linux-kernel - Re: [PATCH 1/2] iommu/vt-d: Ensure memory ordering in context entry updates

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] [day] [month] [year] [list]

Message-ID: <aUfyBmPQfosuCDab@mitya-t14-2025>
Date: Sun, 21 Dec 2025 14:11:34 +0100
From: Dmytro Maluka <dmaluka@...omium.org>
To: Baolu Lu <baolu.lu@...ux.intel.com>
Cc: David Woodhouse <dwmw2@...radead.org>, iommu@...ts.linux.dev,
	Joerg Roedel <joro@...tes.org>, Will Deacon <will@...nel.org>,
	Robin Murphy <robin.murphy@....com>, linux-kernel@...r.kernel.org,
	"Vineeth Pillai (Google)" <vineeth@...byteword.org>,
	Aashish Sharma <aashish@...hishsharma.net>,
	Grzegorz Jaszczyk <jaszczyk@...omium.org>,
	Chuanxiao Dong <chuanxiao.dong@...el.com>,
	Kevin Tian <kevin.tian@...el.com>
Subject: Re: [PATCH 1/2] iommu/vt-d: Ensure memory ordering in context entry
 updates

On Sun, Dec 21, 2025 at 05:04:27PM +0800, Baolu Lu wrote:
> On 12/21/25 09:43, Dmytro Maluka wrote:
> > +static inline void context_set_bits(u64 *ptr, u64 mask, u64 bits)
> > +{
> > +	u64 old;
> > +
> > +	old = READ_ONCE(*ptr);
> > +	WRITE_ONCE(*ptr, (old & ~mask) | bits);
> > +}
> 
> Add a line to ensures that the input "bits" cannot overflow the assigned
> "mask".
> 
> static inline void context_set_bits(u64 *ptr, u64 mask, u64 bits)
> {
> 	u64 val;
> 
> 	val = READ_ONCE(*ptr);
> 	val &= ~mask;
> 	val |= (bits & mask);
> 	WRITE_ONCE(*ptr, val);
> }

Makes sense. And then worth doing the same in pasid_set_bits() as well?

Actually we can use the same helper for both context and pasid entries
(rename it e.g. to entry_set_bits()).

> >   static inline void context_set_present(struct context_entry *context)
> >   {
> > -	context->lo |= 1;
> > +	context_set_bits(&context->lo, 1 << 0, 1);
> >   }
> 
> How about adding a smp_wmb() before setting the present bit? Maybe it's
> unnecessary for x86 architecture, but at least it's harmless and more
> readable. Or not?
> 
> static inline void context_set_present(struct context_entry *context)
> {
> 	smp_wmb();
> 	context_set_bits(&context->lo, 1ULL << 0, 1ULL);
> }

Maybe... And if so, then in pasid_set_present() as well?

Actually this would make a slight behavioral difference even on x86:
right now this patch only provides ordering of context entry updates
between each other, while smp_wmb() would add a full compiler barrier
here.

So this barrier may be redundant as long as we always use these
context_*() helpers (and thus always use WRITE_ONCE) for any updates of
context entries. On the other hand, it might make it more robust if we
still occasionally do that without WRITE_ONCE, for example in
context_entry_set_pasid_table() which I also changed to use WRITE_ONCE
in this patch.