User space needs access to kernel BTF for many modern features of BPF.
Right now each process needs to read the BTF blob either in pieces or
as a whole. Allow mmaping the sysfs file so that processes can directly
access the memory allocated for it in the kernel.

Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
---
 include/asm-generic/vmlinux.lds.h |  3 ++-
 kernel/bpf/sysfs_btf.c            | 25 +++++++++++++++++++++++--
 2 files changed, 25 insertions(+), 3 deletions(-)

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 58a635a6d5bdf0c53c267c2a3d21a5ed8678ce73..1750390735fac7637cc4d2fa05f96cb2a36aa448 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -667,10 +667,11 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
  */
 #ifdef CONFIG_DEBUG_INFO_BTF
 #define BTF								\
+	. = ALIGN(PAGE_SIZE);						\
 	.BTF : AT(ADDR(.BTF) - LOAD_OFFSET) {				\
 		BOUNDED_SECTION_BY(.BTF, _BTF)				\
 	}								\
-	. = ALIGN(4);							\
+	. = ALIGN(PAGE_SIZE);						\
 	.BTF_ids : AT(ADDR(.BTF_ids) - LOAD_OFFSET) {			\
 		*(.BTF_ids)						\
 	}
diff --git a/kernel/bpf/sysfs_btf.c b/kernel/bpf/sysfs_btf.c
index 81d6cf90584a7157929c50f62a5c6862e7a3d081..7651f37b82c78b8afd96078567a5b6612f5f4d97 100644
--- a/kernel/bpf/sysfs_btf.c
+++ b/kernel/bpf/sysfs_btf.c
@@ -7,18 +7,39 @@
 #include <linux/kobject.h>
 #include <linux/init.h>
 #include <linux/sysfs.h>
+#include <linux/mm.h>
+#include <linux/io.h>
 
 /* See scripts/link-vmlinux.sh, gen_btf() func for details */
 extern char __start_BTF[];
 extern char __stop_BTF[];
 
+struct kobject *btf_kobj;
+
+static int btf_vmlinux_mmap(struct file *filp, struct kobject *kobj,
+			    const struct bin_attribute *attr,
+			    struct vm_area_struct *vma)
+{
+	size_t btf_size = __stop_BTF - __start_BTF;
+
+	if (kobj != btf_kobj)
+		return -EINVAL;
+
+	if (vma->vm_flags & (VM_WRITE|VM_EXEC|VM_MAYSHARE))
+		return -EACCES;
+
+	vm_flags_clear(vma, VM_MAYEXEC);
+	vm_flags_clear(vma, VM_MAYWRITE);
+
+	return vm_iomap_memory(vma, virt_to_phys(__start_BTF), btf_size);
+}
+
 static struct bin_attribute bin_attr_btf_vmlinux __ro_after_init = {
 	.attr = { .name = "vmlinux", .mode = 0444, },
 	.read_new = sysfs_bin_attr_simple_read,
+	.mmap = btf_vmlinux_mmap,
 };
 
-struct kobject *btf_kobj;
-
 static int __init btf_vmlinux_init(void)
 {
 	bin_attr_btf_vmlinux.private = __start_BTF;

-- 
2.49.0

On Thu, May 1, 2025 at 7:28 AM Lorenz Bauer <lmb@isovalent.com> wrote:
>
> User space needs access to kernel BTF for many modern features of BPF.
> Right now each process needs to read the BTF blob either in pieces or
> as a whole. Allow mmaping the sysfs file so that processes can directly
> access the memory allocated for it in the kernel.
>
> Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
> ---
>  include/asm-generic/vmlinux.lds.h |  3 ++-
>  kernel/bpf/sysfs_btf.c            | 25 +++++++++++++++++++++++--
>  2 files changed, 25 insertions(+), 3 deletions(-)
>
> diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
> index 58a635a6d5bdf0c53c267c2a3d21a5ed8678ce73..1750390735fac7637cc4d2fa05f96cb2a36aa448 100644
> --- a/include/asm-generic/vmlinux.lds.h
> +++ b/include/asm-generic/vmlinux.lds.h
> @@ -667,10 +667,11 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
>   */
>  #ifdef CONFIG_DEBUG_INFO_BTF
>  #define BTF                                                            \
> +       . = ALIGN(PAGE_SIZE);                                           \
>         .BTF : AT(ADDR(.BTF) - LOAD_OFFSET) {                           \
>                 BOUNDED_SECTION_BY(.BTF, _BTF)                          \
>         }                                                               \
> -       . = ALIGN(4);                                                   \
> +       . = ALIGN(PAGE_SIZE);                                           \
>         .BTF_ids : AT(ADDR(.BTF_ids) - LOAD_OFFSET) {                   \
>                 *(.BTF_ids)                                             \
>         }
> diff --git a/kernel/bpf/sysfs_btf.c b/kernel/bpf/sysfs_btf.c
> index 81d6cf90584a7157929c50f62a5c6862e7a3d081..7651f37b82c78b8afd96078567a5b6612f5f4d97 100644
> --- a/kernel/bpf/sysfs_btf.c
> +++ b/kernel/bpf/sysfs_btf.c
> @@ -7,18 +7,39 @@
>  #include <linux/kobject.h>
>  #include <linux/init.h>
>  #include <linux/sysfs.h>
> +#include <linux/mm.h>
> +#include <linux/io.h>
>
>  /* See scripts/link-vmlinux.sh, gen_btf() func for details */
>  extern char __start_BTF[];
>  extern char __stop_BTF[];
>
> +struct kobject *btf_kobj;
> +
> +static int btf_vmlinux_mmap(struct file *filp, struct kobject *kobj,
> +                           const struct bin_attribute *attr,
> +                           struct vm_area_struct *vma)
> +{
> +       size_t btf_size = __stop_BTF - __start_BTF;
> +
> +       if (kobj != btf_kobj)
> +               return -EINVAL;
> +
> +       if (vma->vm_flags & (VM_WRITE|VM_EXEC|VM_MAYSHARE))
> +               return -EACCES;
> +
> +       vm_flags_clear(vma, VM_MAYEXEC);
> +       vm_flags_clear(vma, VM_MAYWRITE);

Probably should set VM_DONTDUMP to avoid being in the core dump.
vm_flags_mod() can set and clear in one operation.

> +
> +       return vm_iomap_memory(vma, virt_to_phys(__start_BTF), btf_size);

and this one should probably be vm_insert_pages().
Since it's not an IO area.

Overall I think it's a good idea.
As Daniel suggested pls make use of it in libbpf too.
That exercise will make sure that feature probing works
with fallback.

pw-bot: cr

On Thu, May 1, 2025 at 9:26 PM Alexei Starovoitov
<alexei.starovoitov@gmail.com> wrote:
> > +
> > +       return vm_iomap_memory(vma, virt_to_phys(__start_BTF), btf_size);
>
> and this one should probably be vm_insert_pages().
> Since it's not an IO area.

FYI I went with open coding with remap_pfn_range since that allows me
to avoid struct page.

Lorenz