linux-kernel - Re: [RFC PATCH 1/2] x86, lib, xenpv: Add WBNOINVD helper functions

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]

Message-ID: <a9560e97-478d-4e03-b936-cf6f663279a4@citrix.com>
Date: Tue, 3 Dec 2024 01:28:54 +0000
From: Andrew Cooper <andrew.cooper3@...rix.com>
To: Kevin Loughlin <kevinloughlin@...gle.com>, linux-kernel@...r.kernel.org
Cc: seanjc@...gle.com, pbonzini@...hat.com, tglx@...utronix.de,
 mingo@...hat.com, bp@...en8.de, dave.hansen@...ux.intel.com, x86@...nel.org,
 hpa@...or.com, kvm@...r.kernel.org, thomas.lendacky@....com,
 pgonda@...gle.com, sidtelang@...gle.com, mizhang@...gle.com,
 virtualization@...ts.linux.dev, xen-devel@...ts.xenproject.org,
 bcm-kernel-feedback-list@...adcom.com
Subject: Re: [RFC PATCH 1/2] x86, lib, xenpv: Add WBNOINVD helper functions

On 03/12/2024 12:59 am, Kevin Loughlin wrote:
> diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
> index d4eb9e1d61b8..c040af2d8eff 100644
> --- a/arch/x86/include/asm/paravirt.h
> +++ b/arch/x86/include/asm/paravirt.h
> @@ -187,6 +187,13 @@ static __always_inline void wbinvd(void)
>  	PVOP_ALT_VCALL0(cpu.wbinvd, "wbinvd", ALT_NOT_XEN);
>  }
>  
> +extern noinstr void pv_native_wbnoinvd(void);
> +
> +static __always_inline void wbnoinvd(void)
> +{
> +	PVOP_ALT_VCALL0(cpu.wbnoinvd, "wbnoinvd", ALT_NOT_XEN);
> +}

Given this, ...

> diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
> index fec381533555..a66b708d8a1e 100644
> --- a/arch/x86/kernel/paravirt.c
> +++ b/arch/x86/kernel/paravirt.c
> @@ -149,6 +154,7 @@ struct paravirt_patch_template pv_ops = {
>  	.cpu.write_cr0		= native_write_cr0,
>  	.cpu.write_cr4		= native_write_cr4,
>  	.cpu.wbinvd		= pv_native_wbinvd,
> +	.cpu.wbnoinvd		= pv_native_wbnoinvd,
>  	.cpu.read_msr		= native_read_msr,
>  	.cpu.write_msr		= native_write_msr,
>  	.cpu.read_msr_safe	= native_read_msr_safe,

this, and ...

> diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
> index d6818c6cafda..a5c76a6f8976 100644
> --- a/arch/x86/xen/enlighten_pv.c
> +++ b/arch/x86/xen/enlighten_pv.c
> @@ -1162,6 +1162,7 @@ static const typeof(pv_ops) xen_cpu_ops __initconst = {
>  		.write_cr4 = xen_write_cr4,
>  
>  		.wbinvd = pv_native_wbinvd,
> +		.wbnoinvd = pv_native_wbnoinvd,
>  
>  		.read_msr = xen_read_msr,
>  		.write_msr = xen_write_msr,

this, what is the point having a paravirt hook which is wired to
native_wbnoinvd() in all cases?

That just seems like overhead for overhead sake.

~Andrew