Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
MIME-Version: 1.0
References: <20181123221804.440-1-ard.biesheuvel@linaro.org>
 <20181123221804.440-3-ard.biesheuvel@linaro.org> <20181130182629.GA16085@arm.com>
In-Reply-To: <20181130182629.GA16085@arm.com>
From:   Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date:   Fri, 30 Nov 2018 20:20:06 +0100
Message-ID: <CAKv+Gu9QVHLWu5H3Ok1Kbm=vtzd1KaHUn2VEij6oToW5aPR9uA@mail.gmail.com>
Subject: Re: [PATCH v4 2/2] arm64/bpf: don't allocate BPF JIT programs in
 module memory
To:     Will Deacon <will.deacon@arm.com>
Cc:     Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
        Daniel Borkmann <daniel@iogearbox.net>,
        Alexei Starovoitov <ast@kernel.org>,
        Rick Edgecombe <rick.p.edgecombe@intel.com>,
        Eric Dumazet <eric.dumazet@gmail.com>,
        Jann Horn <jannh@google.com>,
        Kees Cook <keescook@chromium.org>,
        Jessica Yu <jeyu@kernel.org>, Arnd Bergmann <arnd@arndb.de>,
        Catalin Marinas <catalin.marinas@arm.com>,
        Mark Rutland <mark.rutland@arm.com>,
        "David S. Miller" <davem@davemloft.net>,
        linux-arm-kernel <linux-arm-kernel@lists.infradead.org>,
        "<netdev@vger.kernel.org>" <netdev@vger.kernel.org>
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Fri, 30 Nov 2018 at 19:26, Will Deacon <will.deacon@arm.com> wrote:
>
> On Fri, Nov 23, 2018 at 11:18:04PM +0100, Ard Biesheuvel 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.biesheuvel@linaro.org>
> > ---
> >  arch/arm64/include/asm/memory.h |  5 ++++-
> >  arch/arm64/net/bpf_jit_comp.c   | 13 +++++++++++++
> >  2 files changed, 17 insertions(+), 1 deletion(-)
> >
> > diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
> > index b96442960aea..ee20fc63899c 100644
> > --- a/arch/arm64/include/asm/memory.h
> > +++ b/arch/arm64/include/asm/memory.h
> > @@ -62,8 +62,11 @@
> >  #define PAGE_OFFSET          (UL(0xffffffffffffffff) - \
> >       (UL(1) << (VA_BITS - 1)) + 1)
> >  #define KIMAGE_VADDR         (MODULES_END)
> > +#define BPF_JIT_REGION_START (VA_START + KASAN_SHADOW_SIZE)
> > +#define BPF_JIT_REGION_SIZE  (SZ_128M)
> > +#define BPF_JIT_REGION_END   (BPF_JIT_REGION_START + BPF_JIT_REGION_SIZE)
> >  #define MODULES_END          (MODULES_VADDR + MODULES_VSIZE)
> > -#define MODULES_VADDR                (VA_START + KASAN_SHADOW_SIZE)
> > +#define MODULES_VADDR                (BPF_JIT_REGION_END)
> >  #define MODULES_VSIZE                (SZ_128M)
> >  #define VMEMMAP_START                (PAGE_OFFSET - VMEMMAP_SIZE)
> >  #define PCI_IO_END           (VMEMMAP_START - SZ_2M)
> > diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
> > index a6fdaea07c63..76c2ab40c02d 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_START,
> > +                                 BPF_JIT_REGION_END, GFP_KERNEL,
> > +                                 PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
> > +                                 __builtin_return_address(0));
>
> I guess we'll want VM_IMMEDIATE_UNMAP here if Rich gets that merged.

I think akpm already queued up that patch.

> In the
> meantime, I wonder if it's worth zeroing the region in bpf_jit_free_exec()?
> (although we'd need the size information...).
>

Not sure. What exactly would that achieve?