Re: [PATCH 3/4] x86/retpoline: Simplify vmexit_fill_RSB()

2018-01-26 Thread Borislav Petkov
On Fri, Jan 26, 2018 at 05:47:46PM +0100, Borislav Petkov wrote: > Proper ones coming soon. Ok, here they are as a reply to this message. Lemme send them out for a quick look, before I run them through the boxes tomorrow. -- Regards/Gruss, Boris. Good mailing practices for 400: avoid

Re: [PATCH 3/4] x86/retpoline: Simplify vmexit_fill_RSB()

2018-01-26 Thread Borislav Petkov
On Fri, Jan 26, 2018 at 05:47:46PM +0100, Borislav Petkov wrote: > Proper ones coming soon. Ok, here they are as a reply to this message. Lemme send them out for a quick look, before I run them through the boxes tomorrow. -- Regards/Gruss, Boris. Good mailing practices for 400: avoid

Re: [PATCH 3/4] x86/retpoline: Simplify vmexit_fill_RSB()

2018-01-26 Thread Borislav Petkov
On Fri, Jan 26, 2018 at 04:24:39PM +, David Woodhouse wrote: > Dammit, have the IBM vowel-stealers escaped again? Yeah, I love vowel dropping. :-) > What was wrong with '__clear_rsb_clobber_ax'? Nothing. I've dropped the clobber part too, btw, as I'm pushin/popping %rAX around it. It is

Re: [PATCH 3/4] x86/retpoline: Simplify vmexit_fill_RSB()

2018-01-26 Thread Borislav Petkov
On Fri, Jan 26, 2018 at 04:24:39PM +, David Woodhouse wrote: > Dammit, have the IBM vowel-stealers escaped again? Yeah, I love vowel dropping. :-) > What was wrong with '__clear_rsb_clobber_ax'? Nothing. I've dropped the clobber part too, btw, as I'm pushin/popping %rAX around it. It is

Re: [PATCH 3/4] x86/retpoline: Simplify vmexit_fill_RSB()

2018-01-26 Thread David Woodhouse
On Fri, 2018-01-26 at 14:24 +0100, Borislav Petkov wrote: > diff --git a/arch/x86/include/asm/asm-prototypes.h > b/arch/x86/include/asm/asm-prototypes.h > index 1908214b9125..b889705f995a 100644 > --- a/arch/x86/include/asm/asm-prototypes.h > +++ b/arch/x86/include/asm/asm-prototypes.h > @@ -38,4

Re: [PATCH 3/4] x86/retpoline: Simplify vmexit_fill_RSB()

2018-01-26 Thread David Woodhouse
On Fri, 2018-01-26 at 14:24 +0100, Borislav Petkov wrote: > diff --git a/arch/x86/include/asm/asm-prototypes.h > b/arch/x86/include/asm/asm-prototypes.h > index 1908214b9125..b889705f995a 100644 > --- a/arch/x86/include/asm/asm-prototypes.h > +++ b/arch/x86/include/asm/asm-prototypes.h > @@ -38,4

Re: [PATCH 3/4] x86/retpoline: Simplify vmexit_fill_RSB()

2018-01-26 Thread Borislav Petkov
On Fri, Jan 26, 2018 at 12:33:31PM +, David Woodhouse wrote: > On Fri, 2018-01-26 at 13:11 +0100, Borislav Petkov wrote: > > > > +ENTRY(__fill_rsb_clobber_ax) > > +   ___FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, %_ASM_SP > > +END(__fill_rsb_clobber_ax) > >

Re: [PATCH 3/4] x86/retpoline: Simplify vmexit_fill_RSB()

2018-01-26 Thread Borislav Petkov
On Fri, Jan 26, 2018 at 12:33:31PM +, David Woodhouse wrote: > On Fri, 2018-01-26 at 13:11 +0100, Borislav Petkov wrote: > > > > +ENTRY(__fill_rsb_clobber_ax) > > +   ___FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, %_ASM_SP > > +END(__fill_rsb_clobber_ax) > >

Re: [PATCH 3/4] x86/retpoline: Simplify vmexit_fill_RSB()

2018-01-26 Thread David Woodhouse
On Fri, 2018-01-26 at 13:11 +0100, Borislav Petkov wrote: > > +ENTRY(__fill_rsb_clobber_ax) > +   ___FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, %_ASM_SP > +END(__fill_rsb_clobber_ax) > +EXPORT_SYMBOL_GPL(__fill_rsb_clobber_ax) You still have clear vs. fill confusion there. How about

Re: [PATCH 3/4] x86/retpoline: Simplify vmexit_fill_RSB()

2018-01-26 Thread David Woodhouse
On Fri, 2018-01-26 at 13:11 +0100, Borislav Petkov wrote: > > +ENTRY(__fill_rsb_clobber_ax) > +   ___FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, %_ASM_SP > +END(__fill_rsb_clobber_ax) > +EXPORT_SYMBOL_GPL(__fill_rsb_clobber_ax) You still have clear vs. fill confusion there. How about

[PATCH 3/4] x86/retpoline: Simplify vmexit_fill_RSB()

2018-01-26 Thread Borislav Petkov
From: Borislav Petkov Simplify it to call an asm-function instead of pasting 41 insn bytes at every call site. Also, add alignment to the macro as suggested here: https://support.google.com/faqs/answer/7625886 Signed-off-by: Borislav Petkov Cc: David Woodhouse

[PATCH 3/4] x86/retpoline: Simplify vmexit_fill_RSB()

2018-01-26 Thread Borislav Petkov
From: Borislav Petkov Simplify it to call an asm-function instead of pasting 41 insn bytes at every call site. Also, add alignment to the macro as suggested here: https://support.google.com/faqs/answer/7625886 Signed-off-by: Borislav Petkov Cc: David Woodhouse ---