Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753309AbbDBJHy (ORCPT ); Thu, 2 Apr 2015 05:07:54 -0400 Received: from mail-wi0-f171.google.com ([209.85.212.171]:33445 "EHLO mail-wi0-f171.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753274AbbDBJHt (ORCPT ); Thu, 2 Apr 2015 05:07:49 -0400 Date: Thu, 2 Apr 2015 11:07:44 +0200 From: Ingo Molnar To: Andy Lutomirski Cc: x86@kernel.org, linux-kernel@vger.kernel.org, Borislav Petkov , Denys Vlasenko , Linus Torvalds , Borislav Petkov , Brian Gerst Subject: Re: [PATCH urgent v2] x86, asm: Disable opportunistic SYSRET if regs->flags has TF set Message-ID: <20150402090744.GA26846@gmail.com> References: <9472f1ca4c19a38ecda45bba9c91b7168135fcfa.1427923514.git.luto@kernel.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <9472f1ca4c19a38ecda45bba9c91b7168135fcfa.1427923514.git.luto@kernel.org> User-Agent: Mutt/1.5.23 (2014-03-12) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3569 Lines: 97 * Andy Lutomirski wrote: > When I wrote the opportunistic SYSRET code, I missed an important > difference between SYSRET and IRET. Both instructions are capable > of setting EFLAGS.TF, but they behave differently when doing so. > IRET will not issue a #DB trap after execution when it sets TF This > is critical -- otherwise you'd never be able to make forward > progress when returning to userspace. SYSRET, on the other hand, > will trap with #DB immediately after returning to CPL3, and the next > instruction will never execute. > > This breaks anything that opportunistically SYSRETs to a user > context with TF set. For example, running this code with TF set and > a SIGTRAP handler loaded never gets past post_nop. > > extern unsigned char post_nop[]; > asm volatile ("pushfq\n\t" > "popq %%r11\n\t" > "nop\n\t" > "post_nop:" > : : "c" (post_nop) : "r11"); > > In my defense, I can't find this documented in the AMD or Intel > manual. > > Fix it by using IRET to restore TF. > > Fixes: 2a23c6b8a9c4 x86_64, entry: Use sysret to return to userspace when possible > Signed-off-by: Andy Lutomirski > --- > > This affects 4.0-rc as well as -tip. A full test case lives here: > > https://git.kernel.org/cgit/linux/kernel/git/luto/misc-tests.git/ > > It's called single_step_syscall_64. > > On Intel systems, the 32-bit version of that test fails for unrelated > reasons, but that's not a regression, and fixing it will be much more > intrusive. > > Changes from v1: > - Remove mention of testl from changelog. > - Improve comment per Denys' suggestion. > > arch/x86/kernel/entry_64.S | 16 +++++++++++++++- > 1 file changed, 15 insertions(+), 1 deletion(-) > > diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S > index 750c6efcb718..537716380959 100644 > --- a/arch/x86/kernel/entry_64.S > +++ b/arch/x86/kernel/entry_64.S > @@ -715,7 +715,21 @@ retint_swapgs: /* return to user-space */ > cmpq %r11,EFLAGS(%rsp) /* R11 == RFLAGS */ > jne opportunistic_sysret_failed > > - testq $X86_EFLAGS_RF,%r11 /* sysret can't restore RF */ > + /* > + * SYSRET can't restore RF. SYSRET can restore TF, but unlike IRET, > + * restoring TF results in a trap from userspace immediately after > + * SYSRET. This would cause an infinite loop whenever #DB happens > + * with register state that satisfies the opportunistic SYSRET > + * conditions. For example, single-stepping this user code: > + * > + * movq $stuck_here,%rcx > + * pushfq > + * popq %r11 > + * stuck_here: > + * > + * would never get past stuck_here. > + */ > + testq $(X86_EFLAGS_RF|X86_EFLAGS_TF),%r11 > jnz opportunistic_sysret_failed So I merged this as it's an obvious bugfix, but in hindsight I'm really uneasy about the whole opportunistic SYSRET concept: it appears that the chance that %rcx matches return-%rip is astronomical - this is why this bug wasn't noticed live so far. So should we really be doing this? It invites fragility and despite being clever, it adds average overhead to interrupt returns to user-space: the chance of the optimization hitting and helping us are much lower than the always paid for cost of doing the tests for it... So please defend it. Thanks, Ingo -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/