diff options
author | Daniel Borkmann <daniel@iogearbox.net> | 2019-04-09 23:20:13 +0200 |
---|---|---|
committer | Alexei Starovoitov <ast@kernel.org> | 2019-04-09 17:05:47 -0700 |
commit | d859900c4c56dc4f0f8894c92a01dad86917453e (patch) | |
tree | ccdad9b2ec417534f3518b4268020d3c30550e09 /tools/lib/bpf | |
parent | f8c7a4d4dc39991c1bc05847ea4378282708f935 (diff) |
bpf, libbpf: support global data/bss/rodata sections
This work adds BPF loader support for global data sections
to libbpf. This allows to write BPF programs in more natural
C-like way by being able to define global variables and const
data.
Back at LPC 2018 [0] we presented a first prototype which
implemented support for global data sections by extending BPF
syscall where union bpf_attr would get additional memory/size
pair for each section passed during prog load in order to later
add this base address into the ldimm64 instruction along with
the user provided offset when accessing a variable. Consensus
from LPC was that for proper upstream support, it would be
more desirable to use maps instead of bpf_attr extension as
this would allow for introspection of these sections as well
as potential live updates of their content. This work follows
this path by taking the following steps from loader side:
1) In bpf_object__elf_collect() step we pick up ".data",
".rodata", and ".bss" section information.
2) If present, in bpf_object__init_internal_map() we add
maps to the obj's map array that corresponds to each
of the present sections. Given section size and access
properties can differ, a single entry array map is
created with value size that is corresponding to the
ELF section size of .data, .bss or .rodata. These
internal maps are integrated into the normal map
handling of libbpf such that when user traverses all
obj maps, they can be differentiated from user-created
ones via bpf_map__is_internal(). In later steps when
we actually create these maps in the kernel via
bpf_object__create_maps(), then for .data and .rodata
sections their content is copied into the map through
bpf_map_update_elem(). For .bss this is not necessary
since array map is already zero-initialized by default.
Additionally, for .rodata the map is frozen as read-only
after setup, such that neither from program nor syscall
side writes would be possible.
3) In bpf_program__collect_reloc() step, we record the
corresponding map, insn index, and relocation type for
the global data.
4) And last but not least in the actual relocation step in
bpf_program__relocate(), we mark the ldimm64 instruction
with src_reg = BPF_PSEUDO_MAP_VALUE where in the first
imm field the map's file descriptor is stored as similarly
done as in BPF_PSEUDO_MAP_FD, and in the second imm field
(as ldimm64 is 2-insn wide) we store the access offset
into the section. Given these maps have only single element
ldimm64's off remains zero in both parts.
5) On kernel side, this special marked BPF_PSEUDO_MAP_VALUE
load will then store the actual target address in order
to have a 'map-lookup'-free access. That is, the actual
map value base address + offset. The destination register
in the verifier will then be marked as PTR_TO_MAP_VALUE,
containing the fixed offset as reg->off and backing BPF
map as reg->map_ptr. Meaning, it's treated as any other
normal map value from verification side, only with
efficient, direct value access instead of actual call to
map lookup helper as in the typical case.
Currently, only support for static global variables has been
added, and libbpf rejects non-static global variables from
loading. This can be lifted until we have proper semantics
for how BPF will treat multi-object BPF loads. From BTF side,
libbpf will set the value type id of the types corresponding
to the ".bss", ".data" and ".rodata" names which LLVM will
emit without the object name prefix. The key type will be
left as zero, thus making use of the key-less BTF option in
array maps.
Simple example dump of program using globals vars in each
section:
# bpftool prog
[...]
6784: sched_cls name load_static_dat tag a7e1291567277844 gpl
loaded_at 2019-03-11T15:39:34+0000 uid 0
xlated 1776B jited 993B memlock 4096B map_ids 2238,2237,2235,2236,2239,2240
# bpftool map show id 2237
2237: array name test_glo.bss flags 0x0
key 4B value 64B max_entries 1 memlock 4096B
# bpftool map show id 2235
2235: array name test_glo.data flags 0x0
key 4B value 64B max_entries 1 memlock 4096B
# bpftool map show id 2236
2236: array name test_glo.rodata flags 0x80
key 4B value 96B max_entries 1 memlock 4096B
# bpftool prog dump xlated id 6784
int load_static_data(struct __sk_buff * skb):
; int load_static_data(struct __sk_buff *skb)
0: (b7) r6 = 0
; test_reloc(number, 0, &num0);
1: (63) *(u32 *)(r10 -4) = r6
2: (bf) r2 = r10
; int load_static_data(struct __sk_buff *skb)
3: (07) r2 += -4
; test_reloc(number, 0, &num0);
4: (18) r1 = map[id:2238]
6: (18) r3 = map[id:2237][0]+0 <-- direct addr in .bss area
8: (b7) r4 = 0
9: (85) call array_map_update_elem#100464
10: (b7) r1 = 1
; test_reloc(number, 1, &num1);
[...]
; test_reloc(string, 2, str2);
120: (18) r8 = map[id:2237][0]+16 <-- same here at offset +16
122: (18) r1 = map[id:2239]
124: (18) r3 = map[id:2237][0]+16
126: (b7) r4 = 0
127: (85) call array_map_update_elem#100464
128: (b7) r1 = 120
; str1[5] = 'x';
129: (73) *(u8 *)(r9 +5) = r1
; test_reloc(string, 3, str1);
130: (b7) r1 = 3
131: (63) *(u32 *)(r10 -4) = r1
132: (b7) r9 = 3
133: (bf) r2 = r10
; int load_static_data(struct __sk_buff *skb)
134: (07) r2 += -4
; test_reloc(string, 3, str1);
135: (18) r1 = map[id:2239]
137: (18) r3 = map[id:2235][0]+16 <-- direct addr in .data area
139: (b7) r4 = 0
140: (85) call array_map_update_elem#100464
141: (b7) r1 = 111
; __builtin_memcpy(&str2[2], "hello", sizeof("hello"));
142: (73) *(u8 *)(r8 +6) = r1 <-- further access based on .bss data
143: (b7) r1 = 108
144: (73) *(u8 *)(r8 +5) = r1
[...]
For Cilium use-case in particular, this enables migrating configuration
constants from Cilium daemon's generated header defines into global
data sections such that expensive runtime recompilations with LLVM can
be avoided altogether. Instead, the ELF file becomes effectively a
"template", meaning, it is compiled only once (!) and the Cilium daemon
will then rewrite relevant configuration data from the ELF's .data or
.rodata sections directly instead of recompiling the program. The
updated ELF is then loaded into the kernel and atomically replaces
the existing program in the networking datapath. More info in [0].
Based upon recent fix in LLVM, commit c0db6b6bd444 ("[BPF] Don't fail
for static variables").
[0] LPC 2018, BPF track, "ELF relocation for static data in BPF",
http://vger.kernel.org/lpc-bpf2018.html#session-3
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Diffstat (limited to 'tools/lib/bpf')
-rw-r--r-- | tools/lib/bpf/Makefile | 2 | ||||
-rw-r--r-- | tools/lib/bpf/bpf.c | 10 | ||||
-rw-r--r-- | tools/lib/bpf/bpf.h | 1 | ||||
-rw-r--r-- | tools/lib/bpf/libbpf.c | 342 | ||||
-rw-r--r-- | tools/lib/bpf/libbpf.h | 1 | ||||
-rw-r--r-- | tools/lib/bpf/libbpf.map | 6 |
6 files changed, 314 insertions, 48 deletions
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 2a578bfc0bca..008344507700 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -3,7 +3,7 @@ BPF_VERSION = 0 BPF_PATCHLEVEL = 0 -BPF_EXTRAVERSION = 2 +BPF_EXTRAVERSION = 3 MAKEFLAGS += --no-print-directory diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index a1db869a6fda..c039094ad3aa 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -429,6 +429,16 @@ int bpf_map_get_next_key(int fd, const void *key, void *next_key) return sys_bpf(BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr)); } +int bpf_map_freeze(int fd) +{ + union bpf_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.map_fd = fd; + + return sys_bpf(BPF_MAP_FREEZE, &attr, sizeof(attr)); +} + int bpf_obj_pin(int fd, const char *pathname) { union bpf_attr attr; diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index e2c0df7b831f..c9d218d21453 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -117,6 +117,7 @@ LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value); LIBBPF_API int bpf_map_delete_elem(int fd, const void *key); LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key); +LIBBPF_API int bpf_map_freeze(int fd); LIBBPF_API int bpf_obj_pin(int fd, const char *pathname); LIBBPF_API int bpf_obj_get(const char *pathname); LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd, diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 6dba0f01673b..f7b245fbb960 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -7,6 +7,7 @@ * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com> * Copyright (C) 2015 Huawei Inc. * Copyright (C) 2017 Nicira, Inc. + * Copyright (C) 2019 Isovalent, Inc. */ #ifndef _GNU_SOURCE @@ -149,6 +150,7 @@ struct bpf_program { enum { RELO_LD64, RELO_CALL, + RELO_DATA, } type; int insn_idx; union { @@ -182,6 +184,19 @@ struct bpf_program { __u32 line_info_cnt; }; +enum libbpf_map_type { + LIBBPF_MAP_UNSPEC, + LIBBPF_MAP_DATA, + LIBBPF_MAP_BSS, + LIBBPF_MAP_RODATA, +}; + +static const char * const libbpf_type_to_btf_name[] = { + [LIBBPF_MAP_DATA] = ".data", + [LIBBPF_MAP_BSS] = ".bss", + [LIBBPF_MAP_RODATA] = ".rodata", +}; + struct bpf_map { int fd; char *name; @@ -193,11 +208,18 @@ struct bpf_map { __u32 btf_value_type_id; void *priv; bpf_map_clear_priv_t clear_priv; + enum libbpf_map_type libbpf_type; +}; + +struct bpf_secdata { + void *rodata; + void *data; }; static LIST_HEAD(bpf_objects_list); struct bpf_object { + char name[BPF_OBJ_NAME_LEN]; char license[64]; __u32 kern_version; @@ -205,6 +227,7 @@ struct bpf_object { size_t nr_programs; struct bpf_map *maps; size_t nr_maps; + struct bpf_secdata sections; bool loaded; bool has_pseudo_calls; @@ -220,6 +243,9 @@ struct bpf_object { Elf *elf; GElf_Ehdr ehdr; Elf_Data *symbols; + Elf_Data *data; + Elf_Data *rodata; + Elf_Data *bss; size_t strtabidx; struct { GElf_Shdr shdr; @@ -228,6 +254,9 @@ struct bpf_object { int nr_reloc; int maps_shndx; int text_shndx; + int data_shndx; + int rodata_shndx; + int bss_shndx; } efile; /* * All loaded bpf_object is linked in a list, which is @@ -449,6 +478,7 @@ static struct bpf_object *bpf_object__new(const char *path, size_t obj_buf_sz) { struct bpf_object *obj; + char *end; obj = calloc(1, sizeof(struct bpf_object) + strlen(path) + 1); if (!obj) { @@ -457,8 +487,14 @@ static struct bpf_object *bpf_object__new(const char *path, } strcpy(obj->path, path); - obj->efile.fd = -1; + /* Using basename() GNU version which doesn't modify arg. */ + strncpy(obj->name, basename((void *)path), + sizeof(obj->name) - 1); + end = strchr(obj->name, '.'); + if (end) + *end = 0; + obj->efile.fd = -1; /* * Caller of this function should also calls * bpf_object__elf_finish() after data collection to return @@ -468,6 +504,9 @@ static struct bpf_object *bpf_object__new(const char *path, obj->efile.obj_buf = obj_buf; obj->efile.obj_buf_sz = obj_buf_sz; obj->efile.maps_shndx = -1; + obj->efile.data_shndx = -1; + obj->efile.rodata_shndx = -1; + obj->efile.bss_shndx = -1; obj->loaded = false; @@ -486,6 +525,9 @@ static void bpf_object__elf_finish(struct bpf_object *obj) obj->efile.elf = NULL; } obj->efile.symbols = NULL; + obj->efile.data = NULL; + obj->efile.rodata = NULL; + obj->efile.bss = NULL; zfree(&obj->efile.reloc); obj->efile.nr_reloc = 0; @@ -627,27 +669,76 @@ static bool bpf_map_type__is_map_in_map(enum bpf_map_type type) return false; } +static bool bpf_object__has_maps(const struct bpf_object *obj) +{ + return obj->efile.maps_shndx >= 0 || + obj->efile.data_shndx >= 0 || + obj->efile.rodata_shndx >= 0 || + obj->efile.bss_shndx >= 0; +} + +static int +bpf_object__init_internal_map(struct bpf_object *obj, struct bpf_map *map, + enum libbpf_map_type type, Elf_Data *data, + void **data_buff) +{ + struct bpf_map_def *def = &map->def; + char map_name[BPF_OBJ_NAME_LEN]; + + map->libbpf_type = type; + map->offset = ~(typeof(map->offset))0; + snprintf(map_name, sizeof(map_name), "%.8s%.7s", obj->name, + libbpf_type_to_btf_name[type]); + map->name = strdup(map_name); + if (!map->name) { + pr_warning("failed to alloc map name\n"); + return -ENOMEM; + } + + def->type = BPF_MAP_TYPE_ARRAY; + def->key_size = sizeof(int); + def->value_size = data->d_size; + def->max_entries = 1; + def->map_flags = type == LIBBPF_MAP_RODATA ? + BPF_F_RDONLY_PROG : 0; + if (data_buff) { + *data_buff = malloc(data->d_size); + if (!*data_buff) { + zfree(&map->name); + pr_warning("failed to alloc map content buffer\n"); + return -ENOMEM; + } + memcpy(*data_buff, data->d_buf, data->d_size); + } + + pr_debug("map %ld is \"%s\"\n", map - obj->maps, map->name); + return 0; +} + static int bpf_object__init_maps(struct bpf_object *obj, int flags) { + int i, map_idx, map_def_sz, nr_syms, nr_maps = 0, nr_maps_glob = 0; bool strict = !(flags & MAPS_RELAX_COMPAT); - int i, map_idx, map_def_sz, nr_maps = 0; - Elf_Scn *scn; - Elf_Data *data = NULL; Elf_Data *symbols = obj->efile.symbols; + Elf_Data *data = NULL; + int ret = 0; - if (obj->efile.maps_shndx < 0) - return -EINVAL; if (!symbols) return -EINVAL; + nr_syms = symbols->d_size / sizeof(GElf_Sym); - scn = elf_getscn(obj->efile.elf, obj->efile.maps_shndx); - if (scn) - data = elf_getdata(scn, NULL); - if (!scn || !data) { - pr_warning("failed to get Elf_Data from map section %d\n", - obj->efile.maps_shndx); - return -EINVAL; + if (obj->efile.maps_shndx >= 0) { + Elf_Scn *scn = elf_getscn(obj->efile.elf, + obj->efile.maps_shndx); + + if (scn) + data = elf_getdata(scn, NULL); + if (!scn || !data) { + pr_warning("failed to get Elf_Data from map section %d\n", + obj->efile.maps_shndx); + return -EINVAL; + } } /* @@ -657,7 +748,13 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) * * TODO: Detect array of map and report error. */ - for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) { + if (obj->efile.data_shndx >= 0) + nr_maps_glob++; + if (obj->efile.rodata_shndx >= 0) + nr_maps_glob++; + if (obj->efile.bss_shndx >= 0) + nr_maps_glob++; + for (i = 0; data && i < nr_syms; i++) { GElf_Sym sym; if (!gelf_getsym(symbols, i, &sym)) @@ -670,19 +767,21 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) /* Alloc obj->maps and fill nr_maps. */ pr_debug("maps in %s: %d maps in %zd bytes\n", obj->path, nr_maps, data->d_size); - - if (!nr_maps) + if (!nr_maps && !nr_maps_glob) return 0; /* Assume equally sized map definitions */ - map_def_sz = data->d_size / nr_maps; - if (!data->d_size || (data->d_size % nr_maps) != 0) { - pr_warning("unable to determine map definition size " - "section %s, %d maps in %zd bytes\n", - obj->path, nr_maps, data->d_size); - return -EINVAL; + if (data) { + map_def_sz = data->d_size / nr_maps; + if (!data->d_size || (data->d_size % nr_maps) != 0) { + pr_warning("unable to determine map definition size " + "section %s, %d maps in %zd bytes\n", + obj->path, nr_maps, data->d_size); + return -EINVAL; + } } + nr_maps += nr_maps_glob; obj->maps = calloc(nr_maps, sizeof(obj->maps[0])); if (!obj->maps) { pr_warning("alloc maps for object failed\n"); @@ -703,7 +802,7 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) /* * Fill obj->maps using data in "maps" section. */ - for (i = 0, map_idx = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) { + for (i = 0, map_idx = 0; data && i < nr_syms; i++) { GElf_Sym sym; const char *map_name; struct bpf_map_def *def; @@ -716,6 +815,8 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) map_name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, sym.st_name); + + obj->maps[map_idx].libbpf_type = LIBBPF_MAP_UNSPEC; obj->maps[map_idx].offset = sym.st_value; if (sym.st_value + map_def_sz > data->d_size) { pr_warning("corrupted maps section in %s: last map \"%s\" too small\n", @@ -764,8 +865,27 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) map_idx++; } - qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), compare_bpf_map); - return 0; + /* + * Populate rest of obj->maps with libbpf internal maps. + */ + if (obj->efile.data_shndx >= 0) + ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++], + LIBBPF_MAP_DATA, + obj->efile.data, + &obj->sections.data); + if (!ret && obj->efile.rodata_shndx >= 0) + ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++], + LIBBPF_MAP_RODATA, + obj->efile.rodata, + &obj->sections.rodata); + if (!ret && obj->efile.bss_shndx >= 0) + ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++], + LIBBPF_MAP_BSS, + obj->efile.bss, NULL); + if (!ret) + qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), + compare_bpf_map); + return ret; } static bool section_have_execinstr(struct bpf_object *obj, int idx) @@ -885,6 +1005,14 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) pr_warning("failed to alloc program %s (%s): %s", name, obj->path, cp); } + } else if (strcmp(name, ".data") == 0) { + obj->efile.data = data; + obj->efile.data_shndx = idx; + } else if (strcmp(name, ".rodata") == 0) { + obj->efile.rodata = data; + obj->efile.rodata_shndx = idx; + } else { + pr_debug("skip section(%d) %s\n", idx, name); } } else if (sh.sh_type == SHT_REL) { void *reloc = obj->efile.reloc; @@ -912,6 +1040,9 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) obj->efile.reloc[n].shdr = sh; obj->efile.reloc[n].data = data; } + } else if (sh.sh_type == SHT_NOBITS && strcmp(name, ".bss") == 0) { + obj->efile.bss = data; + obj->efile.bss_shndx = idx; } else { pr_debug("skip section(%d) %s\n", idx, name); } @@ -938,7 +1069,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) } } } - if (obj->efile.maps_shndx >= 0) { + if (bpf_object__has_maps(obj)) { err = bpf_object__init_maps(obj, flags); if (err) goto out; @@ -974,13 +1105,46 @@ bpf_object__find_program_by_title(struct bpf_object *obj, const char *title) return NULL; } +static bool bpf_object__shndx_is_data(const struct bpf_object *obj, + int shndx) +{ + return shndx == obj->efile.data_shndx || + shndx == obj->efile.bss_shndx || + shndx == obj->efile.rodata_shndx; +} + +static bool bpf_object__shndx_is_maps(const struct bpf_object *obj, + int shndx) +{ + return shndx == obj->efile.maps_shndx; +} + +static bool bpf_object__relo_in_known_section(const struct bpf_object *obj, + int shndx) +{ + return shndx == obj->efile.text_shndx || + bpf_object__shndx_is_maps(obj, shndx) || + bpf_object__shndx_is_data(obj, shndx); +} + +static enum libbpf_map_type +bpf_object__section_to_libbpf_map_type(const struct bpf_object *obj, int shndx) +{ + if (shndx == obj->efile.data_shndx) + return LIBBPF_MAP_DATA; + else if (shndx == obj->efile.bss_shndx) + return LIBBPF_MAP_BSS; + else if (shndx == obj->efile.rodata_shndx) + return LIBBPF_MAP_RODATA; + else + return LIBBPF_MAP_UNSPEC; +} + static int bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, Elf_Data *data, struct bpf_object *obj) { Elf_Data *symbols = obj->efile.symbols; - int text_shndx = obj->efile.text_shndx; - int maps_shndx = obj->efile.maps_shndx; struct bpf_map *maps = obj->maps; size_t nr_maps = obj->nr_maps; int i, nrels; @@ -1000,7 +1164,10 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, GElf_Sym sym; GElf_Rel rel; unsigned int insn_idx; + unsigned int shdr_idx; struct bpf_insn *insns = prog->insns; + enum libbpf_map_type type; + const char *name; size_t map_idx; if (!gelf_getrel(data, i, &rel)) { @@ -1015,13 +1182,18 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, GELF_R_SYM(rel.r_info)); return -LIBBPF_ERRNO__FORMAT; } - pr_debug("relo for %lld value %lld name %d\n", + + name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, + sym.st_name) ? : "<?>"; + + pr_debug("relo for %lld value %lld name %d (\'%s\')\n", (long long) (rel.r_info >> 32), - (long long) sym.st_value, sym.st_name); + (long long) sym.st_value, sym.st_name, name); - if (sym.st_shndx != maps_shndx && sym.st_shndx != text_shndx) { - pr_warning("Program '%s' contains non-map related relo data pointing to section %u\n", - prog->section_name, sym.st_shndx); + shdr_idx = sym.st_shndx; + if (!bpf_object__relo_in_known_section(obj, shdr_idx)) { + pr_warning("Program '%s' contains unrecognized relo data pointing to section %u\n", + prog->section_name, shdr_idx); return -LIBBPF_ERRNO__RELOC; } @@ -1046,10 +1218,22 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, return -LIBBPF_ERRNO__RELOC; } - if (sym.st_shndx == maps_shndx) { - /* TODO: 'maps' is sorted. We can use bsearch to make it faster. */ + if (bpf_object__shndx_is_maps(obj, shdr_idx) || + bpf_object__shndx_is_data(obj, shdr_idx)) { + type = bpf_object__section_to_libbpf_map_type(obj, shdr_idx); + if (type != LIBBPF_MAP_UNSPEC && + GELF_ST_BIND(sym.st_info) == STB_GLOBAL) { + pr_warning("bpf: relocation: not yet supported relo for non-static global \'%s\' variable found in insns[%d].code 0x%x\n", + name, insn_idx, insns[insn_idx].code); + return -LIBBPF_ERRNO__RELOC; + } + for (map_idx = 0; map_idx < nr_maps; map_idx++) { - if (maps[map_idx].offset == sym.st_value) { + if (maps[map_idx].libbpf_type != type) + continue; + if (type != LIBBPF_MAP_UNSPEC || + (type == LIBBPF_MAP_UNSPEC && + maps[map_idx].offset == sym.st_value)) { pr_debug("relocation: find map %zd (%s) for insn %u\n", map_idx, maps[map_idx].name, insn_idx); break; @@ -1062,7 +1246,8 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, return -LIBBPF_ERRNO__RELOC; } - prog->reloc_desc[i].type = RELO_LD64; + prog->reloc_desc[i].type = type != LIBBPF_MAP_UNSPEC ? + RELO_DATA : RELO_LD64; prog->reloc_desc[i].insn_idx = insn_idx; prog->reloc_desc[i].map_idx = map_idx; } @@ -1073,18 +1258,27 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf) { struct bpf_map_def *def = &map->def; - __u32 key_type_id, value_type_id; + __u32 key_type_id = 0, value_type_id = 0; int ret; - ret = btf__get_map_kv_tids(btf, map->name, def->key_size, - def->value_size, &key_type_id, - &value_type_id); - if (ret) + if (!bpf_map__is_internal(map)) { + ret = btf__get_map_kv_tids(btf, map->name, def->key_size, + def->value_size, &key_type_id, + &value_type_id); + } else { + /* + * LLVM annotates global data differently in BTF, that is, + * only as '.data', '.bss' or '.rodata'. + */ + ret = btf__find_by_name(btf, + libbpf_type_to_btf_name[map->libbpf_type]); + } + if (ret < 0) return ret; map->btf_key_type_id = key_type_id; - map->btf_value_type_id = value_type_id; - + map->btf_value_type_id = bpf_map__is_internal(map) ? + ret : value_type_id; return 0; } @@ -1196,6 +1390,34 @@ bpf_object__probe_caps(struct bpf_object *obj) } static int +bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map) +{ + char *cp, errmsg[STRERR_BUFSIZE]; + int err, zero = 0; + __u8 *data; + + /* Nothing to do here since kernel already zero-initializes .bss map. */ + if (map->libbpf_type == LIBBPF_MAP_BSS) + return 0; + + data = map->libbpf_type == LIBBPF_MAP_DATA ? + obj->sections.data : obj->sections.rodata; + + err = bpf_map_update_elem(map->fd, &zero, data, 0); + /* Freeze .rodata map as read-only from syscall side. */ + if (!err && map->libbpf_type == LIBBPF_MAP_RODATA) { + err = bpf_map_freeze(map->fd); + if (err) { + cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + pr_warning("Error freezing map(%s) as read-only: %s\n", + map->name, cp); + err = 0; + } + } + return err; +} + +static int bpf_object__create_maps(struct bpf_object *obj) { struct bpf_create_map_attr create_attr = {}; @@ -1252,6 +1474,7 @@ bpf_object__create_maps(struct bpf_object *obj) size_t j; err = *pfd; +err_out: cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); pr_warning("failed to create map (name: '%s'): %s\n", map->name, cp); @@ -1259,6 +1482,15 @@ bpf_object__create_maps(struct bpf_object *obj) zclose(obj->maps[j].fd); return err; } + + if (bpf_map__is_internal(map)) { + err = bpf_object__populate_internal_map(obj, map); + if (err < 0) { + zclose(*pfd); + goto err_out; + } + } + pr_debug("create map %s: fd=%d\n", map->name, *pfd); } @@ -1413,19 +1645,27 @@ bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj) return 0; for (i = 0; i < prog->nr_reloc; i++) { - if (prog->reloc_desc[i].type == RELO_LD64) { + if (prog->reloc_desc[i].type == RELO_LD64 || + prog->reloc_desc[i].type == RELO_DATA) { + bool relo_data = prog->reloc_desc[i].type == RELO_DATA; struct bpf_insn *insns = prog->insns; int insn_idx, map_idx; insn_idx = prog->reloc_desc[i].insn_idx; map_idx = prog->reloc_desc[i].map_idx; - if (insn_idx >= (int)prog->insns_cnt) { + if (insn_idx + 1 >= (int)prog->insns_cnt) { pr_warning("relocation out of range: '%s'\n", prog->section_name); return -LIBBPF_ERRNO__RELOC; } - insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD; + + if (!relo_data) { + insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD; + } else { + insns[insn_idx].src_reg = BPF_PSEUDO_MAP_VALUE; + insns[insn_idx + 1].imm = insns[insn_idx].imm; + } insns[insn_idx].imm = obj->maps[map_idx].fd; } else if (prog->reloc_desc[i].type == RELO_CALL) { err = bpf_program__reloc_text(prog, obj, @@ -2321,6 +2561,9 @@ void bpf_object__close(struct bpf_object *obj) obj->maps[i].priv = NULL; obj->maps[i].clear_priv = NULL; } + + zfree(&obj->sections.rodata); + zfree(&obj->sections.data); zfree(&obj->maps); obj->nr_maps = 0; @@ -2798,6 +3041,11 @@ bool bpf_map__is_offload_neutral(struct bpf_map *map) return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY; } +bool bpf_map__is_internal(struct bpf_map *map) +{ + return map->libbpf_type != LIBBPF_MAP_UNSPEC; +} + void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex) { map->map_ifindex = ifindex; diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 531323391d07..12db2822c8e7 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -301,6 +301,7 @@ LIBBPF_API void *bpf_map__priv(struct bpf_map *map); LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd); LIBBPF_API int bpf_map__resize(struct bpf_map *map, __u32 max_entries); LIBBPF_API bool bpf_map__is_offload_neutral(struct bpf_map *map); +LIBBPF_API bool bpf_map__is_internal(struct bpf_map *map); LIBBPF_API void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex); 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); diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index f3ce50500cf2..be42bdffc8de 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -157,3 +157,9 @@ LIBBPF_0.0.2 { bpf_program__bpil_addr_to_offs; bpf_program__bpil_offs_to_addr; } LIBBPF_0.0.1; + +LIBBPF_0.0.3 { + global: + bpf_map__is_internal; + bpf_map_freeze; +} LIBBPF_0.0.2; |