On Fri, 23 Nov 2018 at 10:42, Ard Biesheuvel <ard.biesheu...@linaro.org> wrote:
>
> The arm64 module region is a 128 MB region that is kept close to
> the core kernel, in order to ensure that relative branches are
> always in range. So using the same region for programs that do
> not have this restriction is wasteful, and preferably avoided.
>
> Now that the core BPF JIT code permits the alloc/free routines to
> be overridden, implement them by vmalloc()/vfree() calls from a
> dedicated 128 MB region set aside for BPF programs. This ensures
> that BPF programs are still in branching range of each other, which
> is something the JIT currently depends upon (and is not guaranteed
> when using module_alloc() on KASLR kernels like we do currently).
> It also ensures that placement of BPF programs does not correlate
> with the placement of the core kernel or modules, making it less
> likely that leaking the former will reveal the latter.
>
> This also solves an issue under KASAN, where shadow memory is
> needlessly allocated for all BPF programs (which don't require KASAN
> shadow pages since they are not KASAN instrumented)
>
> Signed-off-by: Ard Biesheuvel <ard.biesheu...@linaro.org>
> ---
> arch/arm64/include/asm/memory.h | 3 +++
> arch/arm64/include/asm/pgtable.h | 2 +-
> arch/arm64/net/bpf_jit_comp.c | 13 +++++++++++++
> 3 files changed, 17 insertions(+), 1 deletion(-)
>
> diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
> index b96442960aea..506e319da98f 100644
> --- a/arch/arm64/include/asm/memory.h
> +++ b/arch/arm64/include/asm/memory.h
> @@ -69,6 +69,9 @@
> #define PCI_IO_END (VMEMMAP_START - SZ_2M)
> #define PCI_IO_START (PCI_IO_END - PCI_IO_SIZE)
> #define FIXADDR_TOP (PCI_IO_START - SZ_2M)
> +#define BPF_JIT_REGION_BASE (VMALLOC_END)
> +#define BPF_JIT_REGION_SIZE (SZ_128M)
> +#define BPF_JIT_REGION_END (BPF_JIT_REGION_BASE + BPF_JIT_REGION_SIZE)
>
Discussing this off-line with Daniel, it may be better to put the BPF
region before the module space instead.
This will permit the use of adrp/add/b[l]r sequences for long
jumps/calls. When booting with KASLR enabled, we can enhance the logic
there to ensure that the BPF region remains inside the same 4 GB
window as the module region and the core kernel (and randomize it
relatively as well)
> #define KERNEL_START _text
> #define KERNEL_END _end
> diff --git a/arch/arm64/include/asm/pgtable.h
> b/arch/arm64/include/asm/pgtable.h
> index 50b1ef8584c0..9db98a4cd9b4 100644
> --- a/arch/arm64/include/asm/pgtable.h
> +++ b/arch/arm64/include/asm/pgtable.h
> @@ -31,7 +31,7 @@
> * and fixed mappings
> */
> #define VMALLOC_START (MODULES_END)
> -#define VMALLOC_END (PAGE_OFFSET - PUD_SIZE - VMEMMAP_SIZE -
> SZ_64K)
> +#define VMALLOC_END (PAGE_OFFSET - PUD_SIZE - VMEMMAP_SIZE -
> BPF_JIT_REGION_SIZE - SZ_64K)
>
> #define vmemmap ((struct page *)VMEMMAP_START -
> (memstart_addr >> PAGE_SHIFT))
>
> diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
> index a6fdaea07c63..298beba29fa5 100644
> --- a/arch/arm64/net/bpf_jit_comp.c
> +++ b/arch/arm64/net/bpf_jit_comp.c
> @@ -940,3 +940,16 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog
> *prog)
> tmp : orig_prog);
> return prog;
> }
> +
> +void *bpf_jit_alloc_exec(unsigned long size)
> +{
> + return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_BASE,
> + BPF_JIT_REGION_END, GFP_KERNEL,
> + PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
> + __builtin_return_address(0));
> +}
> +
> +void bpf_jit_free_exec(const void *addr)
> +{
> + return vfree(addr);
> +}
> --
> 2.17.1
>
