libbpf,bpf: Share BTF relocate-related code with kernel

Share relocation implementation with the kernel. As part of this,
we also need the type/string iteration functions so also share
btf_iter.c file. Relocation code in kernel and userspace is identical
save for the impementation of the reparenting of split BTF to the
relocated base BTF and retrieval of the BTF header from "struct btf";
these small functions need separate user-space and kernel implementations
for the separate "struct btf"s they operate upon.

One other wrinkle on the kernel side is we have to map .BTF.ids in
modules as they were generated with the type ids used at BTF encoding
time. btf_relocate() optionally returns an array mapping from old BTF
ids to relocated ids, so we use that to fix up these references where
needed for kfuncs.

Signed-off-by: Alan Maguire <[e-mail]>
Signed-off-by: Andrii Nakryiko <[e-mail]>
Acked-by: Eduard Zingerman <[e-mail]>
Link: https://lore.kernel.org/bpf/[e-mail]

include/linux/btf.h

···
 const char *btf_get_name(const struct btf *btf);
 void btf_get(struct btf *btf);
 void btf_put(struct btf *btf);
+const struct btf_header *btf_header(const struct btf *btf);
 int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr, u32 uattr_sz);
 struct btf *btf_get_by_fd(int fd);
 int btf_get_info_by_fd(const struct btf *btf,
···
 u32 btf_obj_id(const struct btf *btf);
 bool btf_is_kernel(const struct btf *btf);
 bool btf_is_module(const struct btf *btf);
+bool btf_is_vmlinux(const struct btf *btf);
 struct module *btf_try_get_module(const struct btf *btf);
 u32 btf_nr_types(const struct btf *btf);
+struct btf *btf_base_btf(const struct btf *btf);
 bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
 			   const struct btf_member *m,
 			   u32 expected_offset, u32 expected_size);
···
 static inline u8 btf_int_offset(const struct btf_type *t)
 {
 	return BTF_INT_OFFSET(*(u32 *)(t + 1));
+}
+
+static inline __u8 btf_int_bits(const struct btf_type *t)
+{
+	return BTF_INT_BITS(*(__u32 *)(t + 1));
 }
 
 static inline bool btf_type_is_scalar(const struct btf_type *t)
···
 	return (struct btf_param *)(t + 1);
 }
 
+static inline struct btf_decl_tag *btf_decl_tag(const struct btf_type *t)
+{
+	return (struct btf_decl_tag *)(t + 1);
+}
+
 static inline int btf_id_cmp_func(const void *a, const void *b)
 {
 	const int *pa = a, *pb = b;
···
 }
 #endif
 
+enum btf_field_iter_kind {
+	BTF_FIELD_ITER_IDS,
+	BTF_FIELD_ITER_STRS,
+};
+
+struct btf_field_desc {
+	/* once-per-type offsets */
+	int t_off_cnt, t_offs[2];
+	/* member struct size, or zero, if no members */
+	int m_sz;
+	/* repeated per-member offsets */
+	int m_off_cnt, m_offs[1];
+};
+
+struct btf_field_iter {
+	struct btf_field_desc desc;
+	void *p;
+	int m_idx;
+	int off_idx;
+	int vlen;
+};
+
 #ifdef CONFIG_BPF_SYSCALL
 const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);
+void btf_set_base_btf(struct btf *btf, const struct btf *base_btf);
+int btf_relocate(struct btf *btf, const struct btf *base_btf, __u32 **map_ids);
+int btf_field_iter_init(struct btf_field_iter *it, struct btf_type *t,
+			enum btf_field_iter_kind iter_kind);
+__u32 *btf_field_iter_next(struct btf_field_iter *it);
+
 const char *btf_name_by_offset(const struct btf *btf, u32 offset);
+const char *btf_str_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);
 u32 *btf_kfunc_id_set_contains(const struct btf *btf, u32 kfunc_btf_id,
···
 {
 	return NULL;
 }
+
+static inline void btf_set_base_btf(struct btf *btf, const struct btf *base_btf)
+{
+}
+
+static inline int btf_relocate(void *log, struct btf *btf, const struct btf *base_btf,
+			       __u32 **map_ids)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int btf_field_iter_init(struct btf_field_iter *it, struct btf_type *t,
+				      enum btf_field_iter_kind iter_kind)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline __u32 *btf_field_iter_next(struct btf_field_iter *it)
+{
+	return NULL;
+}
+
 static inline const char *btf_name_by_offset(const struct btf *btf,
 					     u32 offset)
 {

kernel/bpf/Makefile

···
 obj-$(CONFIG_BPF_PRELOAD) += preload/
 
 obj-$(CONFIG_BPF_SYSCALL) += relo_core.o
-$(obj)/relo_core.o: $(srctree)/tools/lib/bpf/relo_core.c FORCE
+obj-$(CONFIG_BPF_SYSCALL) += btf_iter.o
+obj-$(CONFIG_BPF_SYSCALL) += btf_relocate.o
+
+# Some source files are common to libbpf.
+vpath %.c $(srctree)/kernel/bpf:$(srctree)/tools/lib/bpf
+
+$(obj)/%.o: %.c FORCE
 	$(call if_changed_rule,cc_o_c)

kernel/bpf/btf.c

···
 	u32 start_str_off; /* first string offset (0 for base BTF) */
 	char name[MODULE_NAME_LEN];
 	bool kernel_btf;
+	__u32 *base_id_map; /* map from distilled base BTF -> vmlinux BTF ids */
 };
 
 enum verifier_phase {
···
 	       btf_type_is_var(t) || btf_type_is_typedef(t);
 }
 
+bool btf_is_vmlinux(const struct btf *btf)
+{
+	return btf->kernel_btf && !btf->base_btf;
+}
+
 u32 btf_nr_types(const struct btf *btf)
 {
 	u32 total = 0;
···
 	return true;
 }
 
-static const char *btf_str_by_offset(const struct btf *btf, u32 offset)
+const char *btf_str_by_offset(const struct btf *btf, u32 offset)
 {
 	while (offset < btf->start_str_off)
 		btf = btf->base_btf;
···
 
 	if (!tab)
 		return;
-	/* For module BTF, we directly assign the sets being registered, so
-	 * there is nothing to free except kfunc_set_tab.
-	 */
-	if (btf_is_module(btf))
-		goto free_tab;
 	for (hook = 0; hook < ARRAY_SIZE(tab->sets); hook++)
 		kfree(tab->sets[hook]);
-free_tab:
 	kfree(tab);
 	btf->kfunc_set_tab = NULL;
 }
···
 	kvfree(btf->types);
 	kvfree(btf->resolved_sizes);
 	kvfree(btf->resolved_ids);
-	kvfree(btf->data);
+	/* vmlinux does not allocate btf->data, it simply points it at
+	 * __start_BTF.
+	 */
+	if (!btf_is_vmlinux(btf))
+		kvfree(btf->data);
+	kvfree(btf->base_id_map);
 	kfree(btf);
 }
 
···
 		btf_free_id(btf);
 		call_rcu(&btf->rcu, btf_free_rcu);
 	}
+}
+
+struct btf *btf_base_btf(const struct btf *btf)
+{
+	return btf->base_btf;
+}
+
+const struct btf_header *btf_header(const struct btf *btf)
+{
+	return &btf->hdr;
+}
+
+void btf_set_base_btf(struct btf *btf, const struct btf *base_btf)
+{
+	btf->base_btf = (struct btf *)base_btf;
+	btf->start_id = btf_nr_types(base_btf);
+	btf->start_str_off = base_btf->hdr.str_len;
 }
 
 static int env_resolve_init(struct btf_verifier_env *env)
···
 BTF_ID_LIST(bpf_ctx_convert_btf_id)
 BTF_ID(struct, bpf_ctx_convert)
 
-struct btf *btf_parse_vmlinux(void)
+static struct btf *btf_parse_base(struct btf_verifier_env *env, const char *name,
+				  void *data, unsigned int data_size)
 {
-	struct btf_verifier_env *env = NULL;
-	struct bpf_verifier_log *log;
 	struct btf *btf = NULL;
 	int err;
 
 	if (!IS_ENABLED(CONFIG_DEBUG_INFO_BTF))
 		return ERR_PTR(-ENOENT);
-
-	env = kzalloc(sizeof(*env), GFP_KERNEL | __GFP_NOWARN);
-	if (!env)
-		return ERR_PTR(-ENOMEM);
-
-	log = &env->log;
-	log->level = BPF_LOG_KERNEL;
 
 	btf = kzalloc(sizeof(*btf), GFP_KERNEL | __GFP_NOWARN);
 	if (!btf) {
···
 	}
 	env->btf = btf;
 
-	btf->data = __start_BTF;
-	btf->data_size = __stop_BTF - __start_BTF;
+	btf->data = data;
+	btf->data_size = data_size;
 	btf->kernel_btf = true;
-	snprintf(btf->name, sizeof(btf->name), "vmlinux");
+	snprintf(btf->name, sizeof(btf->name), "%s", name);
 
 	err = btf_parse_hdr(env);
 	if (err)
···
 	if (err)
 		goto errout;
 
-	/* btf_parse_vmlinux() runs under bpf_verifier_lock */
-	bpf_ctx_convert.t = btf_type_by_id(btf, bpf_ctx_convert_btf_id[0]);
-
 	refcount_set(&btf->refcnt, 1);
 
-	err = btf_alloc_id(btf);
-	if (err)
-		goto errout;
-
-	btf_verifier_env_free(env);
 	return btf;
 
 errout:
-	btf_verifier_env_free(env);
 	if (btf) {
 		kvfree(btf->types);
 		kfree(btf);
···
 	return ERR_PTR(err);
 }
 
-#ifdef CONFIG_DEBUG_INFO_BTF_MODULES
-
-static struct btf *btf_parse_module(const char *module_name, const void *data, unsigned int data_size)
+struct btf *btf_parse_vmlinux(void)
 {
 	struct btf_verifier_env *env = NULL;
 	struct bpf_verifier_log *log;
-	struct btf *btf = NULL, *base_btf;
+	struct btf *btf;
 	int err;
 
-	base_btf = bpf_get_btf_vmlinux();
-	if (IS_ERR(base_btf))
-		return base_btf;
-	if (!base_btf)
+	env = kzalloc(sizeof(*env), GFP_KERNEL | __GFP_NOWARN);
+	if (!env)
+		return ERR_PTR(-ENOMEM);
+
+	log = &env->log;
+	log->level = BPF_LOG_KERNEL;
+	btf = btf_parse_base(env, "vmlinux", __start_BTF, __stop_BTF - __start_BTF);
+	if (IS_ERR(btf))
+		goto err_out;
+
+	/* btf_parse_vmlinux() runs under bpf_verifier_lock */
+	bpf_ctx_convert.t = btf_type_by_id(btf, bpf_ctx_convert_btf_id[0]);
+	err = btf_alloc_id(btf);
+	if (err) {
+		btf_free(btf);
+		btf = ERR_PTR(err);
+	}
+err_out:
+	btf_verifier_env_free(env);
+	return btf;
+}
+
+#ifdef CONFIG_DEBUG_INFO_BTF_MODULES
+
+/* If .BTF_ids section was created with distilled base BTF, both base and
+ * split BTF ids will need to be mapped to actual base/split ids for
+ * BTF now that it has been relocated.
+ */
+static __u32 btf_relocate_id(const struct btf *btf, __u32 id)
+{
+	if (!btf->base_btf || !btf->base_id_map)
+		return id;
+	return btf->base_id_map[id];
+}
+
+static struct btf *btf_parse_module(const char *module_name, const void *data,
+				    unsigned int data_size, void *base_data,
+				    unsigned int base_data_size)
+{
+	struct btf *btf = NULL, *vmlinux_btf, *base_btf = NULL;
+	struct btf_verifier_env *env = NULL;
+	struct bpf_verifier_log *log;
+	int err = 0;
+
+	vmlinux_btf = bpf_get_btf_vmlinux();
+	if (IS_ERR(vmlinux_btf))
+		return vmlinux_btf;
+	if (!vmlinux_btf)
 		return ERR_PTR(-EINVAL);
 
 	env = kzalloc(sizeof(*env), GFP_KERNEL | __GFP_NOWARN);
···
 
 	log = &env->log;
 	log->level = BPF_LOG_KERNEL;
+
+	if (base_data) {
+		base_btf = btf_parse_base(env, ".BTF.base", base_data, base_data_size);
+		if (IS_ERR(base_btf)) {
+			err = PTR_ERR(base_btf);
+			goto errout;
+		}
+	} else {
+		base_btf = vmlinux_btf;
+	}
 
 	btf = kzalloc(sizeof(*btf), GFP_KERNEL | __GFP_NOWARN);
 	if (!btf) {
···
 	if (err)
 		goto errout;
 
+	if (base_btf != vmlinux_btf) {
+		err = btf_relocate(btf, vmlinux_btf, &btf->base_id_map);
+		if (err)
+			goto errout;
+		btf_free(base_btf);
+		base_btf = vmlinux_btf;
+	}
+
 	btf_verifier_env_free(env);
 	refcount_set(&btf->refcnt, 1);
 	return btf;
 
 errout:
 	btf_verifier_env_free(env);
+	if (base_btf != vmlinux_btf)
+		btf_free(base_btf);
 	if (btf) {
 		kvfree(btf->data);
 		kvfree(btf->types);
···
 			err = -ENOMEM;
 			goto out;
 		}
-		btf = btf_parse_module(mod->name, mod->btf_data, mod->btf_data_size);
+		btf = btf_parse_module(mod->name, mod->btf_data, mod->btf_data_size,
+				       mod->btf_base_data, mod->btf_base_data_size);
 		if (IS_ERR(btf)) {
 			kfree(btf_mod);
 			if (!IS_ENABLED(CONFIG_MODULE_ALLOW_BTF_MISMATCH)) {
···
 	bool add_filter = !!kset->filter;
 	struct btf_kfunc_set_tab *tab;
 	struct btf_id_set8 *set;
-	u32 set_cnt;
+	u32 set_cnt, i;
 	int ret;
 
 	if (hook >= BTF_KFUNC_HOOK_MAX) {
···
 		goto end;
 	}
 
-	/* We don't need to allocate, concatenate, and sort module sets, because
-	 * only one is allowed per hook. Hence, we can directly assign the
-	 * pointer and return.
-	 */
-	if (!vmlinux_set) {
-		tab->sets[hook] = add_set;
-		goto do_add_filter;
-	}
-
 	/* In case of vmlinux sets, there may be more than one set being
 	 * registered per hook. To create a unified set, we allocate a new set
 	 * and concatenate all individual sets being registered. While each set
 	 * is individually sorted, they may become unsorted when concatenated,
 	 * hence re-sorting the final set again is required to make binary
 	 * searching the set using btf_id_set8_contains function work.
+	 *
+	 * For module sets, we need to allocate as we may need to relocate
+	 * BTF ids.
 	 */
 	set_cnt = set ? set->cnt : 0;
 
···
 
 	/* Concatenate the two sets */
 	memcpy(set->pairs + set->cnt, add_set->pairs, add_set->cnt * sizeof(set->pairs[0]));
+	/* Now that the set is copied, update with relocated BTF ids */
+	for (i = set->cnt; i < set->cnt + add_set->cnt; i++)
+		set->pairs[i].id = btf_relocate_id(btf, set->pairs[i].id);
+
 	set->cnt += add_set->cnt;
 
 	sort(set->pairs, set->cnt, sizeof(set->pairs[0]), btf_id_cmp_func, NULL);
 
-do_add_filter:
 	if (add_filter) {
 		hook_filter = &tab->hook_filters[hook];
 		hook_filter->filters[hook_filter->nr_filters++] = kset->filter;
···
 		return PTR_ERR(btf);
 
 	for (i = 0; i < kset->set->cnt; i++) {
-		ret = btf_check_kfunc_protos(btf, kset->set->pairs[i].id,
+		ret = btf_check_kfunc_protos(btf, btf_relocate_id(btf, kset->set->pairs[i].id),
 					     kset->set->pairs[i].flags);
 		if (ret)
 			goto err_out;
···
 	u32 nr_args, i;
 
 	for (i = 0; i < cnt; i++) {
-		dtor_btf_id = dtors[i].kfunc_btf_id;
+		dtor_btf_id = btf_relocate_id(btf, dtors[i].kfunc_btf_id);
 
 		dtor_func = btf_type_by_id(btf, dtor_btf_id);
 		if (!dtor_func || !btf_type_is_func(dtor_func))
···
 {
 	struct btf_id_dtor_kfunc_tab *tab;
 	struct btf *btf;
-	u32 tab_cnt;
+	u32 tab_cnt, i;
 	int ret;
 
 	btf = btf_get_module_btf(owner);
···
 	btf->dtor_kfunc_tab = tab;
 
 	memcpy(tab->dtors + tab->cnt, dtors, add_cnt * sizeof(tab->dtors[0]));
+
+	/* remap BTF ids based on BTF relocation (if any) */
+	for (i = tab_cnt; i < tab_cnt + add_cnt; i++) {
+		tab->dtors[i].btf_id = btf_relocate_id(btf, tab->dtors[i].btf_id);
+		tab->dtors[i].kfunc_btf_id = btf_relocate_id(btf, tab->dtors[i].kfunc_btf_id);
+	}
+
 	tab->cnt += add_cnt;
 
 	sort(tab->dtors, tab->cnt, sizeof(tab->dtors[0]), btf_id_cmp_func, NULL);

tools/lib/bpf/btf_iter.c

···
 /* Copyright (c) 2021 Facebook */
 /* Copyright (c) 2024, Oracle and/or its affiliates. */
 
+#ifdef __KERNEL__
+#include <linux/bpf.h>
+#include <linux/btf.h>
+
+#define btf_var_secinfos(t)	(struct btf_var_secinfo *)btf_type_var_secinfo(t)
+
+#else
 #include "btf.h"
 #include "libbpf_internal.h"
+#endif
 
 int btf_field_iter_init(struct btf_field_iter *it, struct btf_type *t,
 			enum btf_field_iter_kind iter_kind)

tools/lib/bpf/btf_relocate.c

···
 #define _GNU_SOURCE
 #endif
 
+#ifdef __KERNEL__
+#include <linux/bpf.h>
+#include <linux/bsearch.h>
+#include <linux/btf.h>
+#include <linux/sort.h>
+#include <linux/string.h>
+#include <linux/bpf_verifier.h>
+
+#define btf_type_by_id				(struct btf_type *)btf_type_by_id
+#define btf__type_cnt				btf_nr_types
+#define btf__base_btf				btf_base_btf
+#define btf__name_by_offset			btf_name_by_offset
+#define btf__str_by_offset			btf_str_by_offset
+#define btf_kflag				btf_type_kflag
+
+#define calloc(nmemb, sz)			kvcalloc(nmemb, sz, GFP_KERNEL | __GFP_NOWARN)
+#define free(ptr)				kvfree(ptr)
+#define qsort(base, num, sz, cmp)		sort(base, num, sz, cmp, NULL)
+
+#else
+
 #include "btf.h"
 #include "bpf.h"
 #include "libbpf.h"
 #include "libbpf_internal.h"
+
+#endif /* __KERNEL__ */
 
 struct btf;