* [RFC bpf 0/2] bpf: kernel CO-RE relocation
@ 2021-09-09 13:31 Matteo Croce
2021-09-09 13:31 ` [RFC bpf 1/2] btf: copy relo_core from tools to kernel Matteo Croce
2021-09-09 13:31 ` [RFC bpf 2/2] btf: adapt relo_core for kernel compilation Matteo Croce
0 siblings, 2 replies; 7+ messages in thread
From: Matteo Croce @ 2021-09-09 13:31 UTC (permalink / raw)
To: bpf, Alexei Starovoitov
Cc: Arnaldo Carvalho de Melo, Daniel Borkmann, Andrii Nakryiko
From: Matteo Croce <mcroce@microsoft.com>
This series is a preliminary work to move the CO-RE relocations in the kernel.
This is the first step to have signed BPF files, since userspace instruction
patching makes any verification ineffective.
The first patch just copies the relocation code from tools/lib/bpf/,
the second one refactors the whole code so to build it in kernel.
It builds with a single warning, which can be suppressed by switching to
dynamic allocation:
kernel/bpf/relo_core.c: In function 'bpf_core_apply_relo_insn':
kernel/bpf/relo_core.c:1457:1: warning: the frame size of 2776 bytes is larger than 1024 bytes [-Wframe-larger-than=]
To really use this code and do the the relocations done in kernel, we will
need an API to pass the relocation informations along the BPF file, so don't
consider this patches for inclusion, but just as a first step toward the
full work.
Matteo Croce (2):
btf: copy relo_core from tools to kernel
btf: adapt relo_core for kernel compilation
include/linux/btf.h | 65 ++
kernel/bpf/Makefile | 1 +
kernel/bpf/btf.c | 45 +-
kernel/bpf/relo_core.c | 1457 ++++++++++++++++++++++++++++++++++++++++
kernel/bpf/relo_core.h | 100 +++
5 files changed, 1630 insertions(+), 38 deletions(-)
create mode 100644 kernel/bpf/relo_core.c
create mode 100644 kernel/bpf/relo_core.h
--
2.31.1
^ permalink raw reply [flat|nested] 7+ messages in thread
* [RFC bpf 1/2] btf: copy relo_core from tools to kernel
2021-09-09 13:31 [RFC bpf 0/2] bpf: kernel CO-RE relocation Matteo Croce
@ 2021-09-09 13:31 ` Matteo Croce
2021-09-09 13:31 ` [RFC bpf 2/2] btf: adapt relo_core for kernel compilation Matteo Croce
1 sibling, 0 replies; 7+ messages in thread
From: Matteo Croce @ 2021-09-09 13:31 UTC (permalink / raw)
To: bpf, Alexei Starovoitov
Cc: Arnaldo Carvalho de Melo, Daniel Borkmann, Andrii Nakryiko
From: Matteo Croce <mcroce@microsoft.com>
Just copy relo_core.{c,h} from tools/lib/bpf/ to kernel/bpf/ and
adapt the Makefile.
Signed-off-by: Matteo Croce <mcroce@microsoft.com>
---
kernel/bpf/Makefile | 1 +
kernel/bpf/relo_core.c | 1295 ++++++++++++++++++++++++++++++++++++++++
kernel/bpf/relo_core.h | 100 ++++
3 files changed, 1396 insertions(+)
create mode 100644 kernel/bpf/relo_core.c
create mode 100644 kernel/bpf/relo_core.h
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 7f33098ca63f..2ed7da9eba4a 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -36,3 +36,4 @@ obj-$(CONFIG_BPF_SYSCALL) += bpf_struct_ops.o
obj-${CONFIG_BPF_LSM} += bpf_lsm.o
endif
obj-$(CONFIG_BPF_PRELOAD) += preload/
+obj-$(CONFIG_BPF_SYSCALL) += relo_core.o
diff --git a/kernel/bpf/relo_core.c b/kernel/bpf/relo_core.c
new file mode 100644
index 000000000000..4016ed492d0c
--- /dev/null
+++ b/kernel/bpf/relo_core.c
@@ -0,0 +1,1295 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+/* Copyright (c) 2019 Facebook */
+
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <ctype.h>
+#include <linux/err.h>
+
+#include "libbpf.h"
+#include "bpf.h"
+#include "btf.h"
+#include "str_error.h"
+#include "libbpf_internal.h"
+
+#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 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;
+}
+
+/* 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;
+}
+
+/*
+ * 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 char *prog_name,
+ 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 char *prog_name,
+ 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_name, relo, local_spec,
+ &res->orig_val, &res->orig_sz,
+ &res->orig_type_id, &res->validate);
+ err = err ?: bpf_core_calc_field_relo(prog_name, 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(const char *prog_name, 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(const char *prog_name, struct bpf_insn *insn,
+ int insn_idx, const struct bpf_core_relo *relo,
+ int relo_idx, const struct bpf_core_relo_res *res)
+{
+ __u32 orig_val, new_val;
+ __u8 class;
+
+ 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_name, relo_idx, insn_idx + 1, insn + 1);
+ bpf_core_poison_insn(prog_name, 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[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;
+ }
+}
+
+/*
+ * 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.
+ */
+int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,
+ int insn_idx,
+ const struct bpf_core_relo *relo,
+ int relo_idx,
+ const struct btf *local_btf,
+ struct bpf_core_cand_list *cands)
+{
+ struct bpf_core_spec local_spec, cand_spec, targ_spec = {};
+ struct bpf_core_relo_res cand_res, targ_res;
+ const struct btf_type *local_type;
+ const char *local_name;
+ __u32 local_id;
+ const char *spec_str;
+ int i, j, err;
+
+ local_id = relo->type_id;
+ local_type = btf__type_by_id(local_btf, local_id);
+ if (!local_type)
+ return -EINVAL;
+
+ local_name = btf__name_by_offset(local_btf, local_type->name_off);
+ if (!local_name)
+ return -EINVAL;
+
+ spec_str = btf__name_by_offset(local_btf, relo->access_str_off);
+ if (str_is_empty(spec_str))
+ return -EINVAL;
+
+ err = bpf_core_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;
+ }
+
+
+ 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_name, 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_name, 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_name, insn, insn_idx, relo, relo_idx, &targ_res);
+ if (err) {
+ pr_warn("prog '%s': relo #%d: failed to patch insn #%u: %d\n",
+ prog_name, relo_idx, relo->insn_off / 8, err);
+ return -EINVAL;
+ }
+
+ return 0;
+}
diff --git a/kernel/bpf/relo_core.h b/kernel/bpf/relo_core.h
new file mode 100644
index 000000000000..3b9f8f18346c
--- /dev/null
+++ b/kernel/bpf/relo_core.h
@@ -0,0 +1,100 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+/* Copyright (c) 2019 Facebook */
+
+#ifndef __RELO_CORE_H
+#define __RELO_CORE_H
+
+/* bpf_core_relo_kind encodes which aspect of captured field/type/enum value
+ * has to be adjusted by relocations.
+ */
+enum bpf_core_relo_kind {
+ BPF_FIELD_BYTE_OFFSET = 0, /* field byte offset */
+ BPF_FIELD_BYTE_SIZE = 1, /* field size in bytes */
+ BPF_FIELD_EXISTS = 2, /* field existence in target kernel */
+ BPF_FIELD_SIGNED = 3, /* field signedness (0 - unsigned, 1 - signed) */
+ BPF_FIELD_LSHIFT_U64 = 4, /* bitfield-specific left bitshift */
+ BPF_FIELD_RSHIFT_U64 = 5, /* bitfield-specific right bitshift */
+ BPF_TYPE_ID_LOCAL = 6, /* type ID in local BPF object */
+ BPF_TYPE_ID_TARGET = 7, /* type ID in target kernel */
+ BPF_TYPE_EXISTS = 8, /* type existence in target kernel */
+ BPF_TYPE_SIZE = 9, /* type size in bytes */
+ BPF_ENUMVAL_EXISTS = 10, /* enum value existence in target kernel */
+ BPF_ENUMVAL_VALUE = 11, /* enum value integer value */
+};
+
+/* The minimum bpf_core_relo checked by the loader
+ *
+ * CO-RE relocation captures the following data:
+ * - insn_off - instruction offset (in bytes) within a BPF program that needs
+ * its insn->imm field to be relocated with actual field info;
+ * - type_id - BTF type ID of the "root" (containing) entity of a relocatable
+ * type or field;
+ * - access_str_off - offset into corresponding .BTF string section. String
+ * interpretation depends on specific relocation kind:
+ * - for field-based relocations, string encodes an accessed field using
+ * a sequence of field and array indices, separated by colon (:). It's
+ * conceptually very close to LLVM's getelementptr ([0]) instruction's
+ * arguments for identifying offset to a field.
+ * - for type-based relocations, strings is expected to be just "0";
+ * - for enum value-based relocations, string contains an index of enum
+ * value within its enum type;
+ *
+ * Example to provide a better feel.
+ *
+ * struct sample {
+ * int a;
+ * struct {
+ * int b[10];
+ * };
+ * };
+ *
+ * struct sample *s = ...;
+ * int x = &s->a; // encoded as "0:0" (a is field #0)
+ * int y = &s->b[5]; // encoded as "0:1:0:5" (anon struct is field #1,
+ * // b is field #0 inside anon struct, accessing elem #5)
+ * int z = &s[10]->b; // encoded as "10:1" (ptr is used as an array)
+ *
+ * type_id for all relocs in this example will capture BTF type id of
+ * `struct sample`.
+ *
+ * Such relocation is emitted when using __builtin_preserve_access_index()
+ * Clang built-in, passing expression that captures field address, e.g.:
+ *
+ * bpf_probe_read(&dst, sizeof(dst),
+ * __builtin_preserve_access_index(&src->a.b.c));
+ *
+ * In this case Clang will emit field relocation recording necessary data to
+ * be able to find offset of embedded `a.b.c` field within `src` struct.
+ *
+ * [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction
+ */
+struct bpf_core_relo {
+ __u32 insn_off;
+ __u32 type_id;
+ __u32 access_str_off;
+ enum bpf_core_relo_kind kind;
+};
+
+struct bpf_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 bpf_core_cand_list {
+ struct bpf_core_cand *cands;
+ int len;
+};
+
+int bpf_core_apply_relo_insn(const char *prog_name,
+ struct bpf_insn *insn, int insn_idx,
+ const struct bpf_core_relo *relo, int relo_idx,
+ const struct btf *local_btf,
+ struct bpf_core_cand_list *cands);
+int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id,
+ const struct btf *targ_btf, __u32 targ_id);
+
+size_t bpf_core_essential_name_len(const char *name);
+#endif
--
2.31.1
^ permalink raw reply related [flat|nested] 7+ messages in thread
* [RFC bpf 2/2] btf: adapt relo_core for kernel compilation
2021-09-09 13:31 [RFC bpf 0/2] bpf: kernel CO-RE relocation Matteo Croce
2021-09-09 13:31 ` [RFC bpf 1/2] btf: copy relo_core from tools to kernel Matteo Croce
@ 2021-09-09 13:31 ` Matteo Croce
2021-09-09 18:23 ` Alexei Starovoitov
1 sibling, 1 reply; 7+ messages in thread
From: Matteo Croce @ 2021-09-09 13:31 UTC (permalink / raw)
To: bpf, Alexei Starovoitov
Cc: Arnaldo Carvalho de Melo, Daniel Borkmann, Andrii Nakryiko
From: Matteo Croce <mcroce@microsoft.com>
Refactor kernel/bpf/relo_core.c so it builds in kernel contexxt.
- Replace lot of helpers used by the userspace code with the in-kernel
equivalent (e.g. s/btf_is_composite/btf_type_is_struct/
and s/btf_vlen/btf_type_vlen)
- Move some static helpers from btf.c to btf.h (e.g. btf_type_is_array)
- Port utility functions (e.g. str_is_empty)
Signed-off-by: Matteo Croce <mcroce@microsoft.com>
---
include/linux/btf.h | 65 ++++++++++
kernel/bpf/btf.c | 45 ++-----
kernel/bpf/relo_core.c | 272 ++++++++++++++++++++++++++++++++---------
3 files changed, 289 insertions(+), 93 deletions(-)
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 214fde93214b..6c5bfbab9f23 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -123,6 +123,11 @@ const char *btf_type_str(const struct btf_type *t);
i < btf_type_vlen(datasec_type); \
i++, member++)
+static inline __u16 btf_kind(const struct btf_type *t)
+{
+ return BTF_INFO_KIND(t->info);
+}
+
static inline bool btf_type_is_ptr(const struct btf_type *t)
{
return BTF_INFO_KIND(t->info) == BTF_KIND_PTR;
@@ -168,6 +173,34 @@ static inline bool btf_type_is_var(const struct btf_type *t)
return BTF_INFO_KIND(t->info) == BTF_KIND_VAR;
}
+static inline bool btf_type_is_array(const struct btf_type *t)
+{
+ return BTF_INFO_KIND(t->info) == BTF_KIND_ARRAY;
+}
+
+static inline bool btf_type_is_modifier(const struct btf_type *t)
+{
+ /* Some of them is not strictly a C modifier
+ * but they are grouped into the same bucket
+ * for BTF concern:
+ * A type (t) that refers to another
+ * type through t->type AND its size cannot
+ * be determined without following the t->type.
+ *
+ * ptr does not fall into this bucket
+ * because its size is always sizeof(void *).
+ */
+ switch (BTF_INFO_KIND(t->info)) {
+ case BTF_KIND_TYPEDEF:
+ case BTF_KIND_VOLATILE:
+ case BTF_KIND_CONST:
+ case BTF_KIND_RESTRICT:
+ return true;
+ }
+
+ return false;
+}
+
/* union is only a special case of struct:
* all its offsetof(member) == 0
*/
@@ -207,6 +240,21 @@ static inline u32 btf_member_bitfield_size(const struct btf_type *struct_type,
: 0;
}
+static inline __u8 btf_member_int_offset(const struct btf_type *t)
+{
+ return BTF_INT_OFFSET(*(__u32 *)(t + 1));
+}
+
+static inline __u8 btf_int_encoding(const struct btf_type *t)
+{
+ return BTF_INT_ENCODING(*(__u32 *)(t + 1));
+}
+
+static inline struct btf_param *btf_type_params(const struct btf_type *t)
+{
+ return (struct btf_param *)(t + 1);
+}
+
static inline const struct btf_member *btf_type_member(const struct btf_type *t)
{
return (const struct btf_member *)(t + 1);
@@ -218,6 +266,23 @@ static inline const struct btf_var_secinfo *btf_type_var_secinfo(
return (const struct btf_var_secinfo *)(t + 1);
}
+static inline const struct btf_enum *btf_type_enum(const struct btf_type *t)
+{
+ return (const struct btf_enum *)(t + 1);
+}
+
+static inline const struct btf_array *btf_type_array(const struct btf_type *t)
+{
+ return (const struct btf_array *)(t + 1);
+}
+
+static inline bool is_ldimm64_insn(struct bpf_insn *insn)
+{
+ return insn->code == (BPF_LD | BPF_IMM | BPF_DW);
+}
+
+const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id);
+
#ifdef CONFIG_BPF_SYSCALL
struct bpf_prog;
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index dfe61df4f974..d0c3a6c7fb2a 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -400,29 +400,6 @@ static struct btf_type btf_void;
static int btf_resolve(struct btf_verifier_env *env,
const struct btf_type *t, u32 type_id);
-static bool btf_type_is_modifier(const struct btf_type *t)
-{
- /* Some of them is not strictly a C modifier
- * but they are grouped into the same bucket
- * for BTF concern:
- * A type (t) that refers to another
- * type through t->type AND its size cannot
- * be determined without following the t->type.
- *
- * ptr does not fall into this bucket
- * because its size is always sizeof(void *).
- */
- switch (BTF_INFO_KIND(t->info)) {
- case BTF_KIND_TYPEDEF:
- case BTF_KIND_VOLATILE:
- case BTF_KIND_CONST:
- case BTF_KIND_RESTRICT:
- return true;
- }
-
- return false;
-}
-
bool btf_type_is_void(const struct btf_type *t)
{
return t == &btf_void;
@@ -449,11 +426,6 @@ static bool __btf_type_is_struct(const struct btf_type *t)
return BTF_INFO_KIND(t->info) == BTF_KIND_STRUCT;
}
-static bool btf_type_is_array(const struct btf_type *t)
-{
- return BTF_INFO_KIND(t->info) == BTF_KIND_ARRAY;
-}
-
static bool btf_type_is_datasec(const struct btf_type *t)
{
return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC;
@@ -601,16 +573,6 @@ static u32 btf_type_int(const struct btf_type *t)
return *(u32 *)(t + 1);
}
-static const struct btf_array *btf_type_array(const struct btf_type *t)
-{
- return (const struct btf_array *)(t + 1);
-}
-
-static const struct btf_enum *btf_type_enum(const struct btf_type *t)
-{
- return (const struct btf_enum *)(t + 1);
-}
-
static const struct btf_var *btf_type_var(const struct btf_type *t)
{
return (const struct btf_var *)(t + 1);
@@ -6007,6 +5969,13 @@ bool btf_id_set_contains(const struct btf_id_set *set, u32 id)
return bsearch(&id, set->ids, set->cnt, sizeof(u32), btf_id_cmp_func) != NULL;
}
+const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id)
+{
+ if (type_id >= btf->start_id + btf->nr_types)
+ return NULL;
+ return btf_type_by_id((struct btf *)btf, type_id);
+}
+
#ifdef CONFIG_DEBUG_INFO_BTF_MODULES
struct btf_module {
struct list_head list;
diff --git a/kernel/bpf/relo_core.c b/kernel/bpf/relo_core.c
index 4016ed492d0c..c15a627d9131 100644
--- a/kernel/bpf/relo_core.c
+++ b/kernel/bpf/relo_core.c
@@ -1,17 +1,11 @@
// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
/* Copyright (c) 2019 Facebook */
-#include <stdio.h>
-#include <string.h>
-#include <errno.h>
-#include <ctype.h>
-#include <linux/err.h>
-
-#include "libbpf.h"
-#include "bpf.h"
-#include "btf.h"
-#include "str_error.h"
-#include "libbpf_internal.h"
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <uapi/linux/btf.h>
+
+#include "relo_core.h"
#define BPF_CORE_SPEC_MAX_LEN 64
@@ -40,6 +34,50 @@ struct bpf_core_spec {
__u32 bit_offset;
};
+enum libbpf_print_level {
+ LIBBPF_WARN,
+ LIBBPF_INFO,
+ LIBBPF_DEBUG,
+};
+
+#define libbpf_print(lvl, fmt...) do { \
+ if (lvl == LIBBPF_WARN) { \
+ pr_warn(fmt); \
+ } else if (lvl == LIBBPF_INFO) { \
+ pr_info(fmt); \
+ } else if (lvl == LIBBPF_DEBUG) { \
+ pr_debug(fmt); \
+ } \
+ } while (0)
+
+static bool str_is_empty(const char *s)
+{
+ return !s || !s[0];
+}
+
+static bool bpf_core_is_flavor_sep(const char *s)
+{
+ /* check X___Y name pattern, where X and Y are not underscores */
+ return s[0] != '_' && /* X */
+ s[1] == '_' && s[2] == '_' && s[3] == '_' && /* ___ */
+ s[4] != '_'; /* Y */
+}
+
+/* Given 'some_struct_name___with_flavor' return the length of a name prefix
+ * before last triple underscore. Struct name part after last triple
+ * underscore is ignored by BPF CO-RE relocation during relocation matching.
+ */
+size_t bpf_core_essential_name_len(const char *name)
+{
+ size_t n = strlen(name);
+ int i;
+
+ for (i = n - 5; i >= 0; i--) {
+ if (bpf_core_is_flavor_sep(name + i))
+ return i + 1;
+ }
+ return n;
+}
static bool is_flex_arr(const struct btf *btf,
const struct bpf_core_accessor *acc,
const struct btf_array *arr)
@@ -52,7 +90,20 @@ static bool is_flex_arr(const struct btf *btf,
/* 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;
+ return acc->idx == btf_type_vlen(t) - 1;
+}
+
+static __s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
+{
+ const struct btf_type *t = btf__type_by_id(btf, type_id);
+ const struct btf_type *ret;
+ __u32 type_size;
+
+ ret = btf_resolve_size(btf, t, &type_size);
+ if (IS_ERR(ret))
+ return PTR_ERR(ret);
+
+ return type_size;
}
static const char *core_relo_kind_str(enum bpf_core_relo_kind kind)
@@ -113,6 +164,117 @@ static bool core_relo_is_enumval_based(enum bpf_core_relo_kind kind)
}
}
+const struct btf_type *
+skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id)
+{
+ const struct btf_type *t = btf__type_by_id(btf, id);
+
+ if (res_id)
+ *res_id = id;
+
+ while (btf_type_is_modifier(t) || btf_type_is_typedef(t)) {
+ if (res_id)
+ *res_id = t->type;
+ t = btf__type_by_id(btf, t->type);
+ }
+
+ return t;
+}
+
+/* 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
+ * checked for name match. Beyond that initial root-level name check, names
+ * are completely ignored. Compatibility rules are as follows:
+ * - any two STRUCTs/UNIONs/FWDs/ENUMs/INTs are considered compatible, but
+ * kind should match for local and target types (i.e., STRUCT is not
+ * compatible with UNION);
+ * - for ENUMs, the size is ignored;
+ * - for INT, size and signedness are ignored;
+ * - for ARRAY, dimensionality is ignored, element types are checked for
+ * compatibility recursively;
+ * - CONST/VOLATILE/RESTRICT modifiers are ignored;
+ * - TYPEDEFs/PTRs are compatible if types they pointing to are compatible;
+ * - FUNC_PROTOs are compatible if they have compatible signature: same
+ * number of input args and compatible return and argument types.
+ * These rules are not set in stone and probably will be adjusted as we get
+ * more experience with using BPF CO-RE relocations.
+ */
+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 */
+
+ /* caller made sure that names match (ignoring flavor suffix) */
+ local_type = btf__type_by_id(local_btf, local_id);
+ targ_type = btf__type_by_id(targ_btf, targ_id);
+ if (btf_kind(local_type) != btf_kind(targ_type))
+ return 0;
+
+recur:
+ depth--;
+ if (depth < 0)
+ return -EINVAL;
+
+ 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_kind(local_type) != btf_kind(targ_type))
+ return 0;
+
+ switch (btf_kind(local_type)) {
+ case BTF_KIND_UNKN:
+ case BTF_KIND_STRUCT:
+ case BTF_KIND_UNION:
+ case BTF_KIND_ENUM:
+ case BTF_KIND_FWD:
+ return 1;
+ case BTF_KIND_INT:
+ /* just reject deprecated bitfield-like integers; all other
+ * integers are by default compatible between each other
+ */
+ return btf_member_int_offset(local_type) == 0 && btf_member_int_offset(targ_type) == 0;
+ case BTF_KIND_PTR:
+ local_id = local_type->type;
+ targ_id = targ_type->type;
+ goto recur;
+ case BTF_KIND_ARRAY:
+ local_id = btf_type_array(local_type)->type;
+ targ_id = btf_type_array(targ_type)->type;
+ goto recur;
+ case BTF_KIND_FUNC_PROTO: {
+ struct btf_param *local_p = btf_type_params(local_type);
+ struct btf_param *targ_p = btf_type_params(targ_type);
+ __u16 local_vlen = btf_type_vlen(local_type);
+ __u16 targ_vlen = btf_type_vlen(targ_type);
+ int i, err;
+
+ if (local_vlen != targ_vlen)
+ return 0;
+
+ for (i = 0; i < local_vlen; i++, local_p++, targ_p++) {
+ skip_mods_and_typedefs(local_btf, local_p->type, &local_id);
+ skip_mods_and_typedefs(targ_btf, targ_p->type, &targ_id);
+ err = bpf_core_types_are_compat(local_btf, local_id, targ_btf, targ_id);
+ if (err <= 0)
+ return err;
+ }
+
+ /* tail recurse for return type check */
+ skip_mods_and_typedefs(local_btf, local_type->type, &local_id);
+ skip_mods_and_typedefs(targ_btf, targ_type->type, &targ_id);
+ goto recur;
+ }
+ default:
+ pr_warn("unexpected kind %s relocated, local [%d], target [%d]\n",
+ btf_type_str(local_type), local_id, targ_id);
+ return 0;
+ }
+}
+
/*
* Turn bpf_core_relo into a low- and high-level spec representation,
* validating correctness along the way, as well as calculating resulting
@@ -204,11 +366,11 @@ static int bpf_core_parse_spec(const struct btf *btf,
spec->len++;
if (core_relo_is_enumval_based(relo_kind)) {
- if (!btf_is_enum(t) || spec->raw_len > 1 || access_idx >= btf_vlen(t))
+ if (!btf_type_is_enum(t) || spec->raw_len > 1 || access_idx >= btf_type_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);
+ acc->name = btf_name_by_offset(btf, btf_type_enum(t)[access_idx].name_off);
return 0;
}
@@ -228,19 +390,19 @@ static int bpf_core_parse_spec(const struct btf *btf,
access_idx = spec->raw_spec[i];
acc = &spec->spec[spec->len];
- if (btf_is_composite(t)) {
+ if (btf_type_is_struct(t)) {
const struct btf_member *m;
__u32 bit_offset;
- if (access_idx >= btf_vlen(t))
+ if (access_idx >= btf_type_vlen(t))
return -EINVAL;
- bit_offset = btf_member_bit_offset(t, access_idx);
+ bit_offset = btf_member_bit_offset(t, btf_type_member(t) + access_idx);
spec->bit_offset += bit_offset;
- m = btf_members(t) + access_idx;
+ m = btf_type_member(t) + access_idx;
if (m->name_off) {
- name = btf__name_by_offset(btf, m->name_off);
+ name = btf_name_by_offset(btf, m->name_off);
if (str_is_empty(name))
return -EINVAL;
@@ -251,8 +413,8 @@ static int bpf_core_parse_spec(const struct btf *btf,
}
id = m->type;
- } else if (btf_is_array(t)) {
- const struct btf_array *a = btf_array(t);
+ } else if (btf_type_is_array(t)) {
+ const struct btf_array *a = btf_type_array(t);
bool flex;
t = skip_mods_and_typedefs(btf, a->type, &id);
@@ -273,7 +435,7 @@ static int bpf_core_parse_spec(const struct btf *btf,
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));
+ type_id, spec_str, i, id, btf_type_str(t));
return -EINVAL;
}
}
@@ -311,7 +473,7 @@ static int bpf_core_fields_are_compat(const struct btf *local_btf,
if (!local_type || !targ_type)
return -EINVAL;
- if (btf_is_composite(local_type) && btf_is_composite(targ_type))
+ if (btf_type_is_struct(local_type) && btf_type_is_struct(targ_type))
return 1;
if (btf_kind(local_type) != btf_kind(targ_type))
return 0;
@@ -325,9 +487,9 @@ static int bpf_core_fields_are_compat(const struct btf *local_btf,
const char *local_name, *targ_name;
size_t local_len, targ_len;
- local_name = btf__name_by_offset(local_btf,
+ local_name = btf_name_by_offset(local_btf,
local_type->name_off);
- targ_name = btf__name_by_offset(targ_btf, targ_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 */
@@ -339,11 +501,11 @@ static int bpf_core_fields_are_compat(const struct btf *local_btf,
/* 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;
+ return btf_member_int_offset(local_type) == 0 &&
+ btf_member_int_offset(targ_type) == 0;
case BTF_KIND_ARRAY:
- local_id = btf_array(local_type)->type;
- targ_id = btf_array(targ_type)->type;
+ local_id = btf_type_array(local_type)->type;
+ targ_id = btf_type_array(targ_type)->type;
goto recur;
default:
pr_warn("unexpected kind %d relocated, local [%d], target [%d]\n",
@@ -384,20 +546,20 @@ static int bpf_core_match_member(const struct btf *local_btf,
targ_type = skip_mods_and_typedefs(targ_btf, targ_id, &targ_id);
if (!targ_type)
return -EINVAL;
- if (!btf_is_composite(targ_type))
+ if (!btf_type_is_struct(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);
+ local_member = btf_type_member(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);
+ n = btf_type_vlen(targ_type);
+ m = btf_type_member(targ_type);
for (i = 0; i < n; i++, m++) {
__u32 bit_offset;
- bit_offset = btf_member_bit_offset(targ_type, i);
+ bit_offset = btf_member_bit_offset(targ_type, btf_type_member(targ_type) + i);
/* too deep struct/union/array nesting */
if (spec->raw_len == BPF_CORE_SPEC_MAX_LEN)
@@ -407,7 +569,7 @@ static int bpf_core_match_member(const struct btf *local_btf,
spec->bit_offset += bit_offset;
spec->raw_spec[spec->raw_len++] = i;
- targ_name = btf__name_by_offset(targ_btf, m->name_off);
+ 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,
@@ -474,13 +636,13 @@ static int bpf_core_spec_match(struct bpf_core_spec *local_spec,
/* 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))
+ if (!btf_type_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);
+ for (i = 0, e = btf_type_enum(targ_type); i < btf_type_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;
@@ -522,10 +684,10 @@ static int bpf_core_spec_match(struct bpf_core_spec *local_spec,
const struct btf_array *a;
bool flex;
- if (!btf_is_array(targ_type))
+ if (!btf_type_is_array(targ_type))
return 0;
- a = btf_array(targ_type);
+ a = btf_type_array(targ_type);
flex = is_flex_arr(targ_btf, targ_acc - 1, a);
if (!flex && local_acc->idx >= a->nelems)
return 0;
@@ -607,10 +769,10 @@ static int bpf_core_calc_field_relo(const char *prog_name,
return 0;
}
- m = btf_members(t) + acc->idx;
+ m = btf_type_member(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);
+ bit_sz = btf_member_bitfield_size(t, btf_type_member(t) + acc->idx);
bitfield = bit_sz > 0;
if (bitfield) {
@@ -656,13 +818,13 @@ static int bpf_core_calc_field_relo(const char *prog_name,
break;
case BPF_FIELD_SIGNED:
/* enums will be assumed unsigned */
- *val = btf_is_enum(mt) ||
+ *val = btf_type_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
+#ifdef __LITTLE_ENDIAN
*val = 64 - (bit_off + bit_sz - byte_off * 8);
#else
*val = (8 - byte_sz) * 8 + (bit_off - byte_off * 8);
@@ -730,7 +892,7 @@ static int bpf_core_calc_enumval_relo(const struct bpf_core_relo *relo,
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;
+ e = btf_type_enum(t) + spec->spec[0].idx;
*val = e->val;
break;
default:
@@ -822,9 +984,9 @@ static int bpf_core_calc_relo(const char *prog_name,
* 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))
+ if (btf_type_is_ptr(orig_t) && btf_type_is_ptr(new_t))
goto done;
- if (btf_is_int(orig_t) && btf_is_int(new_t) &&
+ if (btf_type_is_int(orig_t) && btf_type_is_int(new_t) &&
btf_int_encoding(orig_t) != BTF_INT_SIGNED &&
btf_int_encoding(new_t) != BTF_INT_SIGNED)
goto done;
@@ -1055,17 +1217,17 @@ static void bpf_core_dump_spec(int level, const struct bpf_core_spec *spec)
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);
+ 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);
+ libbpf_print(level, "[%u] %s %s", type_id, btf_type_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);
+ e = btf_type_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;
@@ -1162,18 +1324,18 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,
if (!local_type)
return -EINVAL;
- local_name = btf__name_by_offset(local_btf, local_type->name_off);
+ local_name = btf_name_by_offset(local_btf, local_type->name_off);
if (!local_name)
return -EINVAL;
- spec_str = btf__name_by_offset(local_btf, relo->access_str_off);
+ spec_str = btf_name_by_offset(local_btf, relo->access_str_off);
if (str_is_empty(spec_str))
return -EINVAL;
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),
+ prog_name, relo_idx, local_id, btf_type_str(local_type),
str_is_empty(local_name) ? "<anon>" : local_name,
spec_str, err);
return -EINVAL;
--
2.31.1
^ permalink raw reply related [flat|nested] 7+ messages in thread
* Re: [RFC bpf 2/2] btf: adapt relo_core for kernel compilation
2021-09-09 13:31 ` [RFC bpf 2/2] btf: adapt relo_core for kernel compilation Matteo Croce
@ 2021-09-09 18:23 ` Alexei Starovoitov
2021-09-17 1:21 ` Matteo Croce
0 siblings, 1 reply; 7+ messages in thread
From: Alexei Starovoitov @ 2021-09-09 18:23 UTC (permalink / raw)
To: Matteo Croce
Cc: bpf, Alexei Starovoitov, Arnaldo Carvalho de Melo,
Daniel Borkmann, Andrii Nakryiko
On Thu, Sep 09, 2021 at 03:31:53PM +0200, Matteo Croce wrote:
> From: Matteo Croce <mcroce@microsoft.com>
>
> Refactor kernel/bpf/relo_core.c so it builds in kernel contexxt.
>
> - Replace lot of helpers used by the userspace code with the in-kernel
> equivalent (e.g. s/btf_is_composite/btf_type_is_struct/
> and s/btf_vlen/btf_type_vlen)
> - Move some static helpers from btf.c to btf.h (e.g. btf_type_is_array)
> - Port utility functions (e.g. str_is_empty)
Cool. It's great to see that you're working on it.
> +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 */
> +
> + /* caller made sure that names match (ignoring flavor suffix) */
> + local_type = btf__type_by_id(local_btf, local_id);
> + targ_type = btf__type_by_id(targ_btf, targ_id);
> + if (btf_kind(local_type) != btf_kind(targ_type))
> + return 0;
> +
> +recur:
> + depth--;
> + if (depth < 0)
> + return -EINVAL;
> +
> + 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_kind(local_type) != btf_kind(targ_type))
> + return 0;
> +
> + switch (btf_kind(local_type)) {
> + case BTF_KIND_UNKN:
> + case BTF_KIND_STRUCT:
> + case BTF_KIND_UNION:
> + case BTF_KIND_ENUM:
> + case BTF_KIND_FWD:
> + return 1;
> + case BTF_KIND_INT:
> + /* just reject deprecated bitfield-like integers; all other
> + * integers are by default compatible between each other
> + */
> + return btf_member_int_offset(local_type) == 0 && btf_member_int_offset(targ_type) == 0;
> + case BTF_KIND_PTR:
> + local_id = local_type->type;
> + targ_id = targ_type->type;
> + goto recur;
> + case BTF_KIND_ARRAY:
> + local_id = btf_type_array(local_type)->type;
> + targ_id = btf_type_array(targ_type)->type;
> + goto recur;
> + case BTF_KIND_FUNC_PROTO: {
> + struct btf_param *local_p = btf_type_params(local_type);
> + struct btf_param *targ_p = btf_type_params(targ_type);
> + __u16 local_vlen = btf_type_vlen(local_type);
> + __u16 targ_vlen = btf_type_vlen(targ_type);
> + int i, err;
> +
> + if (local_vlen != targ_vlen)
> + return 0;
> +
> + for (i = 0; i < local_vlen; i++, local_p++, targ_p++) {
> + skip_mods_and_typedefs(local_btf, local_p->type, &local_id);
> + skip_mods_and_typedefs(targ_btf, targ_p->type, &targ_id);
> + err = bpf_core_types_are_compat(local_btf, local_id, targ_btf, targ_id);
The main todo for this function is to convert to non-recursive
or limit the recursion to some small number (like 16).
> /* record enumerator name in a first accessor */
> - acc->name = btf__name_by_offset(btf, btf_enum(t)[access_idx].name_off);
> + acc->name = btf_name_by_offset(btf, btf_type_enum(t)[access_idx].name_off);
Instead of doing this kind of change and diverge further between kernel and
libbpf it would be better to agree on the same names for the helpers.
They're really the same. There is no good reason for them to have
different names in kernel's btf.h and libbpf's btf.h.
See attached patch how relo_core.c can be converted for kernel duty without copy-paste.
We're doing double compile for disasm.c. We can do the same here.
The copy-paste will lead to code divergence.
The same bug/feature would have to be implemented twice in the future.
The CO-RE algorithm can work in both kernel and user space unmodified.
imo code sharing is almost always a win.
From 1e9b236914d3e7672eba2e3b99aa198ac2bdb7bd Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Tue, 7 Sep 2021 15:45:44 -0700
Subject: [PATCH] bpf: Prepare relo_core.c for kernel duty.
Make relo_core.c to be compiled with kernel and with libbpf.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
include/linux/btf.h | 84 +++++++++++++++++++++++++++++++++
kernel/bpf/Makefile | 4 ++
tools/lib/bpf/relo_core.c | 97 ++++++++++++++++++++++++++++++++++++++-
3 files changed, 183 insertions(+), 2 deletions(-)
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 214fde93214b..152aff09ee2d 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -143,6 +143,48 @@ static inline bool btf_type_is_enum(const struct btf_type *t)
return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM;
}
+static inline u16 btf_kind(const struct btf_type *t)
+{
+ return BTF_INFO_KIND(t->info);
+}
+
+static inline bool btf_is_enum(const struct btf_type *t)
+{
+ return btf_kind(t) == BTF_KIND_ENUM;
+}
+
+static inline bool btf_is_composite(const struct btf_type *t)
+{
+ u16 kind = btf_kind(t);
+
+ return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION;
+}
+
+static inline bool btf_is_array(const struct btf_type *t)
+{
+ return btf_kind(t) == BTF_KIND_ARRAY;
+}
+
+static inline bool btf_is_int(const struct btf_type *t)
+{
+ return btf_kind(t) == BTF_KIND_INT;
+}
+
+static inline bool btf_is_ptr(const struct btf_type *t)
+{
+ return btf_kind(t) == BTF_KIND_PTR;
+}
+
+static inline u8 btf_int_offset(const struct btf_type *t)
+{
+ return BTF_INT_OFFSET(*(u32 *)(t + 1));
+}
+
+static inline u8 btf_int_encoding(const struct btf_type *t)
+{
+ return BTF_INT_ENCODING(*(u32 *)(t + 1));
+}
+
static inline bool btf_type_is_scalar(const struct btf_type *t)
{
return btf_type_is_int(t) || btf_type_is_enum(t);
@@ -183,6 +225,11 @@ static inline u16 btf_type_vlen(const struct btf_type *t)
return BTF_INFO_VLEN(t->info);
}
+static inline u16 btf_vlen(const struct btf_type *t)
+{
+ return btf_type_vlen(t);
+}
+
static inline u16 btf_func_linkage(const struct btf_type *t)
{
return BTF_INFO_VLEN(t->info);
@@ -193,6 +240,27 @@ static inline bool btf_type_kflag(const struct btf_type *t)
return BTF_INFO_KFLAG(t->info);
}
+static inline struct btf_member *btf_members(const struct btf_type *t)
+{
+ return (struct btf_member *)(t + 1);
+}
+#ifdef RELO_CORE
+static inline u32 btf_member_bit_offset(const struct btf_type *t, u32 member_idx)
+{
+ const struct btf_member *m = btf_members(t) + member_idx;
+ bool kflag = btf_type_kflag(t);
+
+ return kflag ? BTF_MEMBER_BIT_OFFSET(m->offset) : m->offset;
+}
+
+static inline u32 btf_member_bitfield_size(const struct btf_type *t, u32 member_idx)
+{
+ const struct btf_member *m = btf_members(t) + member_idx;
+ bool kflag = btf_type_kflag(t);
+
+ return kflag ? BTF_MEMBER_BITFIELD_SIZE(m->offset) : 0;
+}
+#else
static inline u32 btf_member_bit_offset(const struct btf_type *struct_type,
const struct btf_member *member)
{
@@ -206,12 +274,24 @@ static inline u32 btf_member_bitfield_size(const struct btf_type *struct_type,
return btf_type_kflag(struct_type) ? BTF_MEMBER_BITFIELD_SIZE(member->offset)
: 0;
}
+#endif
static inline const struct btf_member *btf_type_member(const struct btf_type *t)
{
return (const struct btf_member *)(t + 1);
}
+
+static inline struct btf_array *btf_array(const struct btf_type *t)
+{
+ return (struct btf_array *)(t + 1);
+}
+
+static inline struct btf_enum *btf_enum(const struct btf_type *t)
+{
+ return (struct btf_enum *)(t + 1);
+}
+
static inline const struct btf_var_secinfo *btf_type_var_secinfo(
const struct btf_type *t)
{
@@ -222,6 +302,10 @@ static inline const struct btf_var_secinfo *btf_type_var_secinfo(
struct bpf_prog;
const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);
+static inline const struct btf_type *btf__type_by_id(const struct btf *btf, u32 type_id)
+{
+ return btf_type_by_id(btf, type_id);
+}
const char *btf_name_by_offset(const struct btf *btf, u32 offset);
struct btf *btf_parse_vmlinux(void);
struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog);
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 7f33098ca63f..3d5370c876b5 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -36,3 +36,7 @@ obj-$(CONFIG_BPF_SYSCALL) += bpf_struct_ops.o
obj-${CONFIG_BPF_LSM} += bpf_lsm.o
endif
obj-$(CONFIG_BPF_PRELOAD) += preload/
+
+obj-$(CONFIG_BPF_SYSCALL) += relo_core.o
+$(obj)/relo_core.o: $(srctree)/tools/lib/bpf/relo_core.c FORCE
+ $(call if_changed_rule,cc_o_c)
diff --git a/tools/lib/bpf/relo_core.c b/tools/lib/bpf/relo_core.c
index 4016ed492d0c..9d1f309f05fe 100644
--- a/tools/lib/bpf/relo_core.c
+++ b/tools/lib/bpf/relo_core.c
@@ -1,6 +1,98 @@
// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
/* Copyright (c) 2019 Facebook */
+#ifdef __KERNEL__
+#define RELO_CORE
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <linux/string.h>
+#include "relo_core.h"
+
+static const char *btf_kind_str(const struct btf_type *t)
+{
+ return btf_type_str(t);
+}
+
+static bool str_is_empty(const char *s)
+{
+ return !s || !s[0];
+}
+
+static bool is_ldimm64_insn(struct bpf_insn *insn)
+{
+ return insn->code == (BPF_LD | BPF_IMM | BPF_DW);
+}
+
+static const struct btf_type *
+skip_mods_and_typedefs(const struct btf *btf, u32 id, u32 *res_id)
+{
+ return btf_type_skip_modifiers(btf, id, res_id);
+}
+
+static const char *btf__name_by_offset(const struct btf *btf, u32 offset)
+{
+ return btf_name_by_offset(btf, offset);
+}
+
+static s64 btf__resolve_size(const struct btf *btf, u32 type_id)
+{
+ const struct btf_type *t;
+ int size;
+
+ t = btf_type_by_id(btf, type_id);
+ t = btf_resolve_size(btf, t, &size);
+ if (IS_ERR(t))
+ return PTR_ERR(t);
+ return size;
+}
+
+static bool bpf_core_is_flavor_sep(const char *s)
+{
+ /* check X___Y name pattern, where X and Y are not underscores */
+ return s[0] != '_' && /* X */
+ s[1] == '_' && s[2] == '_' && s[3] == '_' && /* ___ */
+ s[4] != '_'; /* Y */
+}
+
+size_t bpf_core_essential_name_len(const char *name)
+{
+ size_t n = strlen(name);
+ int i;
+
+ for (i = n - 5; i >= 0; i--) {
+ if (bpf_core_is_flavor_sep(name + i))
+ return i + 1;
+ }
+ return n;
+}
+
+enum libbpf_print_level {
+ LIBBPF_WARN,
+ LIBBPF_INFO,
+ LIBBPF_DEBUG,
+};
+__attribute__((format(printf, 2, 3)))
+void libbpf_print(enum libbpf_print_level level,
+ const char *format, ...)
+{
+}
+#define __pr(level, fmt, ...) \
+do { \
+ libbpf_print(level, "libbpf: " fmt, ##__VA_ARGS__); \
+} while (0)
+
+#undef pr_warn
+#undef pr_info
+#undef pr_debug
+#define pr_warn(fmt, ...) __pr(LIBBPF_WARN, fmt, ##__VA_ARGS__)
+#define pr_info(fmt, ...) __pr(LIBBPF_INFO, fmt, ##__VA_ARGS__)
+#define pr_debug(fmt, ...) __pr(LIBBPF_DEBUG, fmt, ##__VA_ARGS__)
+int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id,
+ const struct btf *targ_btf, __u32 targ_id)
+{
+ return 0;
+}
+#else
#include <stdio.h>
#include <string.h>
#include <errno.h>
@@ -12,8 +104,9 @@
#include "btf.h"
#include "str_error.h"
#include "libbpf_internal.h"
+#endif
-#define BPF_CORE_SPEC_MAX_LEN 64
+#define BPF_CORE_SPEC_MAX_LEN 32
/* represents BPF CO-RE field or array element accessor */
struct bpf_core_accessor {
@@ -662,7 +755,7 @@ static int bpf_core_calc_field_relo(const char *prog_name,
*validate = true; /* signedness is never ambiguous */
break;
case BPF_FIELD_LSHIFT_U64:
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
*val = 64 - (bit_off + bit_sz - byte_off * 8);
#else
*val = (8 - byte_sz) * 8 + (bit_off - byte_off * 8);
--
2.30.2
^ permalink raw reply related [flat|nested] 7+ messages in thread
* Re: [RFC bpf 2/2] btf: adapt relo_core for kernel compilation
2021-09-09 18:23 ` Alexei Starovoitov
@ 2021-09-17 1:21 ` Matteo Croce
2021-09-17 4:12 ` Alexei Starovoitov
0 siblings, 1 reply; 7+ messages in thread
From: Matteo Croce @ 2021-09-17 1:21 UTC (permalink / raw)
To: Alexei Starovoitov
Cc: bpf, Alexei Starovoitov, Arnaldo Carvalho de Melo,
Daniel Borkmann, Andrii Nakryiko
On Thu, Sep 9, 2021 at 8:23 PM Alexei Starovoitov
<alexei.starovoitov@gmail.com> wrote:
>
> On Thu, Sep 09, 2021 at 03:31:53PM +0200, Matteo Croce wrote:
> > From: Matteo Croce <mcroce@microsoft.com>
> >
> > Refactor kernel/bpf/relo_core.c so it builds in kernel contexxt.
> >
> > - Replace lot of helpers used by the userspace code with the in-kernel
> > equivalent (e.g. s/btf_is_composite/btf_type_is_struct/
> > and s/btf_vlen/btf_type_vlen)
> > - Move some static helpers from btf.c to btf.h (e.g. btf_type_is_array)
> > - Port utility functions (e.g. str_is_empty)
>
> Cool. It's great to see that you're working on it.
>
> > +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 */
> > +
> > + /* caller made sure that names match (ignoring flavor suffix) */
> > + local_type = btf__type_by_id(local_btf, local_id);
> > + targ_type = btf__type_by_id(targ_btf, targ_id);
> > + if (btf_kind(local_type) != btf_kind(targ_type))
> > + return 0;
> > +
> > +recur:
> > + depth--;
> > + if (depth < 0)
> > + return -EINVAL;
> > +
> > + 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_kind(local_type) != btf_kind(targ_type))
> > + return 0;
> > +
> > + switch (btf_kind(local_type)) {
> > + case BTF_KIND_UNKN:
> > + case BTF_KIND_STRUCT:
> > + case BTF_KIND_UNION:
> > + case BTF_KIND_ENUM:
> > + case BTF_KIND_FWD:
> > + return 1;
> > + case BTF_KIND_INT:
> > + /* just reject deprecated bitfield-like integers; all other
> > + * integers are by default compatible between each other
> > + */
> > + return btf_member_int_offset(local_type) == 0 && btf_member_int_offset(targ_type) == 0;
> > + case BTF_KIND_PTR:
> > + local_id = local_type->type;
> > + targ_id = targ_type->type;
> > + goto recur;
> > + case BTF_KIND_ARRAY:
> > + local_id = btf_type_array(local_type)->type;
> > + targ_id = btf_type_array(targ_type)->type;
> > + goto recur;
> > + case BTF_KIND_FUNC_PROTO: {
> > + struct btf_param *local_p = btf_type_params(local_type);
> > + struct btf_param *targ_p = btf_type_params(targ_type);
> > + __u16 local_vlen = btf_type_vlen(local_type);
> > + __u16 targ_vlen = btf_type_vlen(targ_type);
> > + int i, err;
> > +
> > + if (local_vlen != targ_vlen)
> > + return 0;
> > +
> > + for (i = 0; i < local_vlen; i++, local_p++, targ_p++) {
> > + skip_mods_and_typedefs(local_btf, local_p->type, &local_id);
> > + skip_mods_and_typedefs(targ_btf, targ_p->type, &targ_id);
> > + err = bpf_core_types_are_compat(local_btf, local_id, targ_btf, targ_id);
>
> The main todo for this function is to convert to non-recursive
> or limit the recursion to some small number (like 16).
>
> > /* record enumerator name in a first accessor */
> > - acc->name = btf__name_by_offset(btf, btf_enum(t)[access_idx].name_off);
> > + acc->name = btf_name_by_offset(btf, btf_type_enum(t)[access_idx].name_off);
>
> Instead of doing this kind of change and diverge further between kernel and
> libbpf it would be better to agree on the same names for the helpers.
> They're really the same. There is no good reason for them to have
> different names in kernel's btf.h and libbpf's btf.h.
>
How can we share the helpers source too instead of duplicating it?
> See attached patch how relo_core.c can be converted for kernel duty without copy-paste.
> We're doing double compile for disasm.c. We can do the same here.
Agree.
> The copy-paste will lead to code divergence.
> The same bug/feature would have to be implemented twice in the future.
> The CO-RE algorithm can work in both kernel and user space unmodified.
> imo code sharing is almost always a win.
>
Indeed, I found a small difference between the userspace and kernel code.
In tools/lib/bpf/btf.h we have btf_is_mod() which returns true for
{ BTF_KIND_VOLATILE, BTF_KIND_CONST, BTF_KIND_RESTRICT },
while in kernel/bpf/btf.c we have btf_type_is_modifier() which returns
true also for BTF_KIND_TYPEDEF.
Which is the right one?
>
> From 1e9b236914d3e7672eba2e3b99aa198ac2bdb7bd Mon Sep 17 00:00:00 2001
> From: Alexei Starovoitov <ast@kernel.org>
> Date: Tue, 7 Sep 2021 15:45:44 -0700
> Subject: [PATCH] bpf: Prepare relo_core.c for kernel duty.
>
> Make relo_core.c to be compiled with kernel and with libbpf.
>
> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
> ---
> include/linux/btf.h | 84 +++++++++++++++++++++++++++++++++
> kernel/bpf/Makefile | 4 ++
> tools/lib/bpf/relo_core.c | 97 ++++++++++++++++++++++++++++++++++++++-
> 3 files changed, 183 insertions(+), 2 deletions(-)
>
> diff --git a/include/linux/btf.h b/include/linux/btf.h
> index 214fde93214b..152aff09ee2d 100644
> --- a/include/linux/btf.h
> +++ b/include/linux/btf.h
> @@ -143,6 +143,48 @@ static inline bool btf_type_is_enum(const struct btf_type *t)
> return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM;
> }
>
> +static inline u16 btf_kind(const struct btf_type *t)
> +{
> + return BTF_INFO_KIND(t->info);
> +}
> +
> +static inline bool btf_is_enum(const struct btf_type *t)
> +{
> + return btf_kind(t) == BTF_KIND_ENUM;
> +}
> +
> +static inline bool btf_is_composite(const struct btf_type *t)
> +{
> + u16 kind = btf_kind(t);
> +
> + return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION;
> +}
> +
> +static inline bool btf_is_array(const struct btf_type *t)
> +{
> + return btf_kind(t) == BTF_KIND_ARRAY;
> +}
> +
> +static inline bool btf_is_int(const struct btf_type *t)
> +{
> + return btf_kind(t) == BTF_KIND_INT;
> +}
> +
> +static inline bool btf_is_ptr(const struct btf_type *t)
> +{
> + return btf_kind(t) == BTF_KIND_PTR;
> +}
> +
> +static inline u8 btf_int_offset(const struct btf_type *t)
> +{
> + return BTF_INT_OFFSET(*(u32 *)(t + 1));
> +}
> +
> +static inline u8 btf_int_encoding(const struct btf_type *t)
> +{
> + return BTF_INT_ENCODING(*(u32 *)(t + 1));
> +}
> +
> static inline bool btf_type_is_scalar(const struct btf_type *t)
> {
> return btf_type_is_int(t) || btf_type_is_enum(t);
> @@ -183,6 +225,11 @@ static inline u16 btf_type_vlen(const struct btf_type *t)
> return BTF_INFO_VLEN(t->info);
> }
>
> +static inline u16 btf_vlen(const struct btf_type *t)
> +{
> + return btf_type_vlen(t);
> +}
> +
> static inline u16 btf_func_linkage(const struct btf_type *t)
> {
> return BTF_INFO_VLEN(t->info);
> @@ -193,6 +240,27 @@ static inline bool btf_type_kflag(const struct btf_type *t)
> return BTF_INFO_KFLAG(t->info);
> }
>
> +static inline struct btf_member *btf_members(const struct btf_type *t)
> +{
> + return (struct btf_member *)(t + 1);
> +}
> +#ifdef RELO_CORE
> +static inline u32 btf_member_bit_offset(const struct btf_type *t, u32 member_idx)
> +{
> + const struct btf_member *m = btf_members(t) + member_idx;
> + bool kflag = btf_type_kflag(t);
> +
> + return kflag ? BTF_MEMBER_BIT_OFFSET(m->offset) : m->offset;
> +}
> +
> +static inline u32 btf_member_bitfield_size(const struct btf_type *t, u32 member_idx)
> +{
> + const struct btf_member *m = btf_members(t) + member_idx;
> + bool kflag = btf_type_kflag(t);
> +
> + return kflag ? BTF_MEMBER_BITFIELD_SIZE(m->offset) : 0;
> +}
> +#else
> static inline u32 btf_member_bit_offset(const struct btf_type *struct_type,
> const struct btf_member *member)
> {
> @@ -206,12 +274,24 @@ static inline u32 btf_member_bitfield_size(const struct btf_type *struct_type,
> return btf_type_kflag(struct_type) ? BTF_MEMBER_BITFIELD_SIZE(member->offset)
> : 0;
> }
> +#endif
>
> static inline const struct btf_member *btf_type_member(const struct btf_type *t)
> {
> return (const struct btf_member *)(t + 1);
> }
>
> +
> +static inline struct btf_array *btf_array(const struct btf_type *t)
> +{
> + return (struct btf_array *)(t + 1);
> +}
> +
> +static inline struct btf_enum *btf_enum(const struct btf_type *t)
> +{
> + return (struct btf_enum *)(t + 1);
> +}
> +
> static inline const struct btf_var_secinfo *btf_type_var_secinfo(
> const struct btf_type *t)
> {
> @@ -222,6 +302,10 @@ static inline const struct btf_var_secinfo *btf_type_var_secinfo(
> struct bpf_prog;
>
> const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);
> +static inline const struct btf_type *btf__type_by_id(const struct btf *btf, u32 type_id)
> +{
> + return btf_type_by_id(btf, type_id);
> +}
> const char *btf_name_by_offset(const struct btf *btf, u32 offset);
> struct btf *btf_parse_vmlinux(void);
> struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog);
> diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
> index 7f33098ca63f..3d5370c876b5 100644
> --- a/kernel/bpf/Makefile
> +++ b/kernel/bpf/Makefile
> @@ -36,3 +36,7 @@ obj-$(CONFIG_BPF_SYSCALL) += bpf_struct_ops.o
> obj-${CONFIG_BPF_LSM} += bpf_lsm.o
> endif
> obj-$(CONFIG_BPF_PRELOAD) += preload/
> +
> +obj-$(CONFIG_BPF_SYSCALL) += relo_core.o
> +$(obj)/relo_core.o: $(srctree)/tools/lib/bpf/relo_core.c FORCE
> + $(call if_changed_rule,cc_o_c)
> diff --git a/tools/lib/bpf/relo_core.c b/tools/lib/bpf/relo_core.c
> index 4016ed492d0c..9d1f309f05fe 100644
> --- a/tools/lib/bpf/relo_core.c
> +++ b/tools/lib/bpf/relo_core.c
> @@ -1,6 +1,98 @@
> // SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
> /* Copyright (c) 2019 Facebook */
>
> +#ifdef __KERNEL__
> +#define RELO_CORE
> +#include <linux/bpf.h>
> +#include <linux/btf.h>
> +#include <linux/string.h>
> +#include "relo_core.h"
> +
> +static const char *btf_kind_str(const struct btf_type *t)
> +{
> + return btf_type_str(t);
> +}
> +
> +static bool str_is_empty(const char *s)
> +{
> + return !s || !s[0];
> +}
> +
> +static bool is_ldimm64_insn(struct bpf_insn *insn)
> +{
> + return insn->code == (BPF_LD | BPF_IMM | BPF_DW);
> +}
> +
> +static const struct btf_type *
> +skip_mods_and_typedefs(const struct btf *btf, u32 id, u32 *res_id)
> +{
> + return btf_type_skip_modifiers(btf, id, res_id);
> +}
> +
> +static const char *btf__name_by_offset(const struct btf *btf, u32 offset)
> +{
> + return btf_name_by_offset(btf, offset);
> +}
> +
> +static s64 btf__resolve_size(const struct btf *btf, u32 type_id)
> +{
> + const struct btf_type *t;
> + int size;
> +
> + t = btf_type_by_id(btf, type_id);
> + t = btf_resolve_size(btf, t, &size);
> + if (IS_ERR(t))
> + return PTR_ERR(t);
> + return size;
> +}
> +
> +static bool bpf_core_is_flavor_sep(const char *s)
> +{
> + /* check X___Y name pattern, where X and Y are not underscores */
> + return s[0] != '_' && /* X */
> + s[1] == '_' && s[2] == '_' && s[3] == '_' && /* ___ */
> + s[4] != '_'; /* Y */
> +}
> +
> +size_t bpf_core_essential_name_len(const char *name)
> +{
> + size_t n = strlen(name);
> + int i;
> +
> + for (i = n - 5; i >= 0; i--) {
> + if (bpf_core_is_flavor_sep(name + i))
> + return i + 1;
> + }
> + return n;
> +}
> +
> +enum libbpf_print_level {
> + LIBBPF_WARN,
> + LIBBPF_INFO,
> + LIBBPF_DEBUG,
> +};
> +__attribute__((format(printf, 2, 3)))
> +void libbpf_print(enum libbpf_print_level level,
> + const char *format, ...)
> +{
> +}
> +#define __pr(level, fmt, ...) \
> +do { \
> + libbpf_print(level, "libbpf: " fmt, ##__VA_ARGS__); \
> +} while (0)
> +
> +#undef pr_warn
> +#undef pr_info
> +#undef pr_debug
> +#define pr_warn(fmt, ...) __pr(LIBBPF_WARN, fmt, ##__VA_ARGS__)
> +#define pr_info(fmt, ...) __pr(LIBBPF_INFO, fmt, ##__VA_ARGS__)
> +#define pr_debug(fmt, ...) __pr(LIBBPF_DEBUG, fmt, ##__VA_ARGS__)
> +int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id,
> + const struct btf *targ_btf, __u32 targ_id)
> +{
> + return 0;
> +}
> +#else
> #include <stdio.h>
> #include <string.h>
> #include <errno.h>
> @@ -12,8 +104,9 @@
> #include "btf.h"
> #include "str_error.h"
> #include "libbpf_internal.h"
> +#endif
>
> -#define BPF_CORE_SPEC_MAX_LEN 64
> +#define BPF_CORE_SPEC_MAX_LEN 32
>
> /* represents BPF CO-RE field or array element accessor */
> struct bpf_core_accessor {
> @@ -662,7 +755,7 @@ static int bpf_core_calc_field_relo(const char *prog_name,
> *validate = true; /* signedness is never ambiguous */
> break;
> case BPF_FIELD_LSHIFT_U64:
> -#if __BYTE_ORDER == __LITTLE_ENDIAN
> +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
> *val = 64 - (bit_off + bit_sz - byte_off * 8);
> #else
> *val = (8 - byte_sz) * 8 + (bit_off - byte_off * 8);
> --
> 2.30.2
>
--
per aspera ad upstream
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [RFC bpf 2/2] btf: adapt relo_core for kernel compilation
2021-09-17 1:21 ` Matteo Croce
@ 2021-09-17 4:12 ` Alexei Starovoitov
2021-09-17 17:45 ` Andrii Nakryiko
0 siblings, 1 reply; 7+ messages in thread
From: Alexei Starovoitov @ 2021-09-17 4:12 UTC (permalink / raw)
To: Matteo Croce
Cc: bpf, Alexei Starovoitov, Arnaldo Carvalho de Melo,
Daniel Borkmann, Andrii Nakryiko
On Thu, Sep 16, 2021 at 6:22 PM Matteo Croce <mcroce@linux.microsoft.com> wrote:
>
> How can we share the helpers source too instead of duplicating it?
Ideally. Yes.
Andrii pointed out that libbpf's btf.h is installed,
so it's part of libbpf api.
Therefore it's safer to rename kernel helpers with equivalent meaning
instead of risking libbpf renames.
>
> Indeed, I found a small difference between the userspace and kernel code.
>
> In tools/lib/bpf/btf.h we have btf_is_mod() which returns true for
> { BTF_KIND_VOLATILE, BTF_KIND_CONST, BTF_KIND_RESTRICT },
> while in kernel/bpf/btf.c we have btf_type_is_modifier() which returns
> true also for BTF_KIND_TYPEDEF.
>
> Which is the right one?
btf_is_mod() is part of libbpf btf.h, so we cannot change it.
btf_type_is_modifier() is kernel internal helper.
It doesn't need to change and doesn't need to match.
The equivalent helpers are
skip_mods_and_typedefs() in the libbpf
and
btf_type_skip_modifiers() in the kernel.
In this case it's probably better to search-and-replace in libbpf.
In most other cases kernel search-and-replace will be necessary.
For example:
btf_type_vlen->btf_vlen
btf_type_member->btf_members
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [RFC bpf 2/2] btf: adapt relo_core for kernel compilation
2021-09-17 4:12 ` Alexei Starovoitov
@ 2021-09-17 17:45 ` Andrii Nakryiko
0 siblings, 0 replies; 7+ messages in thread
From: Andrii Nakryiko @ 2021-09-17 17:45 UTC (permalink / raw)
To: Alexei Starovoitov
Cc: Matteo Croce, bpf, Alexei Starovoitov, Arnaldo Carvalho de Melo,
Daniel Borkmann, Andrii Nakryiko
On Thu, Sep 16, 2021 at 9:12 PM Alexei Starovoitov
<alexei.starovoitov@gmail.com> wrote:
>
> On Thu, Sep 16, 2021 at 6:22 PM Matteo Croce <mcroce@linux.microsoft.com> wrote:
> >
> > How can we share the helpers source too instead of duplicating it?
>
> Ideally. Yes.
> Andrii pointed out that libbpf's btf.h is installed,
> so it's part of libbpf api.
> Therefore it's safer to rename kernel helpers with equivalent meaning
> instead of risking libbpf renames.
>
> >
> > Indeed, I found a small difference between the userspace and kernel code.
> >
> > In tools/lib/bpf/btf.h we have btf_is_mod() which returns true for
> > { BTF_KIND_VOLATILE, BTF_KIND_CONST, BTF_KIND_RESTRICT },
> > while in kernel/bpf/btf.c we have btf_type_is_modifier() which returns
> > true also for BTF_KIND_TYPEDEF.
> >
> > Which is the right one?
>
> btf_is_mod() is part of libbpf btf.h, so we cannot change it.
> btf_type_is_modifier() is kernel internal helper.
> It doesn't need to change and doesn't need to match.
libbpf's btf_is_mod() is not including typedef because there are cases
where typedef shouldn't be skipped. I see one such case in btf_dump.c.
So typedef is certainly not just a modifier from libbpf's point of
view. Kernel doesn't care, though, which is why this difference
exists.
> The equivalent helpers are
> skip_mods_and_typedefs() in the libbpf
> and
> btf_type_skip_modifiers() in the kernel.
> In this case it's probably better to search-and-replace in libbpf.
27 uses in kernel vs 42 in libbpf, so, technically, libbpf should win.
I don't mind mass-renaming of internal helpers, I'd just prefer the
name of the function to reflect the actual logic (where as I pointed
out above, libbpf knows and cares about the distinction between
modifiers (const, volatile, restrict) and typedef). Should we rename
both to btf_type_skip_mods_and_typedefs() or
btf_type_skip_mods_typedefs()?
BTW, kernel might need to start caring about typedefs separately from
modifiers in the context of btf_tag work by Yonghong. Typedefs might
have btf_tags associated with them, I think.
> In most other cases kernel search-and-replace will be necessary.
> For example:
> btf_type_vlen->btf_vlen
> btf_type_member->btf_members
^ permalink raw reply [flat|nested] 7+ messages in thread
end of thread, other threads:[~2021-09-17 17:45 UTC | newest]
Thread overview: 7+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-09-09 13:31 [RFC bpf 0/2] bpf: kernel CO-RE relocation Matteo Croce
2021-09-09 13:31 ` [RFC bpf 1/2] btf: copy relo_core from tools to kernel Matteo Croce
2021-09-09 13:31 ` [RFC bpf 2/2] btf: adapt relo_core for kernel compilation Matteo Croce
2021-09-09 18:23 ` Alexei Starovoitov
2021-09-17 1:21 ` Matteo Croce
2021-09-17 4:12 ` Alexei Starovoitov
2021-09-17 17:45 ` Andrii Nakryiko
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).