|
Message-ID: <CALCETrXhUdMNfC0yBah39Z=xWVe3Fix-qF922gJjqzTO1B7TSA@mail.gmail.com> Date: Fri, 10 Nov 2017 06:57:55 -0800 From: Andy Lutomirski <luto@...capital.net> To: "Hector Martin 'marcan'" <marcan@...can.st> Cc: LKML <linux-kernel@...r.kernel.org>, "kernel-hardening@...ts.openwall.com" <kernel-hardening@...ts.openwall.com>, X86 ML <x86@...nel.org> Subject: Re: vDSO maximum stack usage, stack probes, and -fstack-check On Fri, Nov 10, 2017 at 2:40 AM, Hector Martin 'marcan' <marcan@...can.st> wrote: > As far as I know, the vDSO specs (both Documentation/ABI/stable/vdso and > `man 7 vdso`) make no mention of how much stack the vDSO functions are > allowed to use. They just say "the usual C ABI", which makes no guarantees. > > It turns out that Go has been assuming that those functions use less > than 104 bytes of stack space, because it calls them directly on its > tiny stack allocations with no guard pages or other hardware overflow > protection [1]. On most systems, this is fine. > > However, on my system the stars aligned and turned it into a > nondeterministic crash. I use Gentoo Hardened, which builds its > toolchain with -fstack-check on by default. It turns out that with the > combination of GCC 6.4.0, -fstack-protect, linux-4.13.9-gentoo, and > CONFIG_OPTIMIZE_INLINING=n, gcc decides to *not* inline vread_tsc (it's > not marked inline, so it's perfectly within its right not to do that, > though for some reason it does inline when CONFIG_OPTIMIZE_INLINING=y > even though that nominally gives it greater freedom *not* to inline > things marked inline). That turns __vdso_clock_gettime and > __vdso_gettimeofday into non-leaf functions, and GCC then inserts a > stack probe (full objdump at [2]): > > 0000000000000030 <__vdso_clock_gettime>: > 30: 55 push %rbp > 31: 48 89 e5 mov %rsp,%rbp > 34: 48 81 ec 20 10 00 00 sub $0x1020,%rsp > 3b: 48 83 0c 24 00 orq $0x0,(%rsp) > 40: 48 81 c4 20 10 00 00 add $0x1020,%rsp This code is so wrong I don't even no where to start. Seriously, sub, orq, add? How about just orq with an offset? How about a *load* instead of a store? But stepping back even further, an offset > 4096 is just bogus. That's big enough to skip right over the guard page. Anyway, my recollection is that GCC's stack check code is busted until much newer gcc versions. I suppose we could try to make the kernel fail to build at all on a broken configuration like this. --Andy
Powered by blists - more mailing lists
Confused about mailing lists and their use? Read about mailing lists on Wikipedia and check out these guidelines on proper formatting of your messages.