linux-kernel - Re: [PATCH 04/24] x86,nospec: Annotate indirect calls/jumps

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Mon, 29 Jan 2018 18:44:03 +0100
From:   Peter Zijlstra <peterz@...radead.org>
To:     David Woodhouse <dwmw2@...radead.org>
Cc:     Thomas Gleixner <tglx@...utronix.de>,
        Josh Poimboeuf <jpoimboe@...hat.com>,
        linux-kernel@...r.kernel.org, Dave Hansen <dave.hansen@...el.com>,
        Ashok Raj <ashok.raj@...el.com>,
        Tim Chen <tim.c.chen@...ux.intel.com>,
        Andy Lutomirski <luto@...nel.org>,
        Linus Torvalds <torvalds@...ux-foundation.org>,
        Greg KH <gregkh@...uxfoundation.org>,
        Andrea Arcangeli <aarcange@...hat.com>,
        Andi Kleen <ak@...ux.intel.com>,
        Arjan Van De Ven <arjan.van.de.ven@...el.com>,
        Dan Williams <dan.j.williams@...el.com>,
        Paolo Bonzini <pbonzini@...hat.com>,
        Jun Nakajima <jun.nakajima@...el.com>,
        Asit Mallick <asit.k.mallick@...el.com>,
        Jason Baron <jbaron@...mai.com>
Subject: Re: [PATCH 04/24] x86,nospec: Annotate indirect calls/jumps

On Fri, Jan 26, 2018 at 10:19:47AM +0000, David Woodhouse wrote:
> On Tue, 2018-01-23 at 16:25 +0100, Peter Zijlstra wrote:
> > Annotate the indirect calls/jumps in the CALL_NOSPEC/JUMP_NOSPEC
> > alternatives.
> > 
> > 
> > Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
> 
> Reviewed-by: David Woodhouse <dwmw@...zon.co.uk>
> 
> However...
> 
> 
> >  /*
> > + * This should be used immediately before an indirect jump/call. It tells
> > + * objtool the subsequent indirect jump/call is vouched safe for retpoline
> > + * builds.
> > + */
> > +.macro ANNOTATE_RETPOLINE_SAFE
> > +	.Lannotate_\@:
> > +	.pushsection .discard.retpoline_safe
> > +	_ASM_PTR .Lannotate_\@
> > +	.popsection
> > +.endm
> 
> Didn't I just see one of those in patch 3? So this makes two...
> 
> 
> 
> > @@ -143,6 +155,12 @@
> >  	".long 999b - .\n\t"					\
> >  	".popsection\n\t"
> >  
> > +#define ANNOTATE_RETPOLINE_SAFE					\
> > +	"999:\n\t"						\
> > +	".pushsection .discard.retpoline_safe\n\t"		\
> > +	_ASM_PTR " 999b\n\t"					\
> > +	".popsection\n\t"
> > +
> >  #if defined(CONFIG_X86_64) && defined(RETPOLINE)
> 
> ... three.
> 
> Now, I did briefly toy with the idea of using a .macro from both
> __ASSEMBLY__ and inline asm, making the latter work by means of 
> asm(".include \"asm/nospec-branch.h\");
> 
> In the end I just ended up with the __FILL_RETURN_BUFFER CPP macro
> which is used from both by other tricks.
> 
> Can we look at doing something like that, please?


I'll try. The paravirt one might be tricky, I always end in header-hell
with that thing.