linux-kernel - RE: [PATCH] dmaengine: idxd: Change wmb() to smp_wmb() when copying completion record to user space

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: <CO6PR11MB55868C091A77D9D5451D959A9C7C2@CO6PR11MB5586.namprd11.prod.outlook.com>
Date: Wed, 31 Jan 2024 04:18:41 +0000
From: "Rao, Nikhil" <nikhil.rao@...el.com>
To: "Yu, Fenghua" <fenghua.yu@...el.com>, "Hansen, Dave"
	<dave.hansen@...el.com>, Boqun Feng <boqun.feng@...il.com>, Mark Rutland
	<mark.rutland@....com>
CC: Vinod Koul <vkoul@...nel.org>, "Jiang, Dave" <dave.jiang@...el.com>,
	"dmaengine@...r.kernel.org" <dmaengine@...r.kernel.org>, linux-kernel
	<linux-kernel@...r.kernel.org>, "Zhu, Tony" <tony.zhu@...el.com>, "Mathieu
 Desnoyers" <mathieu.desnoyers@...icios.com>, Thomas Gleixner
	<tglx@...utronix.de>, Ingo Molnar <mingo@...hat.com>, Borislav Petkov
	<bp@...en8.de>, Dave Hansen <dave.hansen@...ux.intel.com>, "x86@...nel.org"
	<x86@...nel.org>
Subject: RE: [PATCH] dmaengine: idxd: Change wmb() to smp_wmb() when copying
 completion record to user space



> -----Original Message-----
> From: Yu, Fenghua <fenghua.yu@...el.com>
> Sent: Wednesday, January 31, 2024 2:12 AM
> To: Hansen, Dave <dave.hansen@...el.com>; Boqun Feng
> <boqun.feng@...il.com>; Mark Rutland <mark.rutland@....com>
> Cc: Vinod Koul <vkoul@...nel.org>; Jiang, Dave <dave.jiang@...el.com>;
> dmaengine@...r.kernel.org; linux-kernel <linux-kernel@...r.kernel.org>; Rao,
> Nikhil <nikhil.rao@...el.com>; Zhu, Tony <tony.zhu@...el.com>; Mathieu
> Desnoyers <mathieu.desnoyers@...icios.com>; Thomas Gleixner
> <tglx@...utronix.de>; Ingo Molnar <mingo@...hat.com>; Borislav Petkov
> <bp@...en8.de>; Dave Hansen <dave.hansen@...ux.intel.com>;
> x86@...nel.org
> Subject: Re: [PATCH] dmaengine: idxd: Change wmb() to smp_wmb() when
> copying completion record to user space
> 
> Hi, Dave, Boqun, and Mark,
> 
> On 1/30/24 12:30, Dave Hansen wrote:
> > On 1/30/24 11:53, Boqun Feng wrote:
> >>>> Fixes: b022f59725f0 ("dmaengine: idxd: add idxd_copy_cr() to copy
> >>>> user completion record during page fault handling")
> >>>> Suggested-by: Nikhil Rao <nikhil.rao@...el.com>
> >>>> Tested-by: Tony Zhu <tony.zhu@...el.com>
> >> Since it has a "Fixes" tag and a "Tested-by" tag, I'd assume there
> >> has been a test w/ and w/o this patch showing it can resolve a real
> >> issue *constantly*? If so, I think x86 might be broken somewhere.
> >>
> >> [Cc x86 maintainers]
> >
> > Fenghua, could you perhaps explain how this problem affects end users?
> > What symptom was observed that made it obvious something was broken
> > and what changes with this patch?
> 
> There is no issue found by any test. This wmb() code was reviewed and was
> "thought" that it may have a potential issue. 

I had made this suggestion since the code only needed a smp_wmb(), If the review refers to my suggestion, sorry if my message indicated a potential issue, that certainly wasn't my intention.
memory-barriers.txt does say that mandatory barriers (of which wmb() is one) should not be used to control SMP effects.

Nikhil