Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.34 as permitted sender) client-ip=23.128.96.34;
Date:   Fri, 20 Oct 2023 16:13:13 -0700
In-Reply-To: <20231020-delay-verw-v1-1-cff54096326d@linux.intel.com>
Mime-Version: 1.0
References: <20231020-delay-verw-v1-0-cff54096326d@linux.intel.com> <20231020-delay-verw-v1-1-cff54096326d@linux.intel.com>
Message-ID: <ZTMJiVsEeyu6Vd8E@google.com>
Subject: Re: [PATCH  1/6] x86/bugs: Add asm helpers for executing VERW
From:   Sean Christopherson <seanjc@google.com>
To:     Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Cc:     Thomas Gleixner <tglx@linutronix.de>,
        Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
        Dave Hansen <dave.hansen@linux.intel.com>, x86@kernel.org,
        "H. Peter Anvin" <hpa@zytor.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Josh Poimboeuf <jpoimboe@kernel.org>,
        Andy Lutomirski <luto@kernel.org>,
        Jonathan Corbet <corbet@lwn.net>,
        Paolo Bonzini <pbonzini@redhat.com>, tony.luck@intel.com,
        ak@linux.intel.com, tim.c.chen@linux.intel.com,
        linux-kernel@vger.kernel.org, linux-doc@vger.kernel.org,
        kvm@vger.kernel.org,
        Alyssa Milburn <alyssa.milburn@linux.intel.com>,
        Daniel Sneddon <daniel.sneddon@linux.intel.com>,
        antonio.gomez.iglesias@linux.intel.com,
        Alyssa Milburn <alyssa.milburn@intel.com>
Content-Type: text/plain; charset="us-ascii"
Precedence: bulk

On Fri, Oct 20, 2023, Pawan Gupta wrote:
> diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
> index c55cc243592e..e1b623a27e1b 100644
> --- a/arch/x86/include/asm/nospec-branch.h
> +++ b/arch/x86/include/asm/nospec-branch.h
> @@ -111,6 +111,24 @@
>  #define RESET_CALL_DEPTH_FROM_CALL
>  #endif
>  
> +/*
> + * Macro to execute VERW instruction to mitigate transient data sampling
> + * attacks such as MDS. On affected systems a microcode update overloaded VERW
> + * instruction to also clear the CPU buffers.
> + *
> + * Note: Only the memory operand variant of VERW clears the CPU buffers. To
> + * handle the case when VERW is executed after user registers are restored, use
> + * RIP to point the memory operand to a part NOPL instruction that contains
> + * __KERNEL_DS.
> + */
> +#define __EXEC_VERW(m)	verw _ASM_RIP(m)
> +
> +#define EXEC_VERW				\
> +	__EXEC_VERW(551f);			\
> +	/* nopl __KERNEL_DS(%rax) */		\
> +	.byte 0x0f, 0x1f, 0x80, 0x00, 0x00;	\
> +551:	.word __KERNEL_DS;			\

Why are there so many macro layers?  Nothing jumps out to justfying two layers,
let alone three.

> +
>  /*
>   * Fill the CPU return stack buffer.
>   *
> @@ -329,6 +347,13 @@
>  #endif
>  .endm
>  
> +/* Clear CPU buffers before returning to user */
> +.macro USER_CLEAR_CPU_BUFFERS
> +	ALTERNATIVE "jmp .Lskip_verw_\@;", "", X86_FEATURE_USER_CLEAR_CPU_BUF
> +	EXEC_VERW

Rather than a NOP after VERW, why not something like this?

/* Clear CPU buffers before returning to user */
.macro USER_CLEAR_CPU_BUFFERS
                ALTERNATIVE "jmp .Lskip_verw_\@;", "jmp .Ldo_verw_\@;", X86_FEATURE_USER_CLEAR_CPU_BUF
551:            .word __KERNEL_DS
.Ldo_verw_\@:   verw _ASM_RIP(551b)
.Lskip_verw_\@:
.endm

> +.Lskip_verw_\@:
> +.endm