libbpf: Refactor global data map initialization
Refactor global data map initialization to use anonymous mmap()-ed memory instead of malloc()-ed one. This allows to do a transparent re-mmap()-ing of already existing memory address to point to BPF map's memory after bpf_object__load() step (done in follow up patch). This choreographed setup allows to have a nice and unsurprising way to pre-initialize read-only (and r/w as well) maps by user and after BPF map creation keep working with mmap()-ed contents of this map. All in a way that doesn't require user code to update any pointers: the illusion of working with memory contents is preserved before and after actual BPF map instantiation. Selftests and runqslower example demonstrate this feature in follow up patches. Signed-off-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/20191214014341.3442258-10-andriin@fb.com
This commit is contained in:
parent
01af3bf067
commit
eba9c5f498
|
@ -221,16 +221,12 @@ struct bpf_map {
|
|||
void *priv;
|
||||
bpf_map_clear_priv_t clear_priv;
|
||||
enum libbpf_map_type libbpf_type;
|
||||
void *mmaped;
|
||||
char *pin_path;
|
||||
bool pinned;
|
||||
bool reused;
|
||||
};
|
||||
|
||||
struct bpf_secdata {
|
||||
void *rodata;
|
||||
void *data;
|
||||
};
|
||||
|
||||
static LIST_HEAD(bpf_objects_list);
|
||||
|
||||
struct bpf_object {
|
||||
|
@ -243,7 +239,6 @@ struct bpf_object {
|
|||
struct bpf_map *maps;
|
||||
size_t nr_maps;
|
||||
size_t maps_cap;
|
||||
struct bpf_secdata sections;
|
||||
|
||||
bool loaded;
|
||||
bool has_pseudo_calls;
|
||||
|
@ -828,13 +823,24 @@ static struct bpf_map *bpf_object__add_map(struct bpf_object *obj)
|
|||
return &obj->maps[obj->nr_maps++];
|
||||
}
|
||||
|
||||
static size_t bpf_map_mmap_sz(const struct bpf_map *map)
|
||||
{
|
||||
long page_sz = sysconf(_SC_PAGE_SIZE);
|
||||
size_t map_sz;
|
||||
|
||||
map_sz = roundup(map->def.value_size, 8) * map->def.max_entries;
|
||||
map_sz = roundup(map_sz, page_sz);
|
||||
return map_sz;
|
||||
}
|
||||
|
||||
static int
|
||||
bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
|
||||
int sec_idx, Elf_Data *data, void **data_buff)
|
||||
int sec_idx, void *data, size_t data_sz)
|
||||
{
|
||||
char map_name[BPF_OBJ_NAME_LEN];
|
||||
struct bpf_map_def *def;
|
||||
struct bpf_map *map;
|
||||
int err;
|
||||
|
||||
map = bpf_object__add_map(obj);
|
||||
if (IS_ERR(map))
|
||||
|
@ -854,7 +860,7 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
|
|||
def = &map->def;
|
||||
def->type = BPF_MAP_TYPE_ARRAY;
|
||||
def->key_size = sizeof(int);
|
||||
def->value_size = data->d_size;
|
||||
def->value_size = data_sz;
|
||||
def->max_entries = 1;
|
||||
def->map_flags = type == LIBBPF_MAP_RODATA ? BPF_F_RDONLY_PROG : 0;
|
||||
def->map_flags |= BPF_F_MMAPABLE;
|
||||
|
@ -862,16 +868,20 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
|
|||
pr_debug("map '%s' (global data): at sec_idx %d, offset %zu, flags %x.\n",
|
||||
map_name, map->sec_idx, map->sec_offset, def->map_flags);
|
||||
|
||||
if (data_buff) {
|
||||
*data_buff = malloc(data->d_size);
|
||||
if (!*data_buff) {
|
||||
map->mmaped = mmap(NULL, bpf_map_mmap_sz(map), PROT_READ | PROT_WRITE,
|
||||
MAP_SHARED | MAP_ANONYMOUS, -1, 0);
|
||||
if (map->mmaped == MAP_FAILED) {
|
||||
err = -errno;
|
||||
map->mmaped = NULL;
|
||||
pr_warn("failed to alloc map '%s' content buffer: %d\n",
|
||||
map->name, err);
|
||||
zfree(&map->name);
|
||||
pr_warn("failed to alloc map content buffer\n");
|
||||
return -ENOMEM;
|
||||
}
|
||||
memcpy(*data_buff, data->d_buf, data->d_size);
|
||||
return err;
|
||||
}
|
||||
|
||||
if (type != LIBBPF_MAP_BSS)
|
||||
memcpy(map->mmaped, data, data_sz);
|
||||
|
||||
pr_debug("map %td is \"%s\"\n", map - obj->maps, map->name);
|
||||
return 0;
|
||||
}
|
||||
|
@ -886,23 +896,24 @@ static int bpf_object__init_global_data_maps(struct bpf_object *obj)
|
|||
if (obj->efile.data_shndx >= 0) {
|
||||
err = bpf_object__init_internal_map(obj, LIBBPF_MAP_DATA,
|
||||
obj->efile.data_shndx,
|
||||
obj->efile.data,
|
||||
&obj->sections.data);
|
||||
obj->efile.data->d_buf,
|
||||
obj->efile.data->d_size);
|
||||
if (err)
|
||||
return err;
|
||||
}
|
||||
if (obj->efile.rodata_shndx >= 0) {
|
||||
err = bpf_object__init_internal_map(obj, LIBBPF_MAP_RODATA,
|
||||
obj->efile.rodata_shndx,
|
||||
obj->efile.rodata,
|
||||
&obj->sections.rodata);
|
||||
obj->efile.rodata->d_buf,
|
||||
obj->efile.rodata->d_size);
|
||||
if (err)
|
||||
return err;
|
||||
}
|
||||
if (obj->efile.bss_shndx >= 0) {
|
||||
err = bpf_object__init_internal_map(obj, LIBBPF_MAP_BSS,
|
||||
obj->efile.bss_shndx,
|
||||
obj->efile.bss, NULL);
|
||||
NULL,
|
||||
obj->efile.bss->d_size);
|
||||
if (err)
|
||||
return err;
|
||||
}
|
||||
|
@ -2292,27 +2303,32 @@ 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, map->mmaped, 0);
|
||||
if (err) {
|
||||
err = -errno;
|
||||
cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg));
|
||||
pr_warn("Error setting initial map(%s) contents: %s\n",
|
||||
map->name, cp);
|
||||
return err;
|
||||
}
|
||||
|
||||
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) {
|
||||
if (map->libbpf_type == LIBBPF_MAP_RODATA) {
|
||||
err = bpf_map_freeze(map->fd);
|
||||
if (err) {
|
||||
cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
|
||||
err = -errno;
|
||||
cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg));
|
||||
pr_warn("Error freezing map(%s) as read-only: %s\n",
|
||||
map->name, cp);
|
||||
err = 0;
|
||||
}
|
||||
}
|
||||
return err;
|
||||
}
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int
|
||||
|
@ -4683,17 +4699,22 @@ void bpf_object__close(struct bpf_object *obj)
|
|||
btf_ext__free(obj->btf_ext);
|
||||
|
||||
for (i = 0; i < obj->nr_maps; i++) {
|
||||
zfree(&obj->maps[i].name);
|
||||
zfree(&obj->maps[i].pin_path);
|
||||
if (obj->maps[i].clear_priv)
|
||||
obj->maps[i].clear_priv(&obj->maps[i],
|
||||
obj->maps[i].priv);
|
||||
obj->maps[i].priv = NULL;
|
||||
obj->maps[i].clear_priv = NULL;
|
||||
struct bpf_map *map = &obj->maps[i];
|
||||
|
||||
if (map->clear_priv)
|
||||
map->clear_priv(map, map->priv);
|
||||
map->priv = NULL;
|
||||
map->clear_priv = NULL;
|
||||
|
||||
if (map->mmaped) {
|
||||
munmap(map->mmaped, bpf_map_mmap_sz(map));
|
||||
map->mmaped = NULL;
|
||||
}
|
||||
|
||||
zfree(&map->name);
|
||||
zfree(&map->pin_path);
|
||||
}
|
||||
|
||||
zfree(&obj->sections.rodata);
|
||||
zfree(&obj->sections.data);
|
||||
zfree(&obj->maps);
|
||||
obj->nr_maps = 0;
|
||||
|
||||
|
|
Loading…
Reference in New Issue