On Fri, May 2, 2025 at 3:20 AM Lorenz Bauer <[email protected]> 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 <[email protected]>
> ---
> include/asm-generic/vmlinux.lds.h | 3 ++-
> kernel/bpf/sysfs_btf.c | 36 ++++++++++++++++++++++++++++++++++--
> 2 files changed, 36 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..f4b59b1c2e5b11ffffa80662ad39334c730019ee
> 100644
> --- a/kernel/bpf/sysfs_btf.c
> +++ b/kernel/bpf/sysfs_btf.c
> @@ -7,18 +7,50 @@
> #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)
> +{
> + phys_addr_t start = virt_to_phys(__start_BTF);
> + size_t btf_size = __stop_BTF - __start_BTF;
> + size_t vm_size = vma->vm_end - vma->vm_start;
> + unsigned long pfn = start >> PAGE_SHIFT;
> + unsigned long pages = PAGE_ALIGN(btf_size) >> PAGE_SHIFT;
> +
> + if (kobj != btf_kobj)
> + return -EINVAL;
> +
> + if (vma->vm_pgoff)
> + return -EINVAL;
> +
> + if (vma->vm_flags & (VM_WRITE|VM_EXEC|VM_MAYSHARE))
> + return -EACCES;
> +
> + if (pfn + pages < pfn)
> + return -EINVAL;
> +
> + if (vm_size >> PAGE_SHIFT > pages)
> + return -EINVAL;
> +
> + vm_flags_mod(vma, VM_DONTDUMP, VM_MAYEXEC|VM_MAYWRITE);
> + return remap_pfn_range(vma, vma->vm_start, pfn, vm_size,
> vma->vm_page_prot);
remap_pfn_range() should be avoided.
See big comment in kernel/events/core.c in map_range().
The following seems to work:
diff --git a/kernel/bpf/sysfs_btf.c b/kernel/bpf/sysfs_btf.c
index f4b59b1c2e5b..7d0fd28070d8 100644
--- a/kernel/bpf/sysfs_btf.c
+++ b/kernel/bpf/sysfs_btf.c
@@ -20,13 +20,13 @@ static int btf_vmlinux_mmap(struct file *filp,
struct kobject *kobj,
const struct bin_attribute *attr,
struct vm_area_struct *vma)
{
- phys_addr_t start = virt_to_phys(__start_BTF);
+ unsigned long addr = (unsigned long)__start_BTF;
size_t btf_size = __stop_BTF - __start_BTF;
size_t vm_size = vma->vm_end - vma->vm_start;
- unsigned long pfn = start >> PAGE_SHIFT;
unsigned long pages = PAGE_ALIGN(btf_size) >> PAGE_SHIFT;
+ int i, err = 0;
- if (kobj != btf_kobj)
+ if (kobj != btf_kobj || !pages)
return -EINVAL;
if (vma->vm_pgoff)
@@ -35,14 +35,17 @@ static int btf_vmlinux_mmap(struct file *filp,
struct kobject *kobj,
if (vma->vm_flags & (VM_WRITE|VM_EXEC|VM_MAYSHARE))
return -EACCES;
- if (pfn + pages < pfn)
- return -EINVAL;
-
if (vm_size >> PAGE_SHIFT > pages)
return -EINVAL;
vm_flags_mod(vma, VM_DONTDUMP, VM_MAYEXEC|VM_MAYWRITE);
- return remap_pfn_range(vma, vma->vm_start, pfn, vm_size,
vma->vm_page_prot);
+
+ 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_page_range_single(vma, vma->vm_start, pages *
PAGE_SIZE, NULL);
+ return err;
}
Great that you added:
/* Check padding is zeroed */
for (int i = 0; i < trailing; i++) {
if (((__u8 *)raw_data)[btf_size + i] != 0) {
PRINT_FAIL("tail of BTF is not zero at page
offset %d\n", i);
goto cleanup;
}
}
but this part is puzzling:
trailing = page_size - (btf_size % page_size) % page_size;
