linux-kernel - Re: [PATCH v6 7/7] KVM: TDX: Explicitly do WBINVD when no more TDX SEAMCALLs

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: <ebd8132d5c0d4b1994802028a2bef01bd45e62a2.camel@intel.com>
Date: Thu, 14 Aug 2025 15:38:26 +0000
From: "Edgecombe, Rick P" <rick.p.edgecombe@...el.com>
To: "seanjc@...gle.com" <seanjc@...gle.com>, "Huang, Kai"
	<kai.huang@...el.com>
CC: "kvm@...r.kernel.org" <kvm@...r.kernel.org>, "ashish.kalra@....com"
	<ashish.kalra@....com>, "Hansen, Dave" <dave.hansen@...el.com>,
	"thomas.lendacky@....com" <thomas.lendacky@....com>,
	"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>, "Chatre,
 Reinette" <reinette.chatre@...el.com>, "dwmw@...zon.co.uk"
	<dwmw@...zon.co.uk>, "pbonzini@...hat.com" <pbonzini@...hat.com>,
	"mingo@...hat.com" <mingo@...hat.com>, "Yamahata, Isaku"
	<isaku.yamahata@...el.com>, "kas@...nel.org" <kas@...nel.org>,
	"tglx@...utronix.de" <tglx@...utronix.de>, "nik.borisov@...e.com"
	<nik.borisov@...e.com>, "hpa@...or.com" <hpa@...or.com>,
	"peterz@...radead.org" <peterz@...radead.org>, "sagis@...gle.com"
	<sagis@...gle.com>, "Chen, Farrah" <farrah.chen@...el.com>, "bp@...en8.de"
	<bp@...en8.de>, "Gao, Chao" <chao.gao@...el.com>, "binbin.wu@...ux.intel.com"
	<binbin.wu@...ux.intel.com>, "Williams, Dan J" <dan.j.williams@...el.com>,
	"x86@...nel.org" <x86@...nel.org>
Subject: Re: [PATCH v6 7/7] KVM: TDX: Explicitly do WBINVD when no more TDX
 SEAMCALLs

On Thu, 2025-08-14 at 06:54 -0700, Sean Christopherson wrote:
> >   static inline void tdx_init(void) { }
> >   static inline int tdx_cpu_enable(void) { return -ENODEV; }
> > @@ -224,6 +225,7 @@ static inline int tdx_enable(void)  { return -ENODEV; }
> >   static inline u32 tdx_get_nr_guest_keyids(void) { return 0; }
> >   static inline const char *tdx_dump_mce_info(struct mce *m) { return NULL;
> > }
> >   static inline const struct tdx_sys_info *tdx_get_sysinfo(void) { return
> > NULL; }
> > +static inline void tdx_cpu_flush_cache(void) { }
> 
> Stub is unnecessary.  tdx.c is built iff KVM_INTEL_TDX=y, and that depends on
> INTEL_TDX_HOST.
> 
> At a glance, some of the existing stubs are useless as well.

Oh, yep. We'll add it to the cleanup list.

> 
> >   #endif	/* CONFIG_INTEL_TDX_HOST */
> >   
> >   #endif /* !__ASSEMBLER__ */
> > diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
> > index 66744f5768c8..1bc6f52e0cd7 100644
> > --- a/arch/x86/kvm/vmx/tdx.c
> > +++ b/arch/x86/kvm/vmx/tdx.c
> > @@ -442,6 +442,18 @@ void tdx_disable_virtualization_cpu(void)
> >   		tdx_flush_vp(&arg);
> >   	}
> >   	local_irq_restore(flags);
> > +
> > +	/*
> > +	 * No more TDX activity on this CPU from here.  Flush cache to
> > +	 * avoid having to do WBINVD in stop_this_cpu() during kexec.
> > +	 *
> > +	 * Kexec calls native_stop_other_cpus() to stop remote CPUs
> > +	 * before booting to new kernel, but that code has a "race"
> > +	 * when the normal REBOOT IPI times out and NMIs are sent to
> > +	 * remote CPUs to stop them.  Doing WBINVD in stop_this_cpu()
> > +	 * could potentially increase the possibility of the "race".
> > +	 */
> > +	tdx_cpu_flush_cache();
> 
> IIUC, this can be:
> 
> 	if (IS_ENABLED(CONFIG_KEXEC))
> 		tdx_cpu_flush_cache();
> 

No strong objection, just 2 cents. I bet !CONFIG_KEXEC && CONFIG_INTEL_TDX_HOST
kernels will be the minority. Seems like an opportunity to simplify the code.

But if we do this, we should probably compile out the unused
tdx_cpu_flush_cache() too.

> >   }
> >