kbuild, module, bpf: Support CONFIG_DEBUG_INFO_BTF_EXTRA=m

Allow module-based delivery of potentially large vmlinux .BTF.extra section;
section; also support visibility of BTF data in kernel, modules in
/sys/kernel/btf_extra.

Signed-off-by: Alan Maguire <[email protected]>

Author: alan-maguire

include/linux/bpf.h

@@ -63,6 +63,7 @@ struct inode;
 extern struct idr btf_idr;
 extern spinlock_t btf_idr_lock;
 extern struct kobject *btf_kobj;
+extern struct kobject *btf_extra_kobj;
 extern struct bpf_mem_alloc bpf_global_ma, bpf_global_percpu_ma;
 extern bool bpf_global_ma_set;
 

include/linux/btf.h

@@ -621,6 +621,8 @@ int get_kern_ctx_btf_id(struct bpf_verifier_log *log, enum bpf_prog_type prog_ty
 bool btf_types_are_same(const struct btf *btf1, u32 id1,
 			const struct btf *btf2, u32 id2);
 int btf_check_iter_arg(struct btf *btf, const struct btf_type *func, int arg_idx);
+struct bin_attribute *sysfs_btf_add(struct kobject *kobj, const char *name,
+				    void *data, size_t data_size);
 
 static inline bool btf_type_is_struct_ptr(struct btf *btf, const struct btf_type *t)
 {

include/linux/module.h

@@ -512,6 +512,10 @@ struct module {
 	unsigned int btf_base_data_size;
 	void *btf_data;
 	void *btf_base_data;
+#if IS_ENABLED(CONFIG_DEBUG_INFO_BTF_EXTRA)
+	unsigned int btf_extra_data_size;
+	void *btf_extra_data;
+#endif
 #endif
 #ifdef CONFIG_JUMP_LABEL
 	struct jump_entry *jump_entries;

kernel/bpf/Makefile

@@ -38,6 +38,7 @@ obj-$(CONFIG_BPF_SYSCALL) += reuseport_array.o
 endif
 ifeq ($(CONFIG_SYSFS),y)
 obj-$(CONFIG_DEBUG_INFO_BTF) += sysfs_btf.o
+obj-$(CONFIG_DEBUG_INFO_BTF_EXTRA) += btf_extra.o
 endif
 ifeq ($(CONFIG_BPF_JIT),y)
 obj-$(CONFIG_BPF_SYSCALL) += bpf_struct_ops.o

kernel/bpf/btf.c

@@ -8323,12 +8323,42 @@ enum {
 	BTF_MODULE_F_LIVE = (1 << 0),
 };
 
+#if IS_ENABLED(CONFIG_SYSFS)
+struct bin_attribute *sysfs_btf_add(struct kobject *kobj, const char *name,
+				    void *data, size_t data_size)
+{
+	struct bin_attribute *attr = kzalloc(sizeof(*attr), GFP_KERNEL);
+	int err;
+
+	if (!attr)
+		return ERR_PTR(-ENOMEM);
+
+	sysfs_bin_attr_init(attr);
+	attr->attr.name = name;
+	attr->attr.mode = 0444;
+	attr->size = data_size;
+	attr->private = data;
+	attr->read = sysfs_bin_attr_simple_read;
+
+	err = sysfs_create_bin_file(kobj, attr);
+	if (err) {
+		pr_warn("failed to register module [%s] BTF in sysfs : %d\n", name, err);
+		kfree(attr);
+		return ERR_PTR(err);
+	}
+	return attr;
+}
+
+#endif
+
 #ifdef CONFIG_DEBUG_INFO_BTF_MODULES
 struct btf_module {
 	struct list_head list;
 	struct module *module;
 	struct btf *btf;
 	struct bin_attribute *sysfs_attr;
+	void *btf_extra_data;
+	struct bin_attribute *sysfs_extra_attr;
 	int flags;
 };
 
@@ -8342,12 +8372,12 @@ static int btf_module_notify(struct notifier_block *nb, unsigned long op,
 {
 	struct btf_module *btf_mod, *tmp;
 	struct module *mod = module;
-	struct btf *btf;
+	struct bin_attribute *attr;
+	struct btf *btf = NULL;
 	int err = 0;
 
-	if (mod->btf_data_size == 0 ||
-	    (op != MODULE_STATE_COMING && op != MODULE_STATE_LIVE &&
-	     op != MODULE_STATE_GOING))
+	if (op != MODULE_STATE_COMING && op != MODULE_STATE_LIVE &&
+	     op != MODULE_STATE_GOING)
 		goto out;
 
 	switch (op) {
@@ -8357,8 +8387,10 @@ static int btf_module_notify(struct notifier_block *nb, unsigned long op,
 			err = -ENOMEM;
 			goto out;
 		}
-		btf = btf_parse_module(mod->name, mod->btf_data, mod->btf_data_size,
-				       mod->btf_base_data, mod->btf_base_data_size);
+		if (mod->btf_data_size > 0) {
+			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)) {
@@ -8370,7 +8402,8 @@ static int btf_module_notify(struct notifier_block *nb, unsigned long op,
 			}
 			goto out;
 		}
-		err = btf_alloc_id(btf);
+		if (btf)
+			err = btf_alloc_id(btf);
 		if (err) {
 			btf_free(btf);
 			kfree(btf_mod);
@@ -8384,32 +8417,45 @@ static int btf_module_notify(struct notifier_block *nb, unsigned long op,
 		list_add(&btf_mod->list, &btf_modules);
 		mutex_unlock(&btf_module_mutex);
 
-		if (IS_ENABLED(CONFIG_SYSFS)) {
-			struct bin_attribute *attr;
-
-			attr = kzalloc(sizeof(*attr), GFP_KERNEL);
-			if (!attr)
-				goto out;
-
-			sysfs_bin_attr_init(attr);
-			attr->attr.name = btf->name;
-			attr->attr.mode = 0444;
-			attr->size = btf->data_size;
-			attr->private = btf->data;
-			attr->read = sysfs_bin_attr_simple_read;
-
-			err = sysfs_create_bin_file(btf_kobj, attr);
-			if (err) {
-				pr_warn("failed to register module [%s] BTF in sysfs: %d\n",
-					mod->name, err);
-				kfree(attr);
-				err = 0;
+		if (IS_ENABLED(CONFIG_SYSFS) && btf) {
+			attr = sysfs_btf_add(btf_kobj, btf->name, btf->data, btf->data_size);
+			if (IS_ERR(attr)) {
+				err = PTR_ERR(attr);
 				goto out;
 			}
-
 			btf_mod->sysfs_attr = attr;
 		}
+#if IS_ENABLED(CONFIG_DEBUG_INFO_BTF_EXTRA)
+		if (mod->btf_extra_data_size > 0) {
+			const char *name = mod->name;
+			void *data;
 
+			/* vmlinux .BTF.extra is SHF_ALLOC; other modules
+			 * are not, so for them we need to kvmemdup() the data.
+			 */
+			if (strcmp(mod->name, "btf_extra") == 0) {
+				name = "vmlinux";
+				data = mod->btf_extra_data;
+			} else {
+				data = kvmemdup(mod->btf_extra_data, mod->btf_extra_data_size,
+						GFP_KERNEL | __GFP_NOWARN);
+				if (!data) {
+					err = -ENOMEM;
+					goto out;
+				}
+				btf_mod->btf_extra_data = data;
+			}
+			attr = sysfs_btf_add(btf_extra_kobj, name, data,
+					     mod->btf_extra_data_size);
+			if (IS_ERR(attr)) {
+				err = PTR_ERR(attr);
+				kfree(btf_mod->sysfs_attr);
+				kvfree(btf_mod->btf_extra_data);
+				goto out;
+			}
+			btf_mod->sysfs_extra_attr = attr;
+		}
+#endif
 		break;
 	case MODULE_STATE_LIVE:
 		mutex_lock(&btf_module_mutex);
@@ -8431,9 +8477,15 @@ static int btf_module_notify(struct notifier_block *nb, unsigned long op,
 			list_del(&btf_mod->list);
 			if (btf_mod->sysfs_attr)
 				sysfs_remove_bin_file(btf_kobj, btf_mod->sysfs_attr);
-			purge_cand_cache(btf_mod->btf);
-			btf_put(btf_mod->btf);
-			kfree(btf_mod->sysfs_attr);
+			if (btf_mod->btf_extra_data)
+				kvfree(btf_mod->btf_extra_data);
+			if (btf_mod->sysfs_extra_attr)
+				sysfs_remove_bin_file(btf_extra_kobj, btf_mod->sysfs_extra_attr);
+			if (btf_mod->btf) {
+				purge_cand_cache(btf_mod->btf);
+				btf_put(btf_mod->btf);
+				kfree(btf_mod->sysfs_attr);
+			}
 			kfree(btf_mod);
 			break;
 		}

kernel/bpf/btf_extra.c

@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025, Oracle and/or its affiliates. */
+/*
+ * Provide extra kernel BTF information for use by BPF tools.
+ *
+ * Can be built as a module to support cases where vmlinux .BTF.extra
+ * section size in the vmlinux image is too much.
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+
+static int __init btf_extra_init(void)
+{
+	return 0;
+}
+subsys_initcall(btf_extra_init);
+
+static void __exit btf_extra_exit(void)
+{
+}
+module_exit(btf_extra_exit);
+
+MODULE_DESCRIPTION("Extra BTF information");
+MODULE_LICENSE("GPL v2");

kernel/bpf/sysfs_btf.c

@@ -49,7 +49,15 @@ static struct bin_attribute bin_attr_btf_vmlinux __ro_after_init = {
 	.mmap = btf_sysfs_vmlinux_mmap,
 };
 
-struct kobject *btf_kobj;
+struct kobject *btf_kobj, *btf_extra_kobj;
+
+#if IS_BUILTIN(CONFIG_DEBUG_INFO_BTF_EXTRA)
+/* See scripts/link-vmlinux.sh, gen_btf() func for details */
+extern char __start_BTF_extra[];
+extern char __stop_BTF_extra[];
+
+struct bin_attribute *extra_attr;
+#endif
 
 static int __init btf_vmlinux_init(void)
 {
@@ -62,6 +70,17 @@ static int __init btf_vmlinux_init(void)
 	btf_kobj = kobject_create_and_add("btf", kernel_kobj);
 	if (!btf_kobj)
 		return -ENOMEM;
+	if (IS_ENABLED(CONFIG_DEBUG_INFO_BTF_EXTRA)) {
+		btf_extra_kobj = kobject_create_and_add("btf_extra", kernel_kobj);
+		if (!btf_extra_kobj)
+			return -ENOMEM;
+#if IS_BUILTIN(CONFIG_DEBUG_INFO_BTF_EXTRA)
+		extra_attr = sysfs_btf_add(btf_extra_kobj, "vmlinux", __start_BTF_extra,
+					   __stop_BTF_extra - __start_BTF_extra);
+		if (IS_ERR(extra_attr))
+			return PTR_ERR(extra_attr);
+#endif
+	}
 
 	return sysfs_create_bin_file(btf_kobj, &bin_attr_btf_vmlinux);
 }

kernel/module/main.c

@@ -2648,6 +2648,10 @@ static int find_module_sections(struct module *mod, struct load_info *info)
 	mod->btf_base_data = any_section_objs(info, ".BTF.base", 1,
 					      &mod->btf_base_data_size);
 #endif
+#if IS_ENABLED(CONFIG_DEBUG_INFO_BTF_EXTRA)
+	mod->btf_extra_data = any_section_objs(info, ".BTF.extra", 1,
+					       &mod->btf_extra_data_size);
+#endif
 #ifdef CONFIG_JUMP_LABEL
 	mod->jump_entries = section_objs(info, "__jump_table",
 					sizeof(*mod->jump_entries),

lib/Kconfig.debug

@@ -434,7 +434,7 @@ config MODULE_ALLOW_BTF_MISMATCH
 	  it when a mismatch is found.
 
 config DEBUG_INFO_BTF_EXTRA
-	bool "Provide extra information about inline sites in BTF"
+	tristate "Provide extra information about inline sites in BTF"
 	default n
 	depends on DEBUG_INFO_BTF && PAHOLE_HAS_INLINE
 	help

scripts/Makefile.btf

@@ -32,7 +32,7 @@ module-pahole-flags-$(call test-ge, $(pahole-ver), 128) += --btf_features=distil
 else
 ifneq ($(CONFIG_DEBUG_INFO_BTF_EXTRA),)
 pahole-flags-$(call test-ge, $(pahole-ver), 130) += --btf_features=inline.extra
-btf-extra := y
+btf-extra := $(CONFIG_DEBUG_INFO_BTF_EXTRA)
 endif
 endif
 
@@ -43,3 +43,4 @@ pahole-flags-$(CONFIG_PAHOLE_HAS_LANG_EXCLUDE)		+= --lang_exclude=rust
 export PAHOLE_FLAGS := $(pahole-flags-y)
 export MODULE_PAHOLE_FLAGS := $(module-pahole-flags-y)
 export BTF_EXTRA := $(btf-extra)
+export VMLINUX_BTF_EXTRA := .tmp_vmlinux_btf_extra