker *linker, struct src_obj *obj); static int linker_append_elf_syms(struct bpf_linker *linker, struct src_obj *obj); +static int linker_append_elf_sym(struct bpf_linker *linker, struct src_obj *obj, + Elf64_Sym *sym, const char *sym_name, int src_sym_idx); static int linker_append_elf_relos(struct bpf_linker *linker, struct src_obj *obj); static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj); static int linker_append_btf_ext(struct bpf_linker *linker, struct src_obj *obj); @@ -947,6 +980,7 @@ static int init_sec(struct bpf_linker *linker, struct dst_sec *dst_sec, struct s dst_sec->sec_sz = 0; dst_sec->sec_idx = 0; + dst_sec->ephemeral = src_sec->ephemeral; /* ephemeral sections are just thin section shells lacking most parts */ if (src_sec->ephemeral) @@ -1010,6 +1044,9 @@ static struct dst_sec *find_dst_sec_by_name(struct bpf_linker *linker, const cha static bool secs_match(struct dst_sec *dst, struct src_sec *src) { + if (dst->ephemeral || src->ephemeral) + return true; + if (dst->shdr->sh_type != src->shdr->sh_type) { pr_warn("sec %s types mismatch\n", dst->sec_name); return false; @@ -1035,13 +1072,33 @@ static bool sec_content_is_same(struct dst_sec *dst_sec, struct src_sec *src_sec return true; } -static int extend_sec(struct dst_sec *dst, struct src_sec *src) +static int extend_sec(struct bpf_linker *linker, struct dst_sec *dst, struct src_sec *src) { void *tmp; - size_t dst_align = dst->shdr->sh_addralign; - size_t src_align = src->shdr->sh_addralign; + size_t dst_align, src_align; size_t dst_align_sz, dst_final_sz; + int err; + + /* Ephemeral source section doesn't contribute anything to ELF + * section data. + */ + if (src->ephemeral) + return 0; + + /* Some sections (like .maps) can contain both externs (and thus be + * ephemeral) and non-externs (map definitions). So it's possible that + * it has to be "upgraded" from ephemeral to non-ephemeral when the + * first non-ephemeral entity appears. In such case, we add ELF + * section, data, etc. + */ + if (dst->ephemeral) { + err = init_sec(linker, dst, src); + if (err) + return err; + } + dst_align = dst->shdr->sh_addralign; + src_align = src->shdr->sh_addralign; if (dst_align == 0) dst_align = 1; if (dst_align < src_align) @@ -1137,10 +1194,7 @@ static int linker_append_sec_data(struct bpf_linker *linker, struct src_obj *obj /* record mapped section index */ src_sec->dst_id = dst_sec->id; - if (src_sec->ephemeral) - continue; - - err = extend_sec(dst_sec, src_sec); + err = extend_sec(linker, dst_sec, src_sec); if (err) return err; } @@ -1151,21 +1205,16 @@ static int linker_append_sec_data(struct bpf_linker *linker, struct src_obj *obj static int linker_append_elf_syms(struct bpf_linker *linker, struct src_obj *obj) { struct src_sec *symtab = &obj->secs[obj->symtab_sec_idx]; - Elf64_Sym *sym = symtab->data->d_buf, *dst_sym; - int i, n = symtab->shdr->sh_size / symtab->shdr->sh_entsize; + Elf64_Sym *sym = symtab->data->d_buf; + int i, n = symtab->shdr->sh_size / symtab->shdr->sh_entsize, err; int str_sec_idx = symtab->shdr->sh_link; + const char *sym_name; obj->sym_map = calloc(n + 1, sizeof(*obj->sym_map)); if (!obj->sym_map) return -ENOMEM; for (i = 0; i < n; i++, sym++) { - struct src_sec *src_sec = NULL; - struct dst_sec *dst_sec = NULL; - const char *sym_name; - size_t dst_sym_idx; - int name_off; - /* We already validated all-zero symbol #0 and we already * appended it preventively to the final SYMTAB, so skip it. */ @@ -1178,41 +1227,624 @@ static int linker_append_elf_syms(struct bpf_linker *linker, struct src_obj *obj return -EINVAL; } - if (sym->st_shndx && sym->st_shndx < SHN_LORESERVE) { - src_sec = &obj->secs[sym->st_shndx]; - if (src_sec->skipped) + err = linker_append_elf_sym(linker, obj, sym, sym_name, i); + if (err) + return err; + } + + return 0; +} + +static Elf64_Sym *get_sym_by_idx(struct bpf_linker *linker, size_t sym_idx) +{ + struct dst_sec *symtab = &linker->secs[linker->symtab_sec_idx]; + Elf64_Sym *syms = symtab->raw_data; + + return &syms[sym_idx]; +} + +static struct glob_sym *find_glob_sym(struct bpf_linker *linker, const char *sym_name) +{ + struct glob_sym *glob_sym; + const char *name; + int i; + + for (i = 0; i < linker->glob_sym_cnt; i++) { + glob_sym = &linker->glob_syms[i]; + name = strset__data(linker->strtab_strs) + glob_sym->name_off; + + if (strcmp(name, sym_name) == 0) + return glob_sym; + } + + return NULL; +} + +static struct glob_sym *add_glob_sym(struct bpf_linker *linker) +{ + struct glob_sym *syms, *sym; + + syms = libbpf_reallocarray(linker->glob_syms, linker->glob_sym_cnt + 1, + sizeof(*linker->glob_syms)); + if (!syms) + return NULL; + + sym = &syms[linker->glob_sym_cnt]; + memset(sym, 0, sizeof(*sym)); + sym->var_idx = -1; + + linker->glob_syms = syms; + linker->glob_sym_cnt++; + + return sym; +} + +static bool glob_sym_btf_matches(const char *sym_name, bool exact, + const struct btf *btf1, __u32 id1, + const struct btf *btf2, __u32 id2) +{ + const struct btf_type *t1, *t2; + bool is_static1, is_static2; + const char *n1, *n2; + int i, n; + +recur: + n1 = n2 = NULL; + t1 = skip_mods_and_typedefs(btf1, id1, &id1); + t2 = skip_mods_and_typedefs(btf2, id2, &id2); + + /* check if only one side is FWD, otherwise handle with common logic */ + if (!exact && btf_is_fwd(t1) != btf_is_fwd(t2)) { + n1 = btf__str_by_offset(btf1, t1->name_off); + n2 = btf__str_by_offset(btf2, t2->name_off); + if (strcmp(n1, n2) != 0) { + pr_warn("global '%s': incompatible forward declaration names '%s' and '%s'\n", + sym_name, n1, n2); + return false; + } + /* validate if FWD kind matches concrete kind */ + if (btf_is_fwd(t1)) { + if (btf_kflag(t1) && btf_is_union(t2)) + return true; + if (!btf_kflag(t1) && btf_is_struct(t2)) + return true; + pr_warn("global '%s': incompatible %s forward declaration and concrete kind %s\n", + sym_name, btf_kflag(t1) ? "union" : "struct", btf_kind_str(t2)); + } else { + if (btf_kflag(t2) && btf_is_union(t1)) + return true; + if (!btf_kflag(t2) && btf_is_struct(t1)) + return true; + pr_warn("global '%s': incompatible %s forward declaration and concrete kind %s\n", + sym_name, btf_kflag(t2) ? "union" : "struct", btf_kind_str(t1)); + } + return false; + } + + if (btf_kind(t1) != btf_kind(t2)) { + pr_warn("global '%s': incompatible BTF kinds %s and %s\n", + sym_name, btf_kind_str(t1), btf_kind_str(t2)); + return false; + } + + switch (btf_kind(t1)) { + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + case BTF_KIND_ENUM: + case BTF_KIND_FWD: + case BTF_KIND_FUNC: + case BTF_KIND_VAR: + n1 = btf__str_by_offset(btf1, t1->name_off); + n2 = btf__str_by_offset(btf2, t2->name_off); + if (strcmp(n1, n2) != 0) { + pr_warn("global '%s': incompatible %s names '%s' and '%s'\n", + sym_name, btf_kind_str(t1), n1, n2); + return false; + } + break; + default: + break; + } + + switch (btf_kind(t1)) { + case BTF_KIND_UNKN: /* void */ + case BTF_KIND_FWD: + return true; + case BTF_KIND_INT: + case BTF_KIND_FLOAT: + case BTF_KIND_ENUM: + /* ignore encoding for int and enum values for enum */ + if (t1->size != t2->size) { + pr_warn("global '%s': incompatible %s '%s' size %u and %u\n", + sym_name, btf_kind_str(t1), n1, t1->size, t2->size); + return false; + } + return true; + case BTF_KIND_PTR: + /* just validate overall shape of the referenced type, so no + * contents comparison for struct/union, and allowd fwd vs + * struct/union + */ + exact = false; + id1 = t1->type; + id2 = t2->type; + goto recur; + case BTF_KIND_ARRAY: + /* ignore index type and array size */ + id1 = btf_array(t1)->type; + id2 = btf_array(t2)->type; + goto recur; + case BTF_KIND_FUNC: + /* extern and global linkages are compatible */ + is_static1 = btf_func_linkage(t1) == BTF_FUNC_STATIC; + is_static2 = btf_func_linkage(t2) == BTF_FUNC_STATIC; + if (is_static1 != is_static2) { + pr_warn("global '%s': incompatible func '%s' linkage\n", sym_name, n1); + return false; + } + + id1 = t1->type; + id2 = t2->type; + goto recur; + case BTF_KIND_VAR: + /* extern and global linkages are compatible */ + is_static1 = btf_var(t1)->linkage == BTF_VAR_STATIC; + is_static2 = btf_var(t2)->linkage == BTF_VAR_STATIC; + if (is_static1 != is_static2) { + pr_warn("global '%s': incompatible var '%s' linkage\n", sym_name, n1); + return false; + } + + id1 = t1->type; + id2 = t2->type; + goto recur; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + const struct btf_member *m1, *m2; + + if (!exact) + return true; + + if (btf_vlen(t1) != btf_vlen(t2)) { + pr_warn("global '%s': incompatible number of %s fields %u and %u\n", + sym_name, btf_kind_str(t1), btf_vlen(t1), btf_vlen(t2)); + return false; + } + + n = btf_vlen(t1); + m1 = btf_members(t1); + m2 = btf_members(t2); + for (i = 0; i < n; i++, m1++, m2++) { + n1 = btf__str_by_offset(btf1, m1->name_off); + n2 = btf__str_by_offset(btf2, m2->name_off); + if (strcmp(n1, n2) != 0) { + pr_warn("global '%s': incompatible field #%d names '%s' and '%s'\n", + sym_name, i, n1, n2); + return false; + } + if (m1->offset != m2->offset) { + pr_warn("global '%s': incompatible field #%d ('%s') offsets\n", + sym_name, i, n1); + return false; + } + if (!glob_sym_btf_matches(sym_name, exact, btf1, m1->type, btf2, m2->type)) + return false; + } + + return true; + } + case BTF_KIND_FUNC_PROTO: { + const struct btf_param *m1, *m2; + + if (btf_vlen(t1) != btf_vlen(t2)) { + pr_warn("global '%s': incompatible number of %s params %u and %u\n", + sym_name, btf_kind_str(t1), btf_vlen(t1), btf_vlen(t2)); + return false; + } + + n = btf_vlen(t1); + m1 = btf_params(t1); + m2 = btf_params(t2); + for (i = 0; i < n; i++, m1++, m2++) { + /* ignore func arg names */ + if (!glob_sym_btf_matches(sym_name, exact, btf1, m1->type, btf2, m2->type)) + return false; + } + + /* now check return type as well */ + id1 = t1->type; + id2 = t2->type; + goto recur; + } + + /* skip_mods_and_typedefs() make this impossible */ + case BTF_KIND_TYPEDEF: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + /* DATASECs are never compared with each other */ + case BTF_KIND_DATASEC: + default: + pr_warn("global '%s': unsupported BTF kind %s\n", + sym_name, btf_kind_str(t1)); + return false; + } +} + +static bool glob_syms_match(const char *sym_name, + struct bpf_linker *linker, struct glob_sym *glob_sym, + struct src_obj *obj, Elf64_Sym *sym, size_t sym_idx, int btf_id) +{ + const struct btf_type *src_t; + + /* if we are dealing with externs, BTF types describing both global + * and extern VARs/FUNCs should be completely present in all files + */ + if (!glob_sym->btf_id || !btf_id) { + pr_warn("BTF info is missing for global symbol '%s'\n", sym_name); + return false; + } + + src_t = btf__type_by_id(obj->btf, btf_id); + if (!btf_is_var(src_t) && !btf_is_func(src_t)) { + pr_warn("only extern variables and functions are supported, but got '%s' for '%s'\n", + btf_kind_str(src_t), sym_name); + return false; + } + + if (!glob_sym_btf_matches(sym_name, true /*exact*/, + linker->btf, glob_sym->btf_id, obj->btf, btf_id)) + return false; + + return true; +} + +static bool btf_is_non_static(const struct btf_type *t) +{ + return (btf_is_var(t) && btf_var(t)->linkage != BTF_VAR_STATIC) + || (btf_is_func(t) && btf_func_linkage(t) != BTF_FUNC_STATIC); +} + +static int find_glob_sym_btf(struct src_obj *obj, Elf64_Sym *sym, const char *sym_name, + int *out_btf_sec_id, int *out_btf_id) +{ + int i, j, n = btf__get_nr_types(obj->btf), m, btf_id = 0; + const struct btf_type *t; + const struct btf_var_secinfo *vi; + const char *name; + + for (i = 1; i <= n; i++) { + t = btf__type_by_id(obj->btf, i); + + /* some global and extern FUNCs and VARs might not be associated with any + * DATASEC, so try to detect them in the same pass + */ + if (btf_is_non_static(t)) { + name = btf__str_by_offset(obj->btf, t->name_off); + if (strcmp(name, sym_name) != 0) continue; - dst_sec = &linker->secs[src_sec->dst_id]; - /* allow only one STT_SECTION symbol per section */ - if (ELF64_ST_TYPE(sym->st_info) == STT_SECTION && dst_sec->sec_sym_idx) { - obj->sym_map[i] = dst_sec->sec_sym_idx; + /* remember and still try to find DATASEC */ + btf_id = i; + continue; + } + + if (!btf_is_datasec(t)) + continue; + + vi = btf_var_secinfos(t); + for (j = 0, m = btf_vlen(t); j < m; j++, vi++) { + t = btf__type_by_id(obj->btf, vi->type); + name = btf__str_by_offset(obj->btf, t->name_off); + + if (strcmp(name, sym_name) != 0) + continue; + if (btf_is_var(t) && btf_var(t)->linkage == BTF_VAR_STATIC) + continue; + if (btf_is_func(t) && btf_func_linkage(t) == BTF_FUNC_STATIC) continue; + + if (btf_id && btf_id != vi->type) { + pr_warn("global/extern '%s' BTF is ambiguous: both types #%d and #%u match\n", + sym_name, btf_id, vi->type); + return -EINVAL; } + + *out_btf_sec_id = i; + *out_btf_id = vi->type; + + return 0; } + } - name_off = strset__add_str(linker->strtab_strs, sym_name); - if (name_off < 0) - return name_off; + /* free-floating extern or global FUNC */ + if (btf_id) { + *out_btf_sec_id = 0; + *out_btf_id = btf_id; + return 0; + } - dst_sym = add_new_sym(linker, &dst_sym_idx); - if (!dst_sym) - return -ENOMEM; + pr_warn("failed to find BTF info for global/extern symbol '%s'\n", sym_name); + return -ENOENT; +} - dst_sym->st_name = name_off; - dst_sym->st_info = sym->st_info; - dst_sym->st_other = sym->st_other; - dst_sym->st_shndx = src_sec ? dst_sec->sec_idx : sym->st_shndx; - dst_sym->st_value = (src_sec ? src_sec->dst_off : 0) + sym->st_value; - dst_sym->st_size = sym->st_size; +static struct src_sec *find_src_sec_by_name(struct src_obj *obj, const char *sec_name) +{ + struct src_sec *sec; + int i; - obj->sym_map[i] = dst_sym_idx; + for (i = 1; i < obj->sec_cnt; i++) { + sec = &obj->secs[i]; - if (ELF64_ST_TYPE(sym->st_info) == STT_SECTION && dst_sym) { - dst_sec->sec_sym_idx = dst_sym_idx; - dst_sym->st_value = 0; + if (strcmp(sec->sec_name, sec_name) == 0) + return sec; + } + + return NULL; +} + +static int complete_extern_btf_info(struct btf *dst_btf, int dst_id, + struct btf *src_btf, int src_id) +{ + struct btf_type *dst_t = btf_type_by_id(dst_btf, dst_id); + struct btf_type *src_t = btf_type_by_id(src_btf, src_id); + struct btf_param *src_p, *dst_p; + const char *s; + int i, n, off; + + /* We already made sure that source and destination types (FUNC or + * VAR) match in terms of types and argument names. + */ + if (btf_is_var(dst_t)) { + btf_var(dst_t)->linkage = BTF_VAR_GLOBAL_ALLOCATED; + return 0; + } + + dst_t->info = btf_type_info(BTF_KIND_FUNC, BTF_FUNC_GLOBAL, 0); + + /* now onto FUNC_PROTO types */ + src_t = btf_type_by_id(src_btf, src_t->type); + dst_t = btf_type_by_id(dst_btf, dst_t->type); + + /* Fill in all the argument names, which for extern FUNCs are missing. + * We'll end up with two copies of FUNCs/VARs for externs, but that + * will be taken care of by BTF dedup at the very end. + * It might be that BTF types for extern in one file has less/more BTF + * information (e.g., FWD instead of full STRUCT/UNION information), + * but that should be (in most cases, subject to BTF dedup rules) + * handled and resolved by BTF dedup algorithm as well, so we won't + * worry about it. Our only job is to make sure that argument names + * are populated on both sides, otherwise BTF dedup will pedantically + * consider them different. + */ + src_p = btf_params(src_t); + dst_p = btf_params(dst_t); + for (i = 0, n = btf_vlen(dst_t); i < n; i++, src_p++, dst_p++) { + if (!src_p->name_off) + continue; + + /* src_btf has more complete info, so add name to dst_btf */ + s = btf__str_by_offset(src_btf, src_p->name_off); + off = btf__add_str(dst_btf, s); + if (off < 0) + return off; + dst_p->name_off = off; + } + return 0; +} + +static void sym_update_bind(Elf64_Sym *sym, int sym_bind) +{ + sym->st_info = ELF64_ST_INFO(sym_bind, ELF64_ST_TYPE(sym->st_info)); +} + +static void sym_update_type(Elf64_Sym *sym, int sym_type) +{ + sym->st_info = ELF64_ST_INFO(ELF64_ST_BIND(sym->st_info), sym_type); +} + +static void sym_update_visibility(Elf64_Sym *sym, int sym_vis) +{ + /* libelf doesn't provide setters for ST_VISIBILITY, + * but it is stored in the lower 2 bits of st_other + */ + sym->st_other &= 0x03; + sym->st_other |= sym_vis; +} + +static int linker_append_elf_sym(struct bpf_linker *linker, struct src_obj *obj, + Elf64_Sym *sym, const char *sym_name, int src_sym_idx) +{ + struct src_sec *src_sec = NULL; + struct dst_sec *dst_sec = NULL; + struct glob_sym *glob_sym = NULL; + int name_off, sym_type, sym_bind, sym_vis, err; + int btf_sec_id = 0, btf_id = 0; + size_t dst_sym_idx; + Elf64_Sym *dst_sym; + bool sym_is_extern; + + sym_type = ELF64_ST_TYPE(sym->st_info); + sym_bind = ELF64_ST_BIND(sym->st_info); + sym_vis = ELF64_ST_VISIBILITY(sym->st_other); + sym_is_extern = sym->st_shndx == SHN_UNDEF; + + if (sym_is_extern) { + if (!obj->btf) { + pr_warn("externs without BTF info are not supported\n"); + return -ENOTSUP; + } + } else if (sym->st_shndx < SHN_LORESERVE) { + src_sec = &obj->secs[sym->st_shndx]; + if (src_sec->skipped) + return 0; + dst_sec = &linker->secs[src_sec->dst_id]; + + /* allow only one STT_SECTION symbol per section */ + if (sym_type == STT_SECTION && dst_sec->sec_sym_idx) { + obj->sym_map[src_sym_idx] = dst_sec->sec_sym_idx; + return 0; + } + } + + if (sym_bind == STB_LOCAL) + goto add_sym; + + /* find matching BTF info */ + err = find_glob_sym_btf(obj, sym, sym_name, &btf_sec_id, &btf_id); + if (err) + return err; + + if (sym_is_extern && btf_sec_id) { + const char *sec_name = NULL; + const struct btf_type *t; + + t = btf__type_by_id(obj->btf, btf_sec_id); + sec_name = btf__str_by_offset(obj->btf, t->name_off); + + /* Clang puts unannotated extern vars into + * '.extern' BTF DATASEC. Treat them the same + * as unannotated extern funcs (which are + * currently not put into any DATASECs). + * Those don't have associated src_sec/dst_sec. + */ + if (strcmp(sec_name, BTF_EXTERN_SEC) != 0) { + src_sec = find_src_sec_by_name(obj, sec_name); + if (!src_sec) { + pr_warn("failed to find matching ELF sec '%s'\n", sec_name); + return -ENOENT; + } + dst_sec = &linker->secs[src_sec->dst_id]; + } + } + + glob_sym = find_glob_sym(linker, sym_name); + if (glob_sym) { + /* Preventively resolve to existing symbol. This is + * needed for further relocation symbol remapping in + * the next step of linking. + */ + obj->sym_map[src_sym_idx] = glob_sym->sym_idx; + + /* If both symbols are non-externs, at least one of + * them has to be STB_WEAK, otherwise they are in + * a conflict with each other. + */ + if (!sym_is_extern && !glob_sym->is_extern + && !glob_sym->is_weak && sym_bind != STB_WEAK) { + pr_warn("conflicting non-weak symbol #%d (%s) definition in '%s'\n", + src_sym_idx, sym_name, obj->filename); + return -EINVAL; + } + + if (!glob_syms_match(sym_name, linker, glob_sym, obj, sym, src_sym_idx, btf_id)) + return -EINVAL; + + dst_sym = get_sym_by_idx(linker, glob_sym->sym_idx); + + /* If new symbol is strong, then force dst_sym to be strong as + * well; this way a mix of weak and non-weak extern + * definitions will end up being strong. + */ + if (sym_bind == STB_GLOBAL) { + /* We still need to preserve type (NOTYPE or + * OBJECT/FUNC, depending on whether the symbol is + * extern or not) + */ + sym_update_bind(dst_sym, STB_GLOBAL); + glob_sym->is_weak = false; } + /* Non-default visibility is "contaminating", with stricter + * visibility overwriting more permissive ones, even if more + * permissive visibility comes from just an extern definition. + * Currently only STV_DEFAULT and STV_HIDDEN are allowed and + * ensured by ELF symbol sanity checks above. + */ + if (sym_vis > ELF64_ST_VISIBILITY(dst_sym->st_other)) + sym_update_visibility(dst_sym, sym_vis); + + /* If the new symbol is extern, then regardless if + * existing symbol is extern or resolved global, just + * keep the existing one untouched. + */ + if (sym_is_extern) + return 0; + + /* If existing symbol is a strong resolved symbol, bail out, + * because we lost resolution battle have nothing to + * contribute. We already checked abover that there is no + * strong-strong conflict. We also already tightened binding + * and visibility, so nothing else to contribute at that point. + */ + if (!glob_sym->is_extern && sym_bind == STB_WEAK) + return 0; + + /* At this point, new symbol is strong non-extern, + * so overwrite glob_sym with new symbol information. + * Preserve binding and visibility. + */ + sym_update_type(dst_sym, sym_type); + dst_sym->st_shndx = dst_sec->sec_idx; + dst_sym->st_value = src_sec->dst_off + sym->st_value; + dst_sym->st_size = sym->st_size; + + /* see comment below about dst_sec->id vs dst_sec->sec_idx */ + glob_sym->sec_id = dst_sec->id; + glob_sym->is_extern = false; + + if (complete_extern_btf_info(linker->btf, glob_sym->btf_id, + obj->btf, btf_id)) + return -EINVAL; + + /* request updating VAR's/FUNC's underlying BTF type when appending BTF type */ + glob_sym->underlying_btf_id = 0; + + obj->sym_map[src_sym_idx] = glob_sym->sym_idx; + return 0; + } + +add_sym: + name_off = strset__add_str(linker->strtab_strs, sym_name); + if (name_off < 0) + return name_off; + + dst_sym = add_new_sym(linker, &dst_sym_idx); + if (!dst_sym) + return -ENOMEM; + + dst_sym->st_name = name_off; + dst_sym->st_info = sym->st_info; + dst_sym->st_other = sym->st_other; + dst_sym->st_shndx = dst_sec ? dst_sec->sec_idx : sym->st_shndx; + dst_sym->st_value = (src_sec ? src_sec->dst_off : 0) + sym->st_value; + dst_sym->st_size = sym->st_size; + + obj->sym_map[src_sym_idx] = dst_sym_idx; + + if (sym_type == STT_SECTION && dst_sym) { + dst_sec->sec_sym_idx = dst_sym_idx; + dst_sym->st_value = 0; + } + + if (sym_bind != STB_LOCAL) { + glob_sym = add_glob_sym(linker); + if (!glob_sym) + return -ENOMEM; + + glob_sym->sym_idx = dst_sym_idx; + /* we use dst_sec->id (and not dst_sec->sec_idx), because + * ephemeral sections (.kconfig, .ksyms, etc) don't have + * sec_idx (as they don't have corresponding ELF section), but + * still have id. .extern doesn't have even ephemeral section + * associated with it, so dst_sec->id == dst_sec->sec_idx == 0. + */ + glob_sym->sec_id = dst_sec ? dst_sec->id : 0; + glob_sym->name_off = name_off; + /* we will fill btf_id in during BTF merging step */ + glob_sym->btf_id = 0; + glob_sym->is_extern = sym_is_extern; + glob_sym->is_weak = sym_bind == STB_WEAK; } return 0; @@ -1262,7 +1894,7 @@ static int linker_append_elf_relos(struct bpf_linker *linker, struct src_obj *ob dst_sec->shdr->sh_info = dst_linked_sec->sec_idx; src_sec->dst_id = dst_sec->id; - err = extend_sec(dst_sec, src_sec); + err = extend_sec(linker, dst_sec, src_sec); if (err) return err; @@ -1315,21 +1947,6 @@ static int linker_append_elf_relos(struct bpf_linker *linker, struct src_obj *ob return 0; } -static struct src_sec *find_src_sec_by_name(struct src_obj *obj, const char *sec_name) -{ - struct src_sec *sec; - int i; - - for (i = 1; i < obj->sec_cnt; i++) { - sec = &obj->secs[i]; - - if (strcmp(sec->sec_name, sec_name) == 0) - return sec; - } - - return NULL; -} - static Elf64_Sym *find_sym_by_name(struct src_obj *obj, size_t sec_idx, int sym_type, const char *sym_name) { @@ -1384,12 +2001,32 @@ static int linker_fixup_btf(struct src_obj *obj) t->size = sec->shdr->sh_size; } else { /* BTF can have some sections that are not represented - * in ELF, e.g., .kconfig and .ksyms, which are used - * for special extern variables. Here we'll - * pre-create "section shells" for them to be able to - * keep track of extra per-section metadata later - * (e.g., BTF variables). + * in ELF, e.g., .kconfig, .ksyms, .extern, which are used + * for special extern variables. + * + * For all but one such special (ephemeral) + * sections, we pre-create "section shells" to be able + * to keep track of extra per-section metadata later + * (e.g., those BTF extern variables). + * + * .extern is even more special, though, because it + * contains extern variables that need to be resolved + * by static linker, not libbpf and kernel. When such + * externs are resolved, we are going to remove them + * from .extern BTF section and might end up not + * needing it at all. Each resolved extern should have + * matching non-extern VAR/FUNC in other sections. + * + * We do support leaving some of the externs + * unresolved, though, to support cases of building + * libraries, which will later be linked against final + * BPF applications. So if at finalization we still + * see unresolved externs, we'll create .extern + * section on our own. */ + if (strcmp(sec_name, BTF_EXTERN_SEC) == 0) + continue; + sec = add_src_sec(obj, sec_name); if (!sec) return -ENOMEM; @@ -1446,6 +2083,7 @@ static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj) { const struct btf_type *t; int i, j, n, start_id, id; + const char *name; if (!obj->btf) return 0; @@ -1458,12 +2096,44 @@ static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj) return -ENOMEM; for (i = 1; i <= n; i++) { + struct glob_sym *glob_sym = NULL; + t = btf__type_by_id(obj->btf, i); /* DATASECs are handled specially below */ if (btf_kind(t) == BTF_KIND_DATASEC) continue; + if (btf_is_non_static(t)) { + /* there should be glob_sym already */ + name = btf__str_by_offset(obj->btf, t->name_off); + glob_sym = find_glob_sym(linker, name); + + /* VARs without corresponding glob_sym are those that + * belong to skipped/deduplicated sections (i.e., + * license and version), so just skip them + */ + if (!glob_sym) + continue; + + /* linker_append_elf_sym() might have requested + * updating underlying type ID, if extern was resolved + * to strong symbol or weak got upgraded to non-weak + */ + if (glob_sym->underlying_btf_id == 0) + glob_sym->underlying_btf_id = -t->type; + + /* globals from previous object files that match our + * VAR/FUNC already have a corresponding associated + * BTF type, so just make sure to use it + */ + if (glob_sym->btf_id) { + /* reuse existing BTF type for global var/func */ + obj->btf_type_map[i] = glob_sym->btf_id; + continue; + } + } + id = btf__add_type(linker->btf, obj->btf, t); if (id < 0) { pr_warn("failed to append BTF type #%d from file '%s'\n", i, obj->filename); @@ -1471,6 +2141,12 @@ static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj) } obj->btf_type_map[i] = id; + + /* record just appended BTF type for var/func */ + if (glob_sym) { + glob_sym->btf_id = id; + glob_sym->underlying_btf_id = -t->type; + } } /* remap all the types except DATASECs */ @@ -1482,6 +2158,22 @@ static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj) return -EINVAL; } + /* Rewrite VAR/FUNC underlying types (i.e., FUNC's FUNC_PROTO and VAR's + * actual type), if necessary + */ + for (i = 0; i < linker->glob_sym_cnt; i++) { + struct glob_sym *glob_sym = &linker->glob_syms[i]; + struct btf_type *glob_t; + + if (glob_sym->underlying_btf_id >= 0) + continue; + + glob_sym->underlying_btf_id = obj->btf_type_map[-glob_sym->underlying_btf_id]; + + glob_t = btf_type_by_id(linker->btf, glob_sym->btf_id); + glob_t->type = glob_sym->underlying_btf_id; + } + /* append DATASEC info */ for (i = 1; i < obj->sec_cnt; i++) { struct src_sec *src_sec; @@ -1509,6 +2201,42 @@ static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj) n = btf_vlen(t); for (j = 0; j < n; j++, src_var++) { void *sec_vars = dst_sec->sec_vars; + int new_id = obj->btf_type_map[src_var->type]; + struct glob_sym *glob_sym = NULL; + + t = btf_type_by_id(linker->btf, new_id); + if (btf_is_non_static(t)) { + name = btf__str_by_offset(linker->btf, t->name_off); + glob_sym = find_glob_sym(linker, name); + if (glob_sym->sec_id != dst_sec->id) { + pr_warn("global '%s': section mismatch %d vs %d\n", + name, glob_sym->sec_id, dst_sec->id); + return -EINVAL; + } + } + + /* If there is already a member (VAR or FUNC) mapped + * to the same type, don't add a duplicate entry. + * This will happen when multiple object files define + * the same extern VARs/FUNCs. + */ + if (glob_sym && glob_sym->var_idx >= 0) { + __s64 sz; + + dst_var = &dst_sec->sec_vars[glob_sym->var_idx]; + /* Because underlying BTF type might have + * changed, so might its size have changed, so + * re-calculate and update it in sec_var. + */ + sz = btf__resolve_size(linker->btf, glob_sym->underlying_btf_id); + if (sz < 0) { + pr_warn("global '%s': failed to resolve size of underlying type: %d\n", + name, (int)sz); + return -EINVAL; + } + dst_var->size = sz; + continue; + } sec_vars = libbpf_reallocarray(sec_vars, dst_sec->sec_var_cnt + 1, @@ -1523,6 +2251,9 @@ static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj) dst_var->type = obj->btf_type_map[src_var->type]; dst_var->size = src_var->size; dst_var->offset = src_sec->dst_off + src_var->offset; + + if (glob_sym) + glob_sym->var_idx = dst_sec->sec_var_cnt - 1; } } -- cgit From 0a342457b3bd36e6f9b558da3ff520dee35c5363 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 23 Apr 2021 11:13:42 -0700 Subject: libbpf: Support extern resolution for BTF-defined maps in .maps section Add extra logic to handle map externs (only BTF-defined maps are supported for linking). Re-use the map parsing logic used during bpf_object__open(). Map externs are currently restricted to always match complete map definition. So all the specified attributes will be compared (down to pining, map_flags, numa_node, etc). In the future this restriction might be relaxed with no backwards compatibility issues. If any attribute is mismatched between extern and actual map definition, linker will report an error, pointing out which one mismatches. The original intent was to allow for extern to specify attributes that matters (to user) to enforce. E.g., if you specify just key information and omit value, then any value fits. Similarly, it should have been possible to enforce map_flags, pinning, and any other possible map attribute. Unfortunately, that means that multiple externs can be only partially overlapping with each other, which means linker would need to combine their type definitions to end up with the most restrictive and fullest map definition. This requires an extra amount of BTF manipulation which at this time was deemed unnecessary and would require further extending generic BTF writer APIs. So that is left for future follow ups, if there will be demand for that. But the idea seems intresting and useful, so I want to document it here. Weak definitions are also supported, but are pretty strict as well, just like externs: all weak map definitions have to match exactly. In the follow up patches this most probably will be relaxed, with __weak map definitions being able to differ between each other (with non-weak definition always winning, of course). Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210423181348.1801389-13-andrii@kernel.org --- tools/lib/bpf/linker.c | 132 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 132 insertions(+) (limited to 'tools/lib') diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c index 23f49945dc7a..9de084b1c699 100644 --- a/tools/lib/bpf/linker.c +++ b/tools/lib/bpf/linker.c @@ -1471,6 +1471,134 @@ recur: } } +static bool map_defs_match(const char *sym_name, + const struct btf *main_btf, + const struct btf_map_def *main_def, + const struct btf_map_def *main_inner_def, + const struct btf *extra_btf, + const struct btf_map_def *extra_def, + const struct btf_map_def *extra_inner_def) +{ + const char *reason; + + if (main_def->map_type != extra_def->map_type) { + reason = "type"; + goto mismatch; + } + + /* check key type/size match */ + if (main_def->key_size != extra_def->key_size) { + reason = "key_size"; + goto mismatch; + } + if (!!main_def->key_type_id != !!extra_def->key_type_id) { + reason = "key type"; + goto mismatch; + } + if ((main_def->parts & MAP_DEF_KEY_TYPE) + && !glob_sym_btf_matches(sym_name, true /*exact*/, + main_btf, main_def->key_type_id, + extra_btf, extra_def->key_type_id)) { + reason = "key type"; + goto mismatch; + } + + /* validate value type/size match */ + if (main_def->value_size != extra_def->value_size) { + reason = "value_size"; + goto mismatch; + } + if (!!main_def->value_type_id != !!extra_def->value_type_id) { + reason = "value type"; + goto mismatch; + } + if ((main_def->parts & MAP_DEF_VALUE_TYPE) + && !glob_sym_btf_matches(sym_name, true /*exact*/, + main_btf, main_def->value_type_id, + extra_btf, extra_def->value_type_id)) { + reason = "key type"; + goto mismatch; + } + + if (main_def->max_entries != extra_def->max_entries) { + reason = "max_entries"; + goto mismatch; + } + if (main_def->map_flags != extra_def->map_flags) { + reason = "map_flags"; + goto mismatch; + } + if (main_def->numa_node != extra_def->numa_node) { + reason = "numa_node"; + goto mismatch; + } + if (main_def->pinning != extra_def->pinning) { + reason = "pinning"; + goto mismatch; + } + + if ((main_def->parts & MAP_DEF_INNER_MAP) != (extra_def->parts & MAP_DEF_INNER_MAP)) { + reason = "inner map"; + goto mismatch; + } + + if (main_def->parts & MAP_DEF_INNER_MAP) { + char inner_map_name[128]; + + snprintf(inner_map_name, sizeof(inner_map_name), "%s.inner", sym_name); + + return map_defs_match(inner_map_name, + main_btf, main_inner_def, NULL, + extra_btf, extra_inner_def, NULL); + } + + return true; + +mismatch: + pr_warn("global '%s': map %s mismatch\n", sym_name, reason); + return false; +} + +static bool glob_map_defs_match(const char *sym_name, + struct bpf_linker *linker, struct glob_sym *glob_sym, + struct src_obj *obj, Elf64_Sym *sym, int btf_id) +{ + struct btf_map_def dst_def = {}, dst_inner_def = {}; + struct btf_map_def src_def = {}, src_inner_def = {}; + const struct btf_type *t; + int err; + + t = btf__type_by_id(obj->btf, btf_id); + if (!btf_is_var(t)) { + pr_warn("global '%s': invalid map definition type [%d]\n", sym_name, btf_id); + return false; + } + t = skip_mods_and_typedefs(obj->btf, t->type, NULL); + + err = parse_btf_map_def(sym_name, obj->btf, t, true /*strict*/, &src_def, &src_inner_def); + if (err) { + pr_warn("global '%s': invalid map definition\n", sym_name); + return false; + } + + /* re-parse existing map definition */ + t = btf__type_by_id(linker->btf, glob_sym->btf_id); + t = skip_mods_and_typedefs(linker->btf, t->type, NULL); + err = parse_btf_map_def(sym_name, linker->btf, t, true /*strict*/, &dst_def, &dst_inner_def); + if (err) { + /* this should not happen, because we already validated it */ + pr_warn("global '%s': invalid dst map definition\n", sym_name); + return false; + } + + /* Currently extern map definition has to be complete and match + * concrete map definition exactly. This restriction might be lifted + * in the future. + */ + return map_defs_match(sym_name, linker->btf, &dst_def, &dst_inner_def, + obj->btf, &src_def, &src_inner_def); +} + static bool glob_syms_match(const char *sym_name, struct bpf_linker *linker, struct glob_sym *glob_sym, struct src_obj *obj, Elf64_Sym *sym, size_t sym_idx, int btf_id) @@ -1492,6 +1620,10 @@ static bool glob_syms_match(const char *sym_name, return false; } + /* deal with .maps definitions specially */ + if (glob_sym->sec_id && strcmp(linker->secs[glob_sym->sec_id].sec_name, MAPS_ELF_SEC) == 0) + return glob_map_defs_match(sym_name, linker, glob_sym, obj, sym, btf_id); + if (!glob_sym_btf_matches(sym_name, true /*exact*/, linker->btf, glob_sym->btf_id, obj->btf, btf_id)) return false; -- cgit