summaryrefslogtreecommitdiffstats
path: root/tools/lib/bpf/libbpf.c
diff options
context:
space:
mode:
Diffstat (limited to 'tools/lib/bpf/libbpf.c')
-rw-r--r--tools/lib/bpf/libbpf.c1756
1 files changed, 367 insertions, 1389 deletions
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 6f5e2757bb3c..88d8825fc6f6 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -193,6 +193,8 @@ enum kern_feature_id {
FEAT_MODULE_BTF,
/* BTF_KIND_FLOAT support */
FEAT_BTF_FLOAT,
+ /* BPF perf link support */
+ FEAT_PERF_LINK,
__FEAT_CNT,
};
@@ -498,6 +500,10 @@ struct bpf_object {
* it at load time.
*/
struct btf *btf_vmlinux;
+ /* Path to the custom BTF to be used for BPF CO-RE relocations as an
+ * override for vmlinux BTF.
+ */
+ char *btf_custom_path;
/* vmlinux BTF override for CO-RE relocations */
struct btf *btf_vmlinux_override;
/* Lazily initialized kernel module BTFs */
@@ -591,11 +597,6 @@ static bool insn_is_subprog_call(const struct bpf_insn *insn)
insn->off == 0;
}
-static bool is_ldimm64_insn(struct bpf_insn *insn)
-{
- return insn->code == (BPF_LD | BPF_IMM | BPF_DW);
-}
-
static bool is_call_insn(const struct bpf_insn *insn)
{
return insn->code == (BPF_JMP | BPF_CALL);
@@ -2645,8 +2646,10 @@ static bool obj_needs_vmlinux_btf(const struct bpf_object *obj)
struct bpf_program *prog;
int i;
- /* CO-RE relocations need kernel BTF */
- if (obj->btf_ext && obj->btf_ext->core_relo_info.len)
+ /* CO-RE relocations need kernel BTF, only when btf_custom_path
+ * is not specified
+ */
+ if (obj->btf_ext && obj->btf_ext->core_relo_info.len && !obj->btf_custom_path)
return true;
/* Support for typed ksyms needs kernel BTF */
@@ -2679,7 +2682,7 @@ static int bpf_object__load_vmlinux_btf(struct bpf_object *obj, bool force)
if (!force && !obj_needs_vmlinux_btf(obj))
return 0;
- obj->btf_vmlinux = libbpf_find_kernel_btf();
+ obj->btf_vmlinux = btf__load_vmlinux_btf();
err = libbpf_get_error(obj->btf_vmlinux);
if (err) {
pr_warn("Error loading vmlinux BTF: %d\n", err);
@@ -2768,7 +2771,7 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
*/
btf__set_fd(kern_btf, 0);
} else {
- err = btf__load(kern_btf);
+ err = btf__load_into_kernel(kern_btf);
}
if (sanitize) {
if (!err) {
@@ -3894,6 +3897,42 @@ static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map)
return 0;
}
+static int bpf_get_map_info_from_fdinfo(int fd, struct bpf_map_info *info)
+{
+ char file[PATH_MAX], buff[4096];
+ FILE *fp;
+ __u32 val;
+ int err;
+
+ snprintf(file, sizeof(file), "/proc/%d/fdinfo/%d", getpid(), fd);
+ memset(info, 0, sizeof(*info));
+
+ fp = fopen(file, "r");
+ if (!fp) {
+ err = -errno;
+ pr_warn("failed to open %s: %d. No procfs support?\n", file,
+ err);
+ return err;
+ }
+
+ while (fgets(buff, sizeof(buff), fp)) {
+ if (sscanf(buff, "map_type:\t%u", &val) == 1)
+ info->type = val;
+ else if (sscanf(buff, "key_size:\t%u", &val) == 1)
+ info->key_size = val;
+ else if (sscanf(buff, "value_size:\t%u", &val) == 1)
+ info->value_size = val;
+ else if (sscanf(buff, "max_entries:\t%u", &val) == 1)
+ info->max_entries = val;
+ else if (sscanf(buff, "map_flags:\t%i", &val) == 1)
+ info->map_flags = val;
+ }
+
+ fclose(fp);
+
+ return 0;
+}
+
int bpf_map__reuse_fd(struct bpf_map *map, int fd)
{
struct bpf_map_info info = {};
@@ -3902,6 +3941,8 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd)
char *new_name;
err = bpf_obj_get_info_by_fd(fd, &info, &len);
+ if (err && errno == EINVAL)
+ err = bpf_get_map_info_from_fdinfo(fd, &info);
if (err)
return libbpf_err(err);
@@ -4298,6 +4339,37 @@ static int probe_module_btf(void)
return !err;
}
+static int probe_perf_link(void)
+{
+ struct bpf_load_program_attr attr;
+ struct bpf_insn insns[] = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ };
+ int prog_fd, link_fd, err;
+
+ memset(&attr, 0, sizeof(attr));
+ attr.prog_type = BPF_PROG_TYPE_TRACEPOINT;
+ attr.insns = insns;
+ attr.insns_cnt = ARRAY_SIZE(insns);
+ attr.license = "GPL";
+ prog_fd = bpf_load_program_xattr(&attr, NULL, 0);
+ if (prog_fd < 0)
+ return -errno;
+
+ /* use invalid perf_event FD to get EBADF, if link is supported;
+ * otherwise EINVAL should be returned
+ */
+ link_fd = bpf_link_create(prog_fd, -1, BPF_PERF_EVENT, NULL);
+ err = -errno; /* close() can clobber errno */
+
+ if (link_fd >= 0)
+ close(link_fd);
+ close(prog_fd);
+
+ return link_fd < 0 && err == -EBADF;
+}
+
enum kern_feature_result {
FEAT_UNKNOWN = 0,
FEAT_SUPPORTED = 1,
@@ -4348,6 +4420,9 @@ static struct kern_feature_desc {
[FEAT_BTF_FLOAT] = {
"BTF_KIND_FLOAT support", probe_kern_btf_float,
},
+ [FEAT_PERF_LINK] = {
+ "BPF perf link support", probe_perf_link,
+ },
};
static bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id)
@@ -4381,12 +4456,16 @@ static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd)
struct bpf_map_info map_info = {};
char msg[STRERR_BUFSIZE];
__u32 map_info_len;
+ int err;
map_info_len = sizeof(map_info);
- if (bpf_obj_get_info_by_fd(map_fd, &map_info, &map_info_len)) {
- pr_warn("failed to get map info for map FD %d: %s\n",
- map_fd, libbpf_strerror_r(errno, msg, sizeof(msg)));
+ err = bpf_obj_get_info_by_fd(map_fd, &map_info, &map_info_len);
+ if (err && errno == EINVAL)
+ err = bpf_get_map_info_from_fdinfo(map_fd, &map_info);
+ if (err) {
+ pr_warn("failed to get map info for map FD %d: %s\n", map_fd,
+ libbpf_strerror_r(errno, msg, sizeof(msg)));
return false;
}
@@ -4479,6 +4558,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
{
struct bpf_create_map_attr create_attr;
struct bpf_map_def *def = &map->def;
+ int err = 0;
memset(&create_attr, 0, sizeof(create_attr));
@@ -4521,8 +4601,6 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
if (bpf_map_type__is_map_in_map(def->type)) {
if (map->inner_map) {
- int err;
-
err = bpf_object__create_map(obj, map->inner_map, true);
if (err) {
pr_warn("map '%s': failed to create inner map: %d\n",
@@ -4547,8 +4625,8 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
if (map->fd < 0 && (create_attr.btf_key_type_id ||
create_attr.btf_value_type_id)) {
char *cp, errmsg[STRERR_BUFSIZE];
- int err = -errno;
+ err = -errno;
cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg));
pr_warn("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n",
map->name, cp, err);
@@ -4560,8 +4638,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
map->fd = bpf_create_map_xattr(&create_attr);
}
- if (map->fd < 0)
- return -errno;
+ err = map->fd < 0 ? -errno : 0;
if (bpf_map_type__is_map_in_map(def->type) && map->inner_map) {
if (obj->gen_loader)
@@ -4570,7 +4647,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
zfree(&map->inner_map);
}
- return 0;
+ return err;
}
static int init_map_slots(struct bpf_object *obj, struct bpf_map *map)
@@ -4616,10 +4693,13 @@ bpf_object__create_maps(struct bpf_object *obj)
char *cp, errmsg[STRERR_BUFSIZE];
unsigned int i, j;
int err;
+ bool retried;
for (i = 0; i < obj->nr_maps; i++) {
map = &obj->maps[i];
+ retried = false;
+retry:
if (map->pin_path) {
err = bpf_object__reuse_map(map);
if (err) {
@@ -4627,6 +4707,12 @@ bpf_object__create_maps(struct bpf_object *obj)
map->name);
goto err_out;
}
+ if (retried && map->fd < 0) {
+ pr_warn("map '%s': cannot find pinned map\n",
+ map->name);
+ err = -ENOENT;
+ goto err_out;
+ }
}
if (map->fd >= 0) {
@@ -4660,9 +4746,13 @@ bpf_object__create_maps(struct bpf_object *obj)
if (map->pin_path && !map->pinned) {
err = bpf_map__pin(map, NULL);
if (err) {
+ zclose(map->fd);
+ if (!retried && err == -EEXIST) {
+ retried = true;
+ goto retry;
+ }
pr_warn("map '%s': failed to auto-pin at '%s': %d\n",
map->name, map->pin_path, err);
- zclose(map->fd);
goto err_out;
}
}
@@ -4679,279 +4769,6 @@ err_out:
return err;
}
-#define BPF_CORE_SPEC_MAX_LEN 64
-
-/* represents BPF CO-RE field or array element accessor */
-struct bpf_core_accessor {
- __u32 type_id; /* struct/union type or array element type */
- __u32 idx; /* field index or array index */
- const char *name; /* field name or NULL for array accessor */
-};
-
-struct bpf_core_spec {
- const struct btf *btf;
- /* high-level spec: named fields and array indices only */
- struct bpf_core_accessor spec[BPF_CORE_SPEC_MAX_LEN];
- /* original unresolved (no skip_mods_or_typedefs) root type ID */
- __u32 root_type_id;
- /* CO-RE relocation kind */
- enum bpf_core_relo_kind relo_kind;
- /* high-level spec length */
- int len;
- /* raw, low-level spec: 1-to-1 with accessor spec string */
- int raw_spec[BPF_CORE_SPEC_MAX_LEN];
- /* raw spec length */
- int raw_len;
- /* field bit offset represented by spec */
- __u32 bit_offset;
-};
-
-static bool str_is_empty(const char *s)
-{
- return !s || !s[0];
-}
-
-static bool is_flex_arr(const struct btf *btf,
- const struct bpf_core_accessor *acc,
- const struct btf_array *arr)
-{
- const struct btf_type *t;
-
- /* not a flexible array, if not inside a struct or has non-zero size */
- if (!acc->name || arr->nelems > 0)
- return false;
-
- /* has to be the last member of enclosing struct */
- t = btf__type_by_id(btf, acc->type_id);
- return acc->idx == btf_vlen(t) - 1;
-}
-
-static const char *core_relo_kind_str(enum bpf_core_relo_kind kind)
-{
- switch (kind) {
- case BPF_FIELD_BYTE_OFFSET: return "byte_off";
- case BPF_FIELD_BYTE_SIZE: return "byte_sz";
- case BPF_FIELD_EXISTS: return "field_exists";
- case BPF_FIELD_SIGNED: return "signed";
- case BPF_FIELD_LSHIFT_U64: return "lshift_u64";
- case BPF_FIELD_RSHIFT_U64: return "rshift_u64";
- case BPF_TYPE_ID_LOCAL: return "local_type_id";
- case BPF_TYPE_ID_TARGET: return "target_type_id";
- case BPF_TYPE_EXISTS: return "type_exists";
- case BPF_TYPE_SIZE: return "type_size";
- case BPF_ENUMVAL_EXISTS: return "enumval_exists";
- case BPF_ENUMVAL_VALUE: return "enumval_value";
- default: return "unknown";
- }
-}
-
-static bool core_relo_is_field_based(enum bpf_core_relo_kind kind)
-{
- switch (kind) {
- case BPF_FIELD_BYTE_OFFSET:
- case BPF_FIELD_BYTE_SIZE:
- case BPF_FIELD_EXISTS:
- case BPF_FIELD_SIGNED:
- case BPF_FIELD_LSHIFT_U64:
- case BPF_FIELD_RSHIFT_U64:
- return true;
- default:
- return false;
- }
-}
-
-static bool core_relo_is_type_based(enum bpf_core_relo_kind kind)
-{
- switch (kind) {
- case BPF_TYPE_ID_LOCAL:
- case BPF_TYPE_ID_TARGET:
- case BPF_TYPE_EXISTS:
- case BPF_TYPE_SIZE:
- return true;
- default:
- return false;
- }
-}
-
-static bool core_relo_is_enumval_based(enum bpf_core_relo_kind kind)
-{
- switch (kind) {
- case BPF_ENUMVAL_EXISTS:
- case BPF_ENUMVAL_VALUE:
- return true;
- default:
- return false;
- }
-}
-
-/*
- * Turn bpf_core_relo into a low- and high-level spec representation,
- * validating correctness along the way, as well as calculating resulting
- * field bit offset, specified by accessor string. Low-level spec captures
- * every single level of nestedness, including traversing anonymous
- * struct/union members. High-level one only captures semantically meaningful
- * "turning points": named fields and array indicies.
- * E.g., for this case:
- *
- * struct sample {
- * int __unimportant;
- * struct {
- * int __1;
- * int __2;
- * int a[7];
- * };
- * };
- *
- * struct sample *s = ...;
- *
- * int x = &s->a[3]; // access string = '0:1:2:3'
- *
- * Low-level spec has 1:1 mapping with each element of access string (it's
- * just a parsed access string representation): [0, 1, 2, 3].
- *
- * High-level spec will capture only 3 points:
- * - intial zero-index access by pointer (&s->... is the same as &s[0]...);
- * - field 'a' access (corresponds to '2' in low-level spec);
- * - array element #3 access (corresponds to '3' in low-level spec).
- *
- * Type-based relocations (TYPE_EXISTS/TYPE_SIZE,
- * TYPE_ID_LOCAL/TYPE_ID_TARGET) don't capture any field information. Their
- * spec and raw_spec are kept empty.
- *
- * Enum value-based relocations (ENUMVAL_EXISTS/ENUMVAL_VALUE) use access
- * string to specify enumerator's value index that need to be relocated.
- */
-static int bpf_core_parse_spec(const struct btf *btf,
- __u32 type_id,
- const char *spec_str,
- enum bpf_core_relo_kind relo_kind,
- struct bpf_core_spec *spec)
-{
- int access_idx, parsed_len, i;
- struct bpf_core_accessor *acc;
- const struct btf_type *t;
- const char *name;
- __u32 id;
- __s64 sz;
-
- if (str_is_empty(spec_str) || *spec_str == ':')
- return -EINVAL;
-
- memset(spec, 0, sizeof(*spec));
- spec->btf = btf;
- spec->root_type_id = type_id;
- spec->relo_kind = relo_kind;
-
- /* type-based relocations don't have a field access string */
- if (core_relo_is_type_based(relo_kind)) {
- if (strcmp(spec_str, "0"))
- return -EINVAL;
- return 0;
- }
-
- /* parse spec_str="0:1:2:3:4" into array raw_spec=[0, 1, 2, 3, 4] */
- while (*spec_str) {
- if (*spec_str == ':')
- ++spec_str;
- if (sscanf(spec_str, "%d%n", &access_idx, &parsed_len) != 1)
- return -EINVAL;
- if (spec->raw_len == BPF_CORE_SPEC_MAX_LEN)
- return -E2BIG;
- spec_str += parsed_len;
- spec->raw_spec[spec->raw_len++] = access_idx;
- }
-
- if (spec->raw_len == 0)
- return -EINVAL;
-
- t = skip_mods_and_typedefs(btf, type_id, &id);
- if (!t)
- return -EINVAL;
-
- access_idx = spec->raw_spec[0];
- acc = &spec->spec[0];
- acc->type_id = id;
- acc->idx = access_idx;
- spec->len++;
-
- if (core_relo_is_enumval_based(relo_kind)) {
- if (!btf_is_enum(t) || spec->raw_len > 1 || access_idx >= btf_vlen(t))
- return -EINVAL;
-
- /* record enumerator name in a first accessor */
- acc->name = btf__name_by_offset(btf, btf_enum(t)[access_idx].name_off);
- return 0;
- }
-
- if (!core_relo_is_field_based(relo_kind))
- return -EINVAL;
-
- sz = btf__resolve_size(btf, id);
- if (sz < 0)
- return sz;
- spec->bit_offset = access_idx * sz * 8;
-
- for (i = 1; i < spec->raw_len; i++) {
- t = skip_mods_and_typedefs(btf, id, &id);
- if (!t)
- return -EINVAL;
-
- access_idx = spec->raw_spec[i];
- acc = &spec->spec[spec->len];
-
- if (btf_is_composite(t)) {
- const struct btf_member *m;
- __u32 bit_offset;
-
- if (access_idx >= btf_vlen(t))
- return -EINVAL;
-
- bit_offset = btf_member_bit_offset(t, access_idx);
- spec->bit_offset += bit_offset;
-
- m = btf_members(t) + access_idx;
- if (m->name_off) {
- name = btf__name_by_offset(btf, m->name_off);
- if (str_is_empty(name))
- return -EINVAL;
-
- acc->type_id = id;
- acc->idx = access_idx;
- acc->name = name;
- spec->len++;
- }
-
- id = m->type;
- } else if (btf_is_array(t)) {
- const struct btf_array *a = btf_array(t);
- bool flex;
-
- t = skip_mods_and_typedefs(btf, a->type, &id);
- if (!t)
- return -EINVAL;
-
- flex = is_flex_arr(btf, acc - 1, a);
- if (!flex && access_idx >= a->nelems)
- return -EINVAL;
-
- spec->spec[spec->len].type_id = id;
- spec->spec[spec->len].idx = access_idx;
- spec->len++;
-
- sz = btf__resolve_size(btf, id);
- if (sz < 0)
- return sz;
- spec->bit_offset += access_idx * sz * 8;
- } else {
- pr_warn("relo for [%u] %s (at idx %d) captures type [%d] of unexpected kind %s\n",
- type_id, spec_str, i, id, btf_kind_str(t));
- return -EINVAL;
- }
- }
-
- return 0;
-}
-
static bool bpf_core_is_flavor_sep(const char *s)
{
/* check X___Y name pattern, where X and Y are not underscores */
@@ -4964,7 +4781,7 @@ static bool bpf_core_is_flavor_sep(const char *s)
* before last triple underscore. Struct name part after last triple
* underscore is ignored by BPF CO-RE relocation during relocation matching.
*/
-static size_t bpf_core_essential_name_len(const char *name)
+size_t bpf_core_essential_name_len(const char *name)
{
size_t n = strlen(name);
int i;
@@ -4976,34 +4793,20 @@ static size_t bpf_core_essential_name_len(const char *name)
return n;
}
-struct core_cand
-{
- const struct btf *btf;
- const struct btf_type *t;
- const char *name;
- __u32 id;
-};
-
-/* dynamically sized list of type IDs and its associated struct btf */
-struct core_cand_list {
- struct core_cand *cands;
- int len;
-};
-
-static void bpf_core_free_cands(struct core_cand_list *cands)
+static void bpf_core_free_cands(struct bpf_core_cand_list *cands)
{
free(cands->cands);
free(cands);
}
-static int bpf_core_add_cands(struct core_cand *local_cand,
+static int bpf_core_add_cands(struct bpf_core_cand *local_cand,
size_t local_essent_len,
const struct btf *targ_btf,
const char *targ_btf_name,
int targ_start_id,
- struct core_cand_list *cands)
+ struct bpf_core_cand_list *cands)
{
- struct core_cand *new_cands, *cand;
+ struct bpf_core_cand *new_cands, *cand;
const struct btf_type *t;
const char *targ_name;
size_t targ_essent_len;
@@ -5139,11 +4942,11 @@ err_out:
return 0;
}
-static struct core_cand_list *
+static struct bpf_core_cand_list *
bpf_core_find_cands(struct bpf_object *obj, const struct btf *local_btf, __u32 local_type_id)
{
- struct core_cand local_cand = {};
- struct core_cand_list *cands;
+ struct bpf_core_cand local_cand = {};
+ struct bpf_core_cand_list *cands;
const struct btf *main_btf;
size_t local_essent_len;
int err, i;
@@ -5197,165 +5000,6 @@ err_out:
return ERR_PTR(err);
}
-/* Check two types for compatibility for the purpose of field access
- * relocation. const/volatile/restrict and typedefs are skipped to ensure we
- * are relocating semantically compatible entities:
- * - any two STRUCTs/UNIONs are compatible and can be mixed;
- * - any two FWDs are compatible, if their names match (modulo flavor suffix);
- * - any two PTRs are always compatible;
- * - for ENUMs, names should be the same (ignoring flavor suffix) or at
- * least one of enums should be anonymous;
- * - for ENUMs, check sizes, names are ignored;
- * - for INT, size and signedness are ignored;
- * - any two FLOATs are always compatible;
- * - for ARRAY, dimensionality is ignored, element types are checked for
- * compatibility recursively;
- * - everything else shouldn't be ever a target of relocation.
- * These rules are not set in stone and probably will be adjusted as we get
- * more experience with using BPF CO-RE relocations.
- */
-static int bpf_core_fields_are_compat(const struct btf *local_btf,
- __u32 local_id,
- const struct btf *targ_btf,
- __u32 targ_id)
-{
- const struct btf_type *local_type, *targ_type;
-
-recur:
- local_type = skip_mods_and_typedefs(local_btf, local_id, &local_id);
- targ_type = skip_mods_and_typedefs(targ_btf, targ_id, &targ_id);
- if (!local_type || !targ_type)
- return -EINVAL;
-
- if (btf_is_composite(local_type) && btf_is_composite(targ_type))
- return 1;
- if (btf_kind(local_type) != btf_kind(targ_type))
- return 0;
-
- switch (btf_kind(local_type)) {
- case BTF_KIND_PTR:
- case BTF_KIND_FLOAT:
- return 1;
- case BTF_KIND_FWD:
- case BTF_KIND_ENUM: {
- const char *local_name, *targ_name;
- size_t local_len, targ_len;
-
- local_name = btf__name_by_offset(local_btf,
- local_type->name_off);
- targ_name = btf__name_by_offset(targ_btf, targ_type->name_off);
- local_len = bpf_core_essential_name_len(local_name);
- targ_len = bpf_core_essential_name_len(targ_name);
- /* one of them is anonymous or both w/ same flavor-less names */
- return local_len == 0 || targ_len == 0 ||
- (local_len == targ_len &&
- strncmp(local_name, targ_name, local_len) == 0);
- }
- case BTF_KIND_INT:
- /* just reject deprecated bitfield-like integers; all other
- * integers are by default compatible between each other
- */
- return btf_int_offset(local_type) == 0 &&
- btf_int_offset(targ_type) == 0;
- case BTF_KIND_ARRAY:
- local_id = btf_array(local_type)->type;
- targ_id = btf_array(targ_type)->type;
- goto recur;
- default:
- pr_warn("unexpected kind %d relocated, local [%d], target [%d]\n",
- btf_kind(local_type), local_id, targ_id);
- return 0;
- }
-}
-
-/*
- * Given single high-level named field accessor in local type, find
- * corresponding high-level accessor for a target type. Along the way,
- * maintain low-level spec for target as well. Also keep updating target
- * bit offset.
- *
- * Searching is performed through recursive exhaustive enumeration of all
- * fields of a struct/union. If there are any anonymous (embedded)
- * structs/unions, they are recursively searched as well. If field with
- * desired name is found, check compatibility between local and target types,
- * before returning result.
- *
- * 1 is returned, if field is found.
- * 0 is returned if no compatible field is found.
- * <0 is returned on error.
- */
-static int bpf_core_match_member(const struct btf *local_btf,
- const struct bpf_core_accessor *local_acc,
- const struct btf *targ_btf,
- __u32 targ_id,
- struct bpf_core_spec *spec,
- __u32 *next_targ_id)
-{
- const struct btf_type *local_type, *targ_type;
- const struct btf_member *local_member, *m;
- const char *local_name, *targ_name;
- __u32 local_id;
- int i, n, found;
-
- targ_type = skip_mods_and_typedefs(targ_btf, targ_id, &targ_id);
- if (!targ_type)
- return -EINVAL;
- if (!btf_is_composite(targ_type))
- return 0;
-
- local_id = local_acc->type_id;
- local_type = btf__type_by_id(local_btf, local_id);
- local_member = btf_members(local_type) + local_acc->idx;
- local_name = btf__name_by_offset(local_btf, local_member->name_off);
-
- n = btf_vlen(targ_type);
- m = btf_members(targ_type);
- for (i = 0; i < n; i++, m++) {
- __u32 bit_offset;
-
- bit_offset = btf_member_bit_offset(targ_type, i);
-
- /* too deep struct/union/array nesting */
- if (spec->raw_len == BPF_CORE_SPEC_MAX_LEN)
- return -E2BIG;
-
- /* speculate this member will be the good one */
- spec->bit_offset += bit_offset;
- spec->raw_spec[spec->raw_len++] = i;
-
- targ_name = btf__name_by_offset(targ_btf, m->name_off);
- if (str_is_empty(targ_name)) {
- /* embedded struct/union, we need to go deeper */
- found = bpf_core_match_member(local_btf, local_acc,
- targ_btf, m->type,
- spec, next_targ_id);
- if (found) /* either found or error */
- return found;
- } else if (strcmp(local_name, targ_name) == 0) {
- /* matching named field */
- struct bpf_core_accessor *targ_acc;
-
- targ_acc = &spec->spec[spec->len++];
- targ_acc->type_id = targ_id;
- targ_acc->idx = i;
- targ_acc->name = targ_name;
-
- *next_targ_id = m->type;
- found = bpf_core_fields_are_compat(local_btf,
- local_member->type,
- targ_btf, m->type);
- if (!found)
- spec->len--; /* pop accessor */
- return found;
- }
- /* member turned out not to be what we looked for */
- spec->bit_offset -= bit_offset;
- spec->raw_len--;
- }
-
- return 0;
-}
-
/* Check local and target types for compatibility. This check is used for
* type-based CO-RE relocations and follow slightly different rules than
* field-based relocations. This function assumes that root types were already
@@ -5375,8 +5019,8 @@ static int bpf_core_match_member(const struct btf *local_btf,
* These rules are not set in stone and probably will be adjusted as we get
* more experience with using BPF CO-RE relocations.
*/
-static int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id,
- const struct btf *targ_btf, __u32 targ_id)
+int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id,
+ const struct btf *targ_btf, __u32 targ_id)
{
const struct btf_type *local_type, *targ_type;
int depth = 32; /* max recursion depth */
@@ -5450,671 +5094,6 @@ recur:
}
}
-/*
- * Try to match local spec to a target type and, if successful, produce full
- * target spec (high-level, low-level + bit offset).
- */
-static int bpf_core_spec_match(struct bpf_core_spec *local_spec,
- const struct btf *targ_btf, __u32 targ_id,
- struct bpf_core_spec *targ_spec)
-{
- const struct btf_type *targ_type;
- const struct bpf_core_accessor *local_acc;
- struct bpf_core_accessor *targ_acc;
- int i, sz, matched;
-
- memset(targ_spec, 0, sizeof(*targ_spec));
- targ_spec->btf = targ_btf;
- targ_spec->root_type_id = targ_id;
- targ_spec->relo_kind = local_spec->relo_kind;
-
- if (core_relo_is_type_based(local_spec->relo_kind)) {
- return bpf_core_types_are_compat(local_spec->btf,
- local_spec->root_type_id,
- targ_btf, targ_id);
- }
-
- local_acc = &local_spec->spec[0];
- targ_acc = &targ_spec->spec[0];
-
- if (core_relo_is_enumval_based(local_spec->relo_kind)) {
- size_t local_essent_len, targ_essent_len;
- const struct btf_enum *e;
- const char *targ_name;
-
- /* has to resolve to an enum */
- targ_type = skip_mods_and_typedefs(targ_spec->btf, targ_id, &targ_id);
- if (!btf_is_enum(targ_type))
- return 0;
-
- local_essent_len = bpf_core_essential_name_len(local_acc->name);
-
- for (i = 0, e = btf_enum(targ_type); i < btf_vlen(targ_type); i++, e++) {
- targ_name = btf__name_by_offset(targ_spec->btf, e->name_off);
- targ_essent_len = bpf_core_essential_name_len(targ_name);
- if (targ_essent_len != local_essent_len)
- continue;
- if (strncmp(local_acc->name, targ_name, local_essent_len) == 0) {
- targ_acc->type_id = targ_id;
- targ_acc->idx = i;
- targ_acc->name = targ_name;
- targ_spec->len++;
- targ_spec->raw_spec[targ_spec->raw_len] = targ_acc->idx;
- targ_spec->raw_len++;
- return 1;
- }
- }
- return 0;
- }
-
- if (!core_relo_is_field_based(local_spec->relo_kind))
- return -EINVAL;
-
- for (i = 0; i < local_spec->len; i++, local_acc++, targ_acc++) {
- targ_type = skip_mods_and_typedefs(targ_spec->btf, targ_id,
- &targ_id);
- if (!targ_type)
- return -EINVAL;
-
- if (local_acc->name) {
- matched = bpf_core_match_member(local_spec->btf,
- local_acc,
- targ_btf, targ_id,
- targ_spec, &targ_id);
- if (matched <= 0)
- return matched;
- } else {
- /* for i=0, targ_id is already treated as array element
- * type (because it's the original struct), for others
- * we should find array element type first
- */
- if (i > 0) {
- const struct btf_array *a;
- bool flex;
-
- if (!btf_is_array(targ_type))
- return 0;
-
- a = btf_array(targ_type);
- flex = is_flex_arr(targ_btf, targ_acc - 1, a);
- if (!flex && local_acc->idx >= a->nelems)
- return 0;
- if (!skip_mods_and_typedefs(targ_btf, a->type,
- &targ_id))
- return -EINVAL;
- }
-
- /* too deep struct/union/array nesting */
- if (targ_spec->raw_len == BPF_CORE_SPEC_MAX_LEN)
- return -E2BIG;
-
- targ_acc->type_id = targ_id;
- targ_acc->idx = local_acc->idx;
- targ_acc->name = NULL;
- targ_spec->len++;
- targ_spec->raw_spec[targ_spec->raw_len] = targ_acc->idx;
- targ_spec->raw_len++;
-
- sz = btf__resolve_size(targ_btf, targ_id);
- if (sz < 0)
- return sz;
- targ_spec->bit_offset += local_acc->idx * sz * 8;
- }
- }
-
- return 1;
-}
-
-static int bpf_core_calc_field_relo(const struct bpf_program *prog,
- const struct bpf_core_relo *relo,
- const struct bpf_core_spec *spec,
- __u32 *val, __u32 *field_sz, __u32 *type_id,
- bool *validate)
-{
- const struct bpf_core_accessor *acc;
- const struct btf_type *t;
- __u32 byte_off, byte_sz, bit_off, bit_sz, field_type_id;
- const struct btf_member *m;
- const struct btf_type *mt;
- bool bitfield;
- __s64 sz;
-
- *field_sz = 0;
-
- if (relo->kind == BPF_FIELD_EXISTS) {
- *val = spec ? 1 : 0;
- return 0;
- }
-
- if (!spec)
- return -EUCLEAN; /* request instruction poisoning */
-
- acc = &spec->spec[spec->len - 1];
- t = btf__type_by_id(spec->btf, acc->type_id);
-
- /* a[n] accessor needs special handling */
- if (!acc->name) {
- if (relo->kind == BPF_FIELD_BYTE_OFFSET) {
- *val = spec->bit_offset / 8;
- /* remember field size for load/store mem size */
- sz = btf__resolve_size(spec->btf, acc->type_id);
- if (sz < 0)
- return -EINVAL;
- *field_sz = sz;
- *type_id = acc->type_id;
- } else if (relo->kind == BPF_FIELD_BYTE_SIZE) {
- sz = btf__resolve_size(spec->btf, acc->type_id);
- if (sz < 0)
- return -EINVAL;
- *val = sz;
- } else {
- pr_warn("prog '%s': relo %d at insn #%d can't be applied to array access\n",
- prog->name, relo->kind, relo->insn_off / 8);
- return -EINVAL;
- }
- if (validate)
- *validate = true;
- return 0;
- }
-
- m = btf_members(t) + acc->idx;
- mt = skip_mods_and_typedefs(spec->btf, m->type, &field_type_id);
- bit_off = spec->bit_offset;
- bit_sz = btf_member_bitfield_size(t, acc->idx);
-
- bitfield = bit_sz > 0;
- if (bitfield) {
- byte_sz = mt->size;
- byte_off = bit_off / 8 / byte_sz * byte_sz;
- /* figure out smallest int size necessary for bitfield load */
- while (bit_off + bit_sz - byte_off * 8 > byte_sz * 8) {
- if (byte_sz >= 8) {
- /* bitfield can't be read with 64-bit read */
- pr_warn("prog '%s': relo %d at insn #%d can't be satisfied for bitfield\n",
- prog->name, relo->kind, relo->insn_off / 8);
- return -E2BIG;
- }
- byte_sz *= 2;
- byte_off = bit_off / 8 / byte_sz * byte_sz;
- }
- } else {
- sz = btf__resolve_size(spec->btf, field_type_id);
- if (sz < 0)
- return -EINVAL;
- byte_sz = sz;
- byte_off = spec->bit_offset / 8;
- bit_sz = byte_sz * 8;
- }
-
- /* for bitfields, all the relocatable aspects are ambiguous and we
- * might disagree with compiler, so turn off validation of expected
- * value, except for signedness
- */
- if (validate)
- *validate = !bitfield;
-
- switch (relo->kind) {
- case BPF_FIELD_BYTE_OFFSET:
- *val = byte_off;
- if (!bitfield) {
- *field_sz = byte_sz;
- *type_id = field_type_id;
- }
- break;
- case BPF_FIELD_BYTE_SIZE:
- *val = byte_sz;
- break;
- case BPF_FIELD_SIGNED:
- /* enums will be assumed unsigned */
- *val = btf_is_enum(mt) ||
- (btf_int_encoding(mt) & BTF_INT_SIGNED);
- if (validate)
- *validate = true; /* signedness is never ambiguous */
- break;
- case BPF_FIELD_LSHIFT_U64:
-#if __BYTE_ORDER == __LITTLE_ENDIAN
- *val = 64 - (bit_off + bit_sz - byte_off * 8);
-#else
- *val = (8 - byte_sz) * 8 + (bit_off - byte_off * 8);
-#endif
- break;
- case BPF_FIELD_RSHIFT_U64:
- *val = 64 - bit_sz;
- if (validate)
- *validate = true; /* right shift is never ambiguous */
- break;
- case BPF_FIELD_EXISTS:
- default:
- return -EOPNOTSUPP;
- }
-
- return 0;
-}
-
-static int bpf_core_calc_type_relo(const struct bpf_core_relo *relo,
- const struct bpf_core_spec *spec,
- __u32 *val)
-{
- __s64 sz;
-
- /* type-based relos return zero when target type is not found */
- if (!spec) {
- *val = 0;
- return 0;
- }
-
- switch (relo->kind) {
- case BPF_TYPE_ID_TARGET:
- *val = spec->root_type_id;
- break;
- case BPF_TYPE_EXISTS:
- *val = 1;
- break;
- case BPF_TYPE_SIZE:
- sz = btf__resolve_size(spec->btf, spec->root_type_id);
- if (sz < 0)
- return -EINVAL;
- *val = sz;
- break;
- case BPF_TYPE_ID_LOCAL:
- /* BPF_TYPE_ID_LOCAL is handled specially and shouldn't get here */
- default:
- return -EOPNOTSUPP;
- }
-
- return 0;
-}
-
-static int bpf_core_calc_enumval_relo(const struct bpf_core_relo *relo,
- const struct bpf_core_spec *spec,
- __u32 *val)
-{
- const struct btf_type *t;
- const struct btf_enum *e;
-
- switch (relo->kind) {
- case BPF_ENUMVAL_EXISTS:
- *val = spec ? 1 : 0;
- break;
- case BPF_ENUMVAL_VALUE:
- if (!spec)
- return -EUCLEAN; /* request instruction poisoning */
- t = btf__type_by_id(spec->btf, spec->spec[0].type_id);
- e = btf_enum(t) + spec->spec[0].idx;
- *val = e->val;
- break;
- default:
- return -EOPNOTSUPP;
- }
-
- return 0;
-}
-
-struct bpf_core_relo_res
-{
- /* expected value in the instruction, unless validate == false */
- __u32 orig_val;
- /* new value that needs to be patched up to */
- __u32 new_val;
- /* relocation unsuccessful, poison instruction, but don't fail load */
- bool poison;
- /* some relocations can't be validated against orig_val */
- bool validate;
- /* for field byte offset relocations or the forms:
- * *(T *)(rX + <off>) = rY
- * rX = *(T *)(rY + <off>),
- * we remember original and resolved field size to adjust direct
- * memory loads of pointers and integers; this is necessary for 32-bit
- * host kernel architectures, but also allows to automatically
- * relocate fields that were resized from, e.g., u32 to u64, etc.
- */
- bool fail_memsz_adjust;
- __u32 orig_sz;
- __u32 orig_type_id;
- __u32 new_sz;
- __u32 new_type_id;
-};
-
-/* Calculate original and target relocation values, given local and target
- * specs and relocation kind. These values are calculated for each candidate.
- * If there are multiple candidates, resulting values should all be consistent
- * with each other. Otherwise, libbpf will refuse to proceed due to ambiguity.
- * If instruction has to be poisoned, *poison will be set to true.
- */
-static int bpf_core_calc_relo(const struct bpf_program *prog,
- const struct bpf_core_relo *relo,
- int relo_idx,
- const struct bpf_core_spec *local_spec,
- const struct bpf_core_spec *targ_spec,
- struct bpf_core_relo_res *res)
-{
- int err = -EOPNOTSUPP;
-
- res->orig_val = 0;
- res->new_val = 0;
- res->poison = false;
- res->validate = true;
- res->fail_memsz_adjust = false;
- res->orig_sz = res->new_sz = 0;
- res->orig_type_id = res->new_type_id = 0;
-
- if (core_relo_is_field_based(relo->kind)) {
- err = bpf_core_calc_field_relo(prog, relo, local_spec,
- &res->orig_val, &res->orig_sz,
- &res->orig_type_id, &res->validate);
- err = err ?: bpf_core_calc_field_relo(prog, relo, targ_spec,
- &res->new_val, &res->new_sz,
- &res->new_type_id, NULL);
- if (err)
- goto done;
- /* Validate if it's safe to adjust load/store memory size.
- * Adjustments are performed only if original and new memory
- * sizes differ.
- */
- res->fail_memsz_adjust = false;
- if (res->orig_sz != res->new_sz) {
- const struct btf_type *orig_t, *new_t;
-
- orig_t = btf__type_by_id(local_spec->btf, res->orig_type_id);
- new_t = btf__type_by_id(targ_spec->btf, res->new_type_id);
-
- /* There are two use cases in which it's safe to
- * adjust load/store's mem size:
- * - reading a 32-bit kernel pointer, while on BPF
- * size pointers are always 64-bit; in this case
- * it's safe to "downsize" instruction size due to
- * pointer being treated as unsigned integer with
- * zero-extended upper 32-bits;
- * - reading unsigned integers, again due to
- * zero-extension is preserving the value correctly.
- *
- * In all other cases it's incorrect to attempt to
- * load/store field because read value will be
- * incorrect, so we poison relocated instruction.
- */
- if (btf_is_ptr(orig_t) && btf_is_ptr(new_t))
- goto done;
- if (btf_is_int(orig_t) && btf_is_int(new_t) &&
- btf_int_encoding(orig_t) != BTF_INT_SIGNED &&
- btf_int_encoding(new_t) != BTF_INT_SIGNED)
- goto done;
-
- /* mark as invalid mem size adjustment, but this will
- * only be checked for LDX/STX/ST insns
- */
- res->fail_memsz_adjust = true;
- }
- } else if (core_relo_is_type_based(relo->kind)) {
- err = bpf_core_calc_type_relo(relo, local_spec, &res->orig_val);
- err = err ?: bpf_core_calc_type_relo(relo, targ_spec, &res->new_val);
- } else if (core_relo_is_enumval_based(relo->kind)) {
- err = bpf_core_calc_enumval_relo(relo, local_spec, &res->orig_val);
- err = err ?: bpf_core_calc_enumval_relo(relo, targ_spec, &res->new_val);
- }
-
-done:
- if (err == -EUCLEAN) {
- /* EUCLEAN is used to signal instruction poisoning request */
- res->poison = true;
- err = 0;
- } else if (err == -EOPNOTSUPP) {
- /* EOPNOTSUPP means unknown/unsupported relocation */
- pr_warn("prog '%s': relo #%d: unrecognized CO-RE relocation %s (%d) at insn #%d\n",
- prog->name, relo_idx, core_relo_kind_str(relo->kind),
- relo->kind, relo->insn_off / 8);
- }
-
- return err;
-}
-
-/*
- * Turn instruction for which CO_RE relocation failed into invalid one with
- * distinct signature.
- */
-static void bpf_core_poison_insn(struct bpf_program *prog, int relo_idx,
- int insn_idx, struct bpf_insn *insn)
-{
- pr_debug("prog '%s': relo #%d: substituting insn #%d w/ invalid insn\n",
- prog->name, relo_idx, insn_idx);
- insn->code = BPF_JMP | BPF_CALL;
- insn->dst_reg = 0;
- insn->src_reg = 0;
- insn->off = 0;
- /* if this instruction is reachable (not a dead code),
- * verifier will complain with the following message:
- * invalid func unknown#195896080
- */
- insn->imm = 195896080; /* => 0xbad2310 => "bad relo" */
-}
-
-static int insn_bpf_size_to_bytes(struct bpf_insn *insn)
-{
- switch (BPF_SIZE(insn->code)) {
- case BPF_DW: return 8;
- case BPF_W: return 4;
- case BPF_H: return 2;
- case BPF_B: return 1;
- default: return -1;
- }
-}
-
-static int insn_bytes_to_bpf_size(__u32 sz)
-{
- switch (sz) {
- case 8: return BPF_DW;
- case 4: return BPF_W;
- case 2: return BPF_H;
- case 1: return BPF_B;
- default: return -1;
- }
-}
-
-/*
- * Patch relocatable BPF instruction.
- *
- * Patched value is determined by relocation kind and target specification.
- * For existence relocations target spec will be NULL if field/type is not found.
- * Expected insn->imm value is determined using relocation kind and local
- * spec, and is checked before patching instruction. If actual insn->imm value
- * is wrong, bail out with error.
- *
- * Currently supported classes of BPF instruction are:
- * 1. rX = <imm> (assignment with immediate operand);
- * 2. rX += <imm> (arithmetic operations with immediate operand);
- * 3. rX = <imm64> (load with 64-bit immediate value);
- * 4. rX = *(T *)(rY + <off>), where T is one of {u8, u16, u32, u64};
- * 5. *(T *)(rX + <off>) = rY, where T is one of {u8, u16, u32, u64};
- * 6. *(T *)(rX + <off>) = <imm>, where T is one of {u8, u16, u32, u64}.
- */
-static int bpf_core_patch_insn(struct bpf_program *prog,
- const struct bpf_core_relo *relo,
- int relo_idx,
- const struct bpf_core_relo_res *res)
-{
- __u32 orig_val, new_val;
- struct bpf_insn *insn;
- int insn_idx;
- __u8 class;
-
- if (relo->insn_off % BPF_INSN_SZ)
- return -EINVAL;
- insn_idx = relo->insn_off / BPF_INSN_SZ;
- /* adjust insn_idx from section frame of reference to the local
- * program's frame of reference; (sub-)program code is not yet
- * relocated, so it's enough to just subtract in-section offset
- */
- insn_idx = insn_idx - prog->sec_insn_off;
- insn = &prog->insns[insn_idx];
- class = BPF_CLASS(insn->code);
-
- if (res->poison) {
-poison:
- /* poison second part of ldimm64 to avoid confusing error from
- * verifier about "unknown opcode 00"
- */
- if (is_ldimm64_insn(insn))
- bpf_core_poison_insn(prog, relo_idx, insn_idx + 1, insn + 1);
- bpf_core_poison_insn(prog, relo_idx, insn_idx, insn);
- return 0;
- }
-
- orig_val = res->orig_val;
- new_val = res->new_val;
-
- switch (class) {
- case BPF_ALU:
- case BPF_ALU64:
- if (BPF_SRC(insn->code) != BPF_K)
- return -EINVAL;
- if (res->validate && insn->imm != orig_val) {
- pr_warn("prog '%s': relo #%d: unexpected insn #%d (ALU/ALU64) value: got %u, exp %u -> %u\n",
- prog->name, relo_idx,
- insn_idx, insn->imm, orig_val, new_val);
- return -EINVAL;
- }
- orig_val = insn->imm;
- insn->imm = new_val;
- pr_debug("prog '%s': relo #%d: patched insn #%d (ALU/ALU64) imm %u -> %u\n",
- prog->name, relo_idx, insn_idx,
- orig_val, new_val);
- break;
- case BPF_LDX:
- case BPF_ST:
- case BPF_STX:
- if (res->validate && insn->off != orig_val) {
- pr_warn("prog '%s': relo #%d: unexpected insn #%d (LDX/ST/STX) value: got %u, exp %u -> %u\n",
- prog->name, relo_idx, insn_idx, insn->off, orig_val, new_val);
- return -EINVAL;
- }
- if (new_val > SHRT_MAX) {
- pr_warn("prog '%s': relo #%d: insn #%d (LDX/ST/STX) value too big: %u\n",
- prog->name, relo_idx, insn_idx, new_val);
- return -ERANGE;
- }
- if (res->fail_memsz_adjust) {
- pr_warn("prog '%s': relo #%d: insn #%d (LDX/ST/STX) accesses field incorrectly. "
- "Make sure you are accessing pointers, unsigned integers, or fields of matching type and size.\n",
- prog->name, relo_idx, insn_idx);
- goto poison;
- }
-
- orig_val = insn->off;
- insn->off = new_val;
- pr_debug("prog '%s': relo #%d: patched insn #%d (LDX/ST/STX) off %u -> %u\n",
- prog->name, relo_idx, insn_idx, orig_val, new_val);
-
- if (res->new_sz != res->orig_sz) {
- int insn_bytes_sz, insn_bpf_sz;
-
- insn_bytes_sz = insn_bpf_size_to_bytes(insn);
- if (insn_bytes_sz != res->orig_sz) {
- pr_warn("prog '%s': relo #%d: insn #%d (LDX/ST/STX) unexpected mem size: got %d, exp %u\n",
- prog->name, relo_idx, insn_idx, insn_bytes_sz, res->orig_sz);
- return -EINVAL;
- }
-
- insn_bpf_sz = insn_bytes_to_bpf_size(res->new_sz);
- if (insn_bpf_sz < 0) {
- pr_warn("prog '%s': relo #%d: insn #%d (LDX/ST/STX) invalid new mem size: %u\n",
- prog->name, relo_idx, insn_idx, res->new_sz);
- return -EINVAL;
- }
-
- insn->code = BPF_MODE(insn->code) | insn_bpf_sz | BPF_CLASS(insn->code);
- pr_debug("prog '%s': relo #%d: patched insn #%d (LDX/ST/STX) mem_sz %u -> %u\n",
- prog->name, relo_idx, insn_idx, res->orig_sz, res->new_sz);
- }
- break;
- case BPF_LD: {
- __u64 imm;
-
- if (!is_ldimm64_insn(insn) ||
- insn[0].src_reg != 0 || insn[0].off != 0 ||
- insn_idx + 1 >= prog->insns_cnt ||
- insn[1].code != 0 || insn[1].dst_reg != 0 ||
- insn[1].src_reg != 0 || insn[1].off != 0) {
- pr_warn("prog '%s': relo #%d: insn #%d (LDIMM64) has unexpected form\n",
- prog->name, relo_idx, insn_idx);
- return -EINVAL;
- }
-
- imm = insn[0].imm + ((__u64)insn[1].imm << 32);
- if (res->validate && imm != orig_val) {
- pr_warn("prog '%s': relo #%d: unexpected insn #%d (LDIMM64) value: got %llu, exp %u -> %u\n",
- prog->name, relo_idx,
- insn_idx, (unsigned long long)imm,
- orig_val, new_val);
- return -EINVAL;
- }
-
- insn[0].imm = new_val;
- insn[1].imm = 0; /* currently only 32-bit values are supported */
- pr_debug("prog '%s': relo #%d: patched insn #%d (LDIMM64) imm64 %llu -> %u\n",
- prog->name, relo_idx, insn_idx,
- (unsigned long long)imm, new_val);
- break;
- }
- default:
- pr_warn("prog '%s': relo #%d: trying to relocate unrecognized insn #%d, code:0x%x, src:0x%x, dst:0x%x, off:0x%x, imm:0x%x\n",
- prog->name, relo_idx, insn_idx, insn->code,
- insn->src_reg, insn->dst_reg, insn->off, insn->imm);
- return -EINVAL;
- }
-
- return 0;
-}
-
-/* Output spec definition in the format:
- * [<type-id>] (<type-name>) + <raw-spec> => <offset>@<spec>,
- * where <spec> is a C-syntax view of recorded field access, e.g.: x.a[3].b
- */
-static void bpf_core_dump_spec(int level, const struct bpf_core_spec *spec)
-{
- const struct btf_type *t;
- const struct btf_enum *e;
- const char *s;
- __u32 type_id;
- int i;
-
- type_id = spec->root_type_id;
- t = btf__type_by_id(spec->btf, type_id);
- s = btf__name_by_offset(spec->btf, t->name_off);
-
- libbpf_print(level, "[%u] %s %s", type_id, btf_kind_str(t), str_is_empty(s) ? "<anon>" : s);
-
- if (core_relo_is_type_based(spec->relo_kind))
- return;
-
- if (core_relo_is_enumval_based(spec->relo_kind)) {
- t = skip_mods_and_typedefs(spec->btf, type_id, NULL);
- e = btf_enum(t) + spec->raw_spec[0];
- s = btf__name_by_offset(spec->btf, e->name_off);
-
- libbpf_print(level, "::%s = %u", s, e->val);
- return;
- }
-
- if (core_relo_is_field_based(spec->relo_kind)) {
- for (i = 0; i < spec->len; i++) {
- if (spec->spec[i].name)
- libbpf_print(level, ".%s", spec->spec[i].name);
- else if (i > 0 || spec->spec[i].idx > 0)
- libbpf_print(level, "[%u]", spec->spec[i].idx);
- }
-
- libbpf_print(level, " (");
- for (i = 0; i < spec->raw_len; i++)
- libbpf_print(level, "%s%d", i == 0 ? "" : ":", spec->raw_spec[i]);
-
- if (spec->bit_offset % 8)
- libbpf_print(level, " @ offset %u.%u)",
- spec->bit_offset / 8, spec->bit_offset % 8);
- else
- libbpf_print(level, " @ offset %u)", spec->bit_offset / 8);
- return;
- }
-}
-
static size_t bpf_core_hash_fn(const void *key, void *ctx)
{
return (size_t)key;
@@ -6130,73 +5109,33 @@ static void *u32_as_hash_key(__u32 x)
return (void *)(uintptr_t)x;
}
-/*
- * CO-RE relocate single instruction.
- *
- * The outline and important points of the algorithm:
- * 1. For given local type, find corresponding candidate target types.
- * Candidate type is a type with the same "essential" name, ignoring
- * everything after last triple underscore (___). E.g., `sample`,
- * `sample___flavor_one`, `sample___flavor_another_one`, are all candidates
- * for each other. Names with triple underscore are referred to as
- * "flavors" and are useful, among other things, to allow to
- * specify/support incompatible variations of the same kernel struct, which
- * might differ between different kernel versions and/or build
- * configurations.
- *
- * N.B. Struct "flavors" could be generated by bpftool's BTF-to-C
- * converter, when deduplicated BTF of a kernel still contains more than
- * one different types with the same name. In that case, ___2, ___3, etc
- * are appended starting from second name conflict. But start flavors are
- * also useful to be defined "locally", in BPF program, to extract same
- * data from incompatible changes between different kernel
- * versions/configurations. For instance, to handle field renames between
- * kernel versions, one can use two flavors of the struct name with the
- * same common name and use conditional relocations to extract that field,
- * depending on target kernel version.
- * 2. For each candidate type, try to match local specification to this
- * candidate target type. Matching involves finding corresponding
- * high-level spec accessors, meaning that all named fields should match,
- * as well as all array accesses should be within the actual bounds. Also,
- * types should be compatible (see bpf_core_fields_are_compat for details).
- * 3. It is supported and expected that there might be multiple flavors
- * matching the spec. As long as all the specs resolve to the same set of
- * offsets across all candidates, there is no error. If there is any
- * ambiguity, CO-RE relocation will fail. This is necessary to accomodate
- * imprefection of BTF deduplication, which can cause slight duplication of
- * the same BTF type, if some directly or indirectly referenced (by
- * pointer) type gets resolved to different actual types in different
- * object files. If such situation occurs, deduplicated BTF will end up
- * with two (or more) structurally identical types, which differ only in
- * types they refer to through pointer. This should be OK in most cases and
- * is not an error.
- * 4. Candidate types search is performed by linearly scanning through all
- * types in target BTF. It is anticipated that this is overall more
- * efficient memory-wise and not significantly worse (if not better)
- * CPU-wise compared to prebuilding a map from all local type names to
- * a list of candidate type names. It's also sped up by caching resolved
- * list of matching candidates per each local "root" type ID, that has at
- * least one bpf_core_relo associated with it. This list is shared
- * between multiple relocations for the same type ID and is updated as some
- * of the candidates are pruned due to structural incompatibility.
- */
static int bpf_core_apply_relo(struct bpf_program *prog,
const struct bpf_core_relo *relo,
int relo_idx,
const struct btf *local_btf,
struct hashmap *cand_cache)
{
- struct bpf_core_spec local_spec, cand_spec, targ_spec = {};
const void *type_key = u32_as_hash_key(relo->type_id);
- struct bpf_core_relo_res cand_res, targ_res;
+ struct bpf_core_cand_list *cands = NULL;
+ const char *prog_name = prog->name;
const struct btf_type *local_type;
const char *local_name;
- struct core_cand_list *cands = NULL;
- __u32 local_id;
- const char *spec_str;
- int i, j, err;
+ __u32 local_id = relo->type_id;
+ struct bpf_insn *insn;
+ int insn_idx, err;
+
+ if (relo->insn_off % BPF_INSN_SZ)
+ return -EINVAL;
+ insn_idx = relo->insn_off / BPF_INSN_SZ;
+ /* adjust insn_idx from section frame of reference to the local
+ * program's frame of reference; (sub-)program code is not yet
+ * relocated, so it's enough to just subtract in-section offset
+ */
+ insn_idx = insn_idx - prog->sec_insn_off;
+ if (insn_idx > prog->insns_cnt)
+ return -EINVAL;
+ insn = &prog->insns[insn_idx];
- local_id = relo->type_id;
local_type = btf__type_by_id(local_btf, local_id);
if (!local_type)
return -EINVAL;
@@ -6205,51 +5144,19 @@ static int bpf_core_apply_relo(struct bpf_program *prog,
if (!local_name)
return -EINVAL;
- spec_str = btf__name_by_offset(local_btf, relo->access_str_off);
- if (str_is_empty(spec_str))
- return -EINVAL;
-
if (prog->obj->gen_loader) {
- pr_warn("// TODO core_relo: prog %td insn[%d] %s %s kind %d\n",
+ pr_warn("// TODO core_relo: prog %td insn[%d] %s kind %d\n",
prog - prog->obj->programs, relo->insn_off / 8,
- local_name, spec_str, relo->kind);
+ local_name, relo->kind);
return -ENOTSUP;
}
- err = bpf_core_parse_spec(local_btf, local_id, spec_str, relo->kind, &local_spec);
- if (err) {
- pr_warn("prog '%s': relo #%d: parsing [%d] %s %s + %s failed: %d\n",
- prog->name, relo_idx, local_id, btf_kind_str(local_type),
- str_is_empty(local_name) ? "<anon>" : local_name,
- spec_str, err);
- return -EINVAL;
- }
-
- pr_debug("prog '%s': relo #%d: kind <%s> (%d), spec is ", prog->name,
- relo_idx, core_relo_kind_str(relo->kind), relo->kind);
- bpf_core_dump_spec(LIBBPF_DEBUG, &local_spec);
- libbpf_print(LIBBPF_DEBUG, "\n");
- /* TYPE_ID_LOCAL relo is special and doesn't need candidate search */
- if (relo->kind == BPF_TYPE_ID_LOCAL) {
- targ_res.validate = true;
- targ_res.poison = false;
- targ_res.orig_val = local_spec.root_type_id;
- targ_res.new_val = local_spec.root_type_id;
- goto patch_insn;
- }
-
- /* libbpf doesn't support candidate search for anonymous types */
- if (str_is_empty(spec_str)) {
- pr_warn("prog '%s': relo #%d: <%s> (%d) relocation doesn't support anonymous types\n",
- prog->name, relo_idx, core_relo_kind_str(relo->kind), relo->kind);
- return -EOPNOTSUPP;
- }
-
- if (!hashmap__find(cand_cache, type_key, (void **)&cands)) {
+ if (relo->kind != BPF_TYPE_ID_LOCAL &&
+ !hashmap__find(cand_cache, type_key, (void **)&cands)) {
cands = bpf_core_find_cands(prog->obj, local_btf, local_id);
if (IS_ERR(cands)) {
pr_warn("prog '%s': relo #%d: target candidate search failed for [%d] %s %s: %ld\n",
- prog->name, relo_idx, local_id, btf_kind_str(local_type),
+ prog_name, relo_idx, local_id, btf_kind_str(local_type),
local_name, PTR_ERR(cands));
return PTR_ERR(cands);
}
@@ -6260,97 +5167,7 @@ static int bpf_core_apply_relo(struct bpf_program *prog,
}
}
- for (i = 0, j = 0; i < cands->len; i++) {
- err = bpf_core_spec_match(&local_spec, cands->cands[i].btf,
- cands->cands[i].id, &cand_spec);
- if (err < 0) {
- pr_warn("prog '%s': relo #%d: error matching candidate #%d ",
- prog->name, relo_idx, i);
- bpf_core_dump_spec(LIBBPF_WARN, &cand_spec);
- libbpf_print(LIBBPF_WARN, ": %d\n", err);
- return err;
- }
-
- pr_debug("prog '%s': relo #%d: %s candidate #%d ", prog->name,
- relo_idx, err == 0 ? "non-matching" : "matching", i);
- bpf_core_dump_spec(LIBBPF_DEBUG, &cand_spec);
- libbpf_print(LIBBPF_DEBUG, "\n");
-
- if (err == 0)
- continue;
-
- err = bpf_core_calc_relo(prog, relo, relo_idx, &local_spec, &cand_spec, &cand_res);
- if (err)
- return err;
-
- if (j == 0) {
- targ_res = cand_res;
- targ_spec = cand_spec;
- } else if (cand_spec.bit_offset != targ_spec.bit_offset) {
- /* if there are many field relo candidates, they
- * should all resolve to the same bit offset
- */
- pr_warn("prog '%s': relo #%d: field offset ambiguity: %u != %u\n",
- prog->name, relo_idx, cand_spec.bit_offset,
- targ_spec.bit_offset);
- return -EINVAL;
- } else if (cand_res.poison != targ_res.poison || cand_res.new_val != targ_res.new_val) {
- /* all candidates should result in the same relocation
- * decision and value, otherwise it's dangerous to
- * proceed due to ambiguity
- */
- pr_warn("prog '%s': relo #%d: relocation decision ambiguity: %s %u != %s %u\n",
- prog->name, relo_idx,
- cand_res.poison ? "failure" : "success", cand_res.new_val,
- targ_res.poison ? "failure" : "success", targ_res.new_val);
- return -EINVAL;
- }
-
- cands->cands[j++] = cands->cands[i];
- }
-
- /*
- * For BPF_FIELD_EXISTS relo or when used BPF program has field
- * existence checks or kernel version/config checks, it's expected
- * that we might not find any candidates. In this case, if field
- * wasn't found in any candidate, the list of candidates shouldn't
- * change at all, we'll just handle relocating appropriately,
- * depending on relo's kind.
- */
- if (j > 0)
- cands->len = j;
-
- /*
- * If no candidates were found, it might be both a programmer error,
- * as well as expected case, depending whether instruction w/
- * relocation is guarded in some way that makes it unreachable (dead
- * code) if relocation can't be resolved. This is handled in
- * bpf_core_patch_insn() uniformly by replacing that instruction with
- * BPF helper call insn (using invalid helper ID). If that instruction
- * is indeed unreachable, then it will be ignored and eliminated by
- * verifier. If it was an error, then verifier will complain and point
- * to a specific instruction number in its log.
- */
- if (j == 0) {
- pr_debug("prog '%s': relo #%d: no matching targets found\n",
- prog->name, relo_idx);
-
- /* calculate single target relo result explicitly */
- err = bpf_core_calc_relo(prog, relo, relo_idx, &local_spec, NULL, &targ_res);
- if (err)
- return err;
- }
-
-patch_insn:
- /* bpf_core_patch_insn() should know how to handle missing targ_spec */
- err = bpf_core_patch_insn(prog, relo, relo_idx, &targ_res);
- if (err) {
- pr_warn("prog '%s': relo #%d: failed to patch insn #%zu: %d\n",
- prog->name, relo_idx, relo->insn_off / BPF_INSN_SZ, err);
- return -EINVAL;
- }
-
- return 0;
+ return bpf_core_apply_relo_insn(prog_name, insn, insn_idx, relo, relo_idx, local_btf, cands);
}
static int
@@ -6496,11 +5313,11 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog)
}
insn[1].imm = ext->kcfg.data_off;
} else /* EXT_KSYM */ {
- if (ext->ksym.type_id) { /* typed ksyms */
+ if (ext->ksym.type_id && ext->is_set) { /* typed ksyms */
insn[0].src_reg = BPF_PSEUDO_BTF_ID;
insn[0].imm = ext->ksym.kernel_btf_id;
insn[1].imm = ext->ksym.kernel_btf_obj_fd;
- } else { /* typeless ksyms */
+ } else { /* typeless ksyms or unresolved typed ksyms */
insn[0].imm = (__u32)ext->ksym.addr;
insn[1].imm = ext->ksym.addr >> 32;
}
@@ -7190,7 +6007,7 @@ static int bpf_object__collect_relos(struct bpf_object *obj)
for (i = 0; i < obj->nr_programs; i++) {
struct bpf_program *p = &obj->programs[i];
-
+
if (!p->nr_reloc)
continue;
@@ -7554,7 +6371,7 @@ static struct bpf_object *
__bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
const struct bpf_object_open_opts *opts)
{
- const char *obj_name, *kconfig;
+ const char *obj_name, *kconfig, *btf_tmp_path;
struct bpf_program *prog;
struct bpf_object *obj;
char tmp_name[64];
@@ -7585,11 +6402,26 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
if (IS_ERR(obj))
return obj;
+ btf_tmp_path = OPTS_GET(opts, btf_custom_path, NULL);
+ if (btf_tmp_path) {
+ if (strlen(btf_tmp_path) >= PATH_MAX) {
+ err = -ENAMETOOLONG;
+ goto out;
+ }
+ obj->btf_custom_path = strdup(btf_tmp_path);
+ if (!obj->btf_custom_path) {
+ err = -ENOMEM;
+ goto out;
+ }
+ }
+
kconfig = OPTS_GET(opts, kconfig, NULL);
if (kconfig) {
obj->kconfig = strdup(kconfig);
- if (!obj->kconfig)
- return ERR_PTR(-ENOMEM);
+ if (!obj->kconfig) {
+ err = -ENOMEM;
+ goto out;
+ }
}
err = bpf_object__elf_init(obj);
@@ -7812,11 +6644,8 @@ static int find_ksym_btf_id(struct bpf_object *obj, const char *ksym_name,
break;
}
}
- if (id <= 0) {
- pr_warn("extern (%s ksym) '%s': failed to find BTF ID in kernel BTF(s).\n",
- __btf_kind_str(kind), ksym_name);
+ if (id <= 0)
return -ESRCH;
- }
*res_btf = btf;
*res_btf_fd = btf_fd;
@@ -7833,8 +6662,13 @@ static int bpf_object__resolve_ksym_var_btf_id(struct bpf_object *obj,
struct btf *btf = NULL;
id = find_ksym_btf_id(obj, ext->name, BTF_KIND_VAR, &btf, &btf_fd);
- if (id < 0)
+ if (id == -ESRCH && ext->is_weak) {
+ return 0;
+ } else if (id < 0) {
+ pr_warn("extern (var ksym) '%s': not found in kernel BTF\n",
+ ext->name);
return id;
+ }
/* find local type_id */
local_type_id = ext->ksym.type_id;
@@ -8055,7 +6889,7 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr)
err = err ? : bpf_object__sanitize_maps(obj);
err = err ? : bpf_object__init_kern_struct_ops_maps(obj);
err = err ? : bpf_object__create_maps(obj);
- err = err ? : bpf_object__relocate(obj, attr->target_btf_path);
+ err = err ? : bpf_object__relocate(obj, obj->btf_custom_path ? : attr->target_btf_path);
err = err ? : bpf_object__load_progs(obj, attr->log_level);
if (obj->gen_loader) {
@@ -8450,6 +7284,11 @@ const char *bpf_map__get_pin_path(const struct bpf_map *map)
return map->pin_path;
}
+const char *bpf_map__pin_path(const struct bpf_map *map)
+{
+ return map->pin_path;
+}
+
bool bpf_map__is_pinned(const struct bpf_map *map)
{
return map->pinned;
@@ -8702,6 +7541,7 @@ void bpf_object__close(struct bpf_object *obj)
for (i = 0; i < obj->nr_maps; i++)
bpf_map__destroy(&obj->maps[i]);
+ zfree(&obj->btf_custom_path);
zfree(&obj->kconfig);
zfree(&obj->externs);
obj->nr_extern = 0;
@@ -9471,7 +8311,7 @@ static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix,
ret = snprintf(btf_type_name, sizeof(btf_type_name),
"%s%s", prefix, name);
/* snprintf returns the number of characters written excluding the
- * the terminating null. So, if >= BTF_MAX_NAME_SIZE are written, it
+ * terminating null. So, if >= BTF_MAX_NAME_SIZE are written, it
* indicates truncation.
*/
if (ret < 0 || ret >= sizeof(btf_type_name))
@@ -9495,7 +8335,7 @@ int libbpf_find_vmlinux_btf_id(const char *name,
struct btf *btf;
int err;
- btf = libbpf_find_kernel_btf();
+ btf = btf__load_vmlinux_btf();
err = libbpf_get_error(btf);
if (err) {
pr_warn("vmlinux BTF is not found\n");
@@ -9514,8 +8354,8 @@ static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd)
{
struct bpf_prog_info_linear *info_linear;
struct bpf_prog_info *info;
- struct btf *btf = NULL;
- int err = -EINVAL;
+ struct btf *btf;
+ int err;
info_linear = bpf_program__get_prog_info_linear(attach_prog_fd, 0);
err = libbpf_get_error(info_linear);
@@ -9524,12 +8364,15 @@ static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd)
attach_prog_fd);
return err;
}
+
+ err = -EINVAL;
info = &info_linear->info;
if (!info->btf_id) {
pr_warn("The target program doesn't have BTF\n");
goto out;
}
- if (btf__get_from_id(info->btf_id, &btf)) {
+ btf = btf__load_from_kernel_by_id(info->btf_id);
+ if (libbpf_get_error(btf)) {
pr_warn("Failed to get BTF of the program\n");
goto out;
}
@@ -10003,7 +8846,7 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
struct bpf_link {
int (*detach)(struct bpf_link *link);
- int (*destroy)(struct bpf_link *link);
+ void (*dealloc)(struct bpf_link *link);
char *pin_path; /* NULL, if not pinned */
int fd; /* hook FD, -1 if not applicable */
bool disconnected;
@@ -10013,7 +8856,7 @@ struct bpf_link {
int bpf_link__update_program(struct bpf_link *link, struct bpf_program *prog)
{
int ret;
-
+
ret = bpf_link_update(bpf_link__fd(link), bpf_program__fd(prog), NULL);
return libbpf_err_errno(ret);
}
@@ -10042,11 +8885,12 @@ int bpf_link__destroy(struct bpf_link *link)
if (!link->disconnected && link->detach)
err = link->detach(link);
- if (link->destroy)
- link->destroy(link);
if (link->pin_path)
free(link->pin_path);
- free(link);
+ if (link->dealloc)
+ link->dealloc(link);
+ else
+ free(link);
return libbpf_err(err);
}
@@ -10143,23 +8987,42 @@ int bpf_link__unpin(struct bpf_link *link)
return 0;
}
-static int bpf_link__detach_perf_event(struct bpf_link *link)
+struct bpf_link_perf {
+ struct bpf_link link;
+ int perf_event_fd;
+};
+
+static int bpf_link_perf_detach(struct bpf_link *link)
{
- int err;
+ struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link);
+ int err = 0;
- err = ioctl(link->fd, PERF_EVENT_IOC_DISABLE, 0);
- if (err)
+ if (ioctl(perf_link->perf_event_fd, PERF_EVENT_IOC_DISABLE, 0) < 0)
err = -errno;
+ if (perf_link->perf_event_fd != link->fd)
+ close(perf_link->perf_event_fd);
close(link->fd);
+
return libbpf_err(err);
}
-struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog, int pfd)
+static void bpf_link_perf_dealloc(struct bpf_link *link)
+{
+ struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link);
+
+ free(perf_link);
+}
+
+struct bpf_link *bpf_program__attach_perf_event_opts(struct bpf_program *prog, int pfd,
+ const struct bpf_perf_event_opts *opts)
{
char errmsg[STRERR_BUFSIZE];
- struct bpf_link *link;
- int prog_fd, err;
+ struct bpf_link_perf *link;
+ int prog_fd, link_fd = -1, err;
+
+ if (!OPTS_VALID(opts, bpf_perf_event_opts))
+ return libbpf_err_ptr(-EINVAL);
if (pfd < 0) {
pr_warn("prog '%s': invalid perf event FD %d\n",
@@ -10176,27 +9039,59 @@ struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog, int pf
link = calloc(1, sizeof(*link));
if (!link)
return libbpf_err_ptr(-ENOMEM);
- link->detach = &bpf_link__detach_perf_event;
- link->fd = pfd;
+ link->link.detach = &bpf_link_perf_detach;
+ link->link.dealloc = &bpf_link_perf_dealloc;
+ link->perf_event_fd = pfd;
- if (ioctl(pfd, PERF_EVENT_IOC_SET_BPF, prog_fd) < 0) {
- err = -errno;
- free(link);
- pr_warn("prog '%s': failed to attach to pfd %d: %s\n",
- prog->name, pfd, libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
- if (err == -EPROTO)
- pr_warn("prog '%s': try add PERF_SAMPLE_CALLCHAIN to or remove exclude_callchain_[kernel|user] from pfd %d\n",
- prog->name, pfd);
- return libbpf_err_ptr(err);
+ if (kernel_supports(prog->obj, FEAT_PERF_LINK)) {
+ DECLARE_LIBBPF_OPTS(bpf_link_create_opts, link_opts,
+ .perf_event.bpf_cookie = OPTS_GET(opts, bpf_cookie, 0));
+
+ link_fd = bpf_link_create(prog_fd, pfd, BPF_PERF_EVENT, &link_opts);
+ if (link_fd < 0) {
+ err = -errno;
+ pr_warn("prog '%s': failed to create BPF link for perf_event FD %d: %d (%s)\n",
+ prog->name, pfd,
+ err, libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+ goto err_out;
+ }
+ link->link.fd = link_fd;
+ } else {
+ if (OPTS_GET(opts, bpf_cookie, 0)) {
+ pr_warn("prog '%s': user context value is not supported\n", prog->name);
+ err = -EOPNOTSUPP;
+ goto err_out;
+ }
+
+ if (ioctl(pfd, PERF_EVENT_IOC_SET_BPF, prog_fd) < 0) {
+ err = -errno;
+ pr_warn("prog '%s': failed to attach to perf_event FD %d: %s\n",
+ prog->name, pfd, libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+ if (err == -EPROTO)
+ pr_warn("prog '%s': try add PERF_SAMPLE_CALLCHAIN to or remove exclude_callchain_[kernel|user] from pfd %d\n",
+ prog->name, pfd);
+ goto err_out;
+ }
+ link->link.fd = pfd;
}
if (ioctl(pfd, PERF_EVENT_IOC_ENABLE, 0) < 0) {
err = -errno;
- free(link);
- pr_warn("prog '%s': failed to enable pfd %d: %s\n",
+ pr_warn("prog '%s': failed to enable perf_event FD %d: %s\n",
prog->name, pfd, libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
- return libbpf_err_ptr(err);
+ goto err_out;
}
- return link;
+
+ return &link->link;
+err_out:
+ if (link_fd >= 0)
+ close(link_fd);
+ free(link);
+ return libbpf_err_ptr(err);
+}
+
+struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog, int pfd)
+{
+ return bpf_program__attach_perf_event_opts(prog, pfd, NULL);
}
/*
@@ -10257,13 +9152,19 @@ static int determine_uprobe_retprobe_bit(void)
return parse_uint_from_file(file, "config:%d\n");
}
+#define PERF_UPROBE_REF_CTR_OFFSET_BITS 32
+#define PERF_UPROBE_REF_CTR_OFFSET_SHIFT 32
+
static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name,
- uint64_t offset, int pid)
+ uint64_t offset, int pid, size_t ref_ctr_off)
{
struct perf_event_attr attr = {};
char errmsg[STRERR_BUFSIZE];
int type, pfd, err;
+ if (ref_ctr_off >= (1ULL << PERF_UPROBE_REF_CTR_OFFSET_BITS))
+ return -EINVAL;
+
type = uprobe ? determine_uprobe_perf_type()
: determine_kprobe_perf_type();
if (type < 0) {
@@ -10286,6 +9187,7 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name,
}
attr.size = sizeof(attr);
attr.type = type;
+ attr.config |= (__u64)ref_ctr_off << PERF_UPROBE_REF_CTR_OFFSET_SHIFT;
attr.config1 = ptr_to_u64(name); /* kprobe_func or uprobe_path */
attr.config2 = offset; /* kprobe_addr or probe_offset */
@@ -10304,23 +9206,34 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name,
return pfd;
}
-struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog,
- bool retprobe,
- const char *func_name)
+struct bpf_link *
+bpf_program__attach_kprobe_opts(struct bpf_program *prog,
+ const char *func_name,
+ const struct bpf_kprobe_opts *opts)
{
+ DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts);
char errmsg[STRERR_BUFSIZE];
struct bpf_link *link;
+ unsigned long offset;
+ bool retprobe;
int pfd, err;
+ if (!OPTS_VALID(opts, bpf_kprobe_opts))
+ return libbpf_err_ptr(-EINVAL);
+
+ retprobe = OPTS_GET(opts, retprobe, false);
+ offset = OPTS_GET(opts, offset, 0);
+ pe_opts.bpf_cookie = OPTS_GET(opts, bpf_cookie, 0);
+
pfd = perf_event_open_probe(false /* uprobe */, retprobe, func_name,
- 0 /* offset */, -1 /* pid */);
+ offset, -1 /* pid */, 0 /* ref_ctr_off */);
if (pfd < 0) {
pr_warn("prog '%s': failed to create %s '%s' perf event: %s\n",
prog->name, retprobe ? "kretprobe" : "kprobe", func_name,
libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
return libbpf_err_ptr(pfd);
}
- link = bpf_program__attach_perf_event(prog, pfd);
+ link = bpf_program__attach_perf_event_opts(prog, pfd, &pe_opts);
err = libbpf_get_error(link);
if (err) {
close(pfd);
@@ -10332,29 +9245,70 @@ struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog,
return link;
}
+struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog,
+ bool retprobe,
+ const char *func_name)
+{
+ DECLARE_LIBBPF_OPTS(bpf_kprobe_opts, opts,
+ .retprobe = retprobe,
+ );
+
+ return bpf_program__attach_kprobe_opts(prog, func_name, &opts);
+}
+
static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec,
struct bpf_program *prog)
{
+ DECLARE_LIBBPF_OPTS(bpf_kprobe_opts, opts);
+ unsigned long offset = 0;
+ struct bpf_link *link;
const char *func_name;
- bool retprobe;
+ char *func;
+ int n, err;
func_name = prog->sec_name + sec->len;
- retprobe = strcmp(sec->sec, "kretprobe/") == 0;
+ opts.retprobe = strcmp(sec->sec, "kretprobe/") == 0;
+
+ n = sscanf(func_name, "%m[a-zA-Z0-9_.]+%li", &func, &offset);
+ if (n < 1) {
+ err = -EINVAL;
+ pr_warn("kprobe name is invalid: %s\n", func_name);
+ return libbpf_err_ptr(err);
+ }
+ if (opts.retprobe && offset != 0) {
+ free(func);
+ err = -EINVAL;
+ pr_warn("kretprobes do not support offset specification\n");
+ return libbpf_err_ptr(err);
+ }
- return bpf_program__attach_kprobe(prog, retprobe, func_name);
+ opts.offset = offset;
+ link = bpf_program__attach_kprobe_opts(prog, func, &opts);
+ free(func);
+ return link;
}
-struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog,
- bool retprobe, pid_t pid,
- const char *binary_path,
- size_t func_offset)
+LIBBPF_API struct bpf_link *
+bpf_program__attach_uprobe_opts(struct bpf_program *prog, pid_t pid,
+ const char *binary_path, size_t func_offset,
+ const struct bpf_uprobe_opts *opts)
{
+ DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts);
char errmsg[STRERR_BUFSIZE];
struct bpf_link *link;
+ size_t ref_ctr_off;
int pfd, err;
+ bool retprobe;
+
+ if (!OPTS_VALID(opts, bpf_uprobe_opts))
+ return libbpf_err_ptr(-EINVAL);
- pfd = perf_event_open_probe(true /* uprobe */, retprobe,
- binary_path, func_offset, pid);
+ retprobe = OPTS_GET(opts, retprobe, false);
+ ref_ctr_off = OPTS_GET(opts, ref_ctr_offset, 0);
+ pe_opts.bpf_cookie = OPTS_GET(opts, bpf_cookie, 0);
+
+ pfd = perf_event_open_probe(true /* uprobe */, retprobe, binary_path,
+ func_offset, pid, ref_ctr_off);
if (pfd < 0) {
pr_warn("prog '%s': failed to create %s '%s:0x%zx' perf event: %s\n",
prog->name, retprobe ? "uretprobe" : "uprobe",
@@ -10362,7 +9316,7 @@ struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog,
libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
return libbpf_err_ptr(pfd);
}
- link = bpf_program__attach_perf_event(prog, pfd);
+ link = bpf_program__attach_perf_event_opts(prog, pfd, &pe_opts);
err = libbpf_get_error(link);
if (err) {
close(pfd);
@@ -10375,6 +9329,16 @@ struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog,
return link;
}
+struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog,
+ bool retprobe, pid_t pid,
+ const char *binary_path,
+ size_t func_offset)
+{
+ DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, opts, .retprobe = retprobe);
+
+ return bpf_program__attach_uprobe_opts(prog, pid, binary_path, func_offset, &opts);
+}
+
static int determine_tracepoint_id(const char *tp_category,
const char *tp_name)
{
@@ -10425,14 +9389,21 @@ static int perf_event_open_tracepoint(const char *tp_category,
return pfd;
}
-struct bpf_link *bpf_program__attach_tracepoint(struct bpf_program *prog,
- const char *tp_category,
- const char *tp_name)
+struct bpf_link *bpf_program__attach_tracepoint_opts(struct bpf_program *prog,
+ const char *tp_category,
+ const char *tp_name,
+ const struct bpf_tracepoint_opts *opts)
{
+ DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts);
char errmsg[STRERR_BUFSIZE];
struct bpf_link *link;
int pfd, err;
+ if (!OPTS_VALID(opts, bpf_tracepoint_opts))
+ return libbpf_err_ptr(-EINVAL);
+
+ pe_opts.bpf_cookie = OPTS_GET(opts, bpf_cookie, 0);
+
pfd = perf_event_open_tracepoint(tp_category, tp_name);
if (pfd < 0) {
pr_warn("prog '%s': failed to create tracepoint '%s/%s' perf event: %s\n",
@@ -10440,7 +9411,7 @@ struct bpf_link *bpf_program__attach_tracepoint(struct bpf_program *prog,
libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
return libbpf_err_ptr(pfd);
}
- link = bpf_program__attach_perf_event(prog, pfd);
+ link = bpf_program__attach_perf_event_opts(prog, pfd, &pe_opts);
err = libbpf_get_error(link);
if (err) {
close(pfd);
@@ -10452,6 +9423,13 @@ struct bpf_link *bpf_program__attach_tracepoint(struct bpf_program *prog,
return link;
}
+struct bpf_link *bpf_program__attach_tracepoint(struct bpf_program *prog,
+ const char *tp_category,
+ const char *tp_name)
+{
+ return bpf_program__attach_tracepoint_opts(prog, tp_category, tp_name, NULL);
+}
+
static struct bpf_link *attach_tp(const struct bpf_sec_def *sec,
struct bpf_program *prog)
{