Re: [PATCH bpf-next v3 1/3] btf: allow mmap of vmlinux btf

On Mon, May 5, 2025 at 11:39 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 | 37 +++++++++++++++++++++++++++++++++++++ 2 files changed, 39 insertions(+), 1 deletion(-)

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..37278d7f38ae72f2d7efcfa859e86aaf12e39a25 100644 --- a/kernel/bpf/sysfs_btf.c +++ b/kernel/bpf/sysfs_btf.c @@ -7,14 +7,51 @@ #include <linux/kobject.h> #include <linux/init.h> #include <linux/sysfs.h> +#include <linux/mm.h> +#include <linux/io.h> +#include <linux/btf.h>

/* See scripts/link-vmlinux.sh, gen_btf() func for details */ extern char __start_BTF[]; extern char __stop_BTF[];

+static int btf_sysfs_vmlinux_mmap(struct file *filp, struct kobject *kobj,

•                             const struct bin_attribute *attr,
  

•                             struct vm_area_struct *vma)
  

+{

•   unsigned long pages = PAGE_ALIGN(attr->size) >> PAGE_SHIFT;
  

•   size_t vm_size = vma->vm_end - vma->vm_start;
  

•   unsigned long addr = (unsigned long)attr->private;
  

•   int i, err = 0;
  

•   if (addr != (unsigned long)__start_BTF || !PAGE_ALIGNED(addr))
  

•           return -EINVAL;
  

•   if (vma->vm_pgoff)
  

•           return -EINVAL;
  

any particular reason to not allow vm_pgoff?

•   if (vma->vm_flags & (VM_WRITE | VM_EXEC | VM_MAYSHARE))
  

•           return -EACCES;
  

•   if (vm_size >> PAGE_SHIFT > pages)
  

() around shift operation, please, for those of us who haven't memorized the entire C operator precedence table ;)

•           return -EINVAL;
  

•   vm_flags_mod(vma, VM_DONTDUMP, VM_MAYEXEC | VM_MAYWRITE);
  

•   for (i = 0; i < pages && !err; i++, addr += PAGE_SIZE)
  

•           err = vm_insert_page(vma, vma->vm_start + i * PAGE_SIZE,
  

•                                virt_to_page(addr));
  

•   if (err)
  

•           zap_vma_pages(vma);
  

it's certainly subjective, but I find this error handling with !err in for loop condition hard to follow. What's wrong with arguably more straightforward (and as you can see I'm not a big fan of mutated addr but calculated vma->vm_start + i * PAGE_SIZE: pick one style one follow it for both entities?):

for (i = 0; i < pages; i++) { err = vm_insert_page(vma, vma->vm_start + i * PAGE_SIZE, virt_to_page(addr + i * PAGE_SIZE)); if (err) { zap_vma_pages(vma); return err; } }

return 0;

?

•   return err;
  

+}

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_sysfs_vmlinux_mmap,
  

};

struct kobject *btf_kobj;

-- 2.49.0