linux-kernel - Re: [PATCH 23/33] KVM: TDX: create/destroy VM structure

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: <543bcbd5-c217-41f7-b478-e32e6dcf66dc@intel.com>
Date: Wed, 25 Jun 2025 08:46:58 -0700
From: Dave Hansen <dave.hansen@...el.com>
To: Paolo Bonzini <pbonzini@...hat.com>, linux-kernel@...r.kernel.org,
 kvm@...r.kernel.org
Cc: seanjc@...gle.com, Yan Zhao <yan.y.zhao@...el.com>,
 Rick Edgecombe <rick.p.edgecombe@...el.com>,
 Isaku Yamahata <isaku.yamahata@...el.com>,
 Tony Lindgren <tony.lindgren@...ux.intel.com>,
 Sean Christopherson <sean.j.christopherson@...el.com>,
 Kai Huang <kai.huang@...el.com>, Adrian Hunter <adrian.hunter@...el.com>
Subject: Re: [PATCH 23/33] KVM: TDX: create/destroy VM structure

On 2/26/25 10:14, Paolo Bonzini wrote:
> +static void tdx_clear_page(struct page *page)
> +{
> +	const void *zero_page = (const void *) page_to_virt(ZERO_PAGE(0));
> +	void *dest = page_to_virt(page);
> +	unsigned long i;
> +
> +	/*
> +	 * The page could have been poisoned.  MOVDIR64B also clears
> +	 * the poison bit so the kernel can safely use the page again.
> +	 */
> +	for (i = 0; i < PAGE_SIZE; i += 64)
> +		movdir64b(dest + i, zero_page);
> +	/*
> +	 * MOVDIR64B store uses WC buffer.  Prevent following memory reads
> +	 * from seeing potentially poisoned cache.
> +	 */
> +	__mb();
> +}

Hey guys,

This ended up in KVM code when we already have the *VERY* similar
reset_tdx_pages().

Could we consolidate them, please? There's no reason to sprinkle
knowledge of movdir64b's memory ordering rules all across the tree.

Adrian, this is probably something to go do, first, before you try and
poke at this code that probably shouldn't be in KVM in the first place.