Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Tue, 19 Jul 2022 23:33:04 +0200
From:   Peter Zijlstra <peterz@infradead.org>
To:     "Maciej S. Szmigiero" <mail@maciej.szmigiero.name>
Cc:     linux-kernel@vger.kernel.org, keescook@chromium.org,
        hjl.tools@gmail.com, andrew.cooper3@citrix.com,
        mark.rutland@arm.com, will@kernel.org, ndesaulniers@google.com,
        x86@kernel.org, Ankur Arora <ankur.a.arora@oracle.com>
Subject: Re: [RFC][PATCH] x86,nospec: Simplify {JMP,CALL}_NOSPEC
Message-ID: <YtcjEEpfvYmvHjmE@worktop.programming.kicks-ass.net>
References: <20211204134338.760603010@infradead.org>
 <20211204134908.140103474@infradead.org>
 <9011132e-d78b-8bec-10cb-2b3d77a4e1fc@maciej.szmigiero.name>
 <Ytcguqp+/aTiOcnN@worktop.programming.kicks-ass.net>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <Ytcguqp+/aTiOcnN@worktop.programming.kicks-ass.net>
Precedence: bulk

On Tue, Jul 19, 2022 at 11:23:07PM +0200, Peter Zijlstra wrote:
> Subject: x86,nospec: Simplify {JMP,CALL}_NOSPEC
> 
> Have {JMP,CALL}_NOSPEC generate the same code GCC does for indirect
> calls and rely on the objtool retpoline patching infrastructure.
> 
> There's no reason these should be alternatives while the vast bulk of
> compiler generated retpolines are not.
> 
> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
> ---
>  arch/x86/include/asm/nospec-branch.h | 24 ++++++++++++++++++------
>  1 file changed, 18 insertions(+), 6 deletions(-)
> 
> diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
> index 10a3bfc1eb23..7bb319d2932c 100644
> --- a/arch/x86/include/asm/nospec-branch.h
> +++ b/arch/x86/include/asm/nospec-branch.h
> @@ -93,6 +93,19 @@
>  #endif
>  .endm
>  
> +/*
> + * Equivalent to -mindirect-branch-cs-prefix; emit the 5 byte jmp/call
> + * to the retpoline thunk with a CS prefix when the register requires
> + * a RAX prefix byte to encode. Also see apply_alternatives().

Obviously I meant: apply_retpolines() ...

> + */
> +.macro __CS_PREFIX reg:req
> +	.irp rs,r8,r9,r10,r11,r12,r13,r14,r15
> +	.ifc \reg,\rs
> +	.byte 0x2e
> +	.endif
> +	.endr
> +.endm
> +
>  /*
>   * JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple
>   * indirect jmp/call which may be susceptible to the Spectre variant 2
> @@ -100,19 +113,18 @@
>   */
>  .macro JMP_NOSPEC reg:req
>  #ifdef CONFIG_RETPOLINE
> -	ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \
> -		      __stringify(jmp __x86_indirect_thunk_\reg), X86_FEATURE_RETPOLINE, \
> -		      __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), X86_FEATURE_RETPOLINE_LFENCE
> +	__CS_PREFIX \reg
> +	jmp	__x86_indirect_thunk_\reg
>  #else
>  	jmp	*%\reg
> +	int3
>  #endif
>  .endm
>  
>  .macro CALL_NOSPEC reg:req
>  #ifdef CONFIG_RETPOLINE
> -	ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; call *%\reg), \
> -		      __stringify(call __x86_indirect_thunk_\reg), X86_FEATURE_RETPOLINE, \
> -		      __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; call *%\reg), X86_FEATURE_RETPOLINE_LFENCE
> +	__CS_PREFIX \reg
> +	call	__x86_indirect_thunk_\reg
>  #else
>  	call	*%\reg
>  #endif