linux-kernel - Re: [PATCH v2 1/1] iommu/sva: Invalidate KVA range on kernel TLB flush

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: <20250711115806.GW1599700@nvidia.com>
Date: Fri, 11 Jul 2025 08:58:06 -0300
From: Jason Gunthorpe <jgg@...dia.com>
To: Peter Zijlstra <peterz@...radead.org>
Cc: Baolu Lu <baolu.lu@...ux.intel.com>, Joerg Roedel <joro@...tes.org>,
	Will Deacon <will@...nel.org>, Robin Murphy <robin.murphy@....com>,
	Kevin Tian <kevin.tian@...el.com>, Jann Horn <jannh@...gle.com>,
	Vasant Hegde <vasant.hegde@....com>,
	Dave Hansen <dave.hansen@...el.com>,
	Alistair Popple <apopple@...dia.com>,
	Uladzislau Rezki <urezki@...il.com>,
	Jean-Philippe Brucker <jean-philippe@...aro.org>,
	Andy Lutomirski <luto@...nel.org>,
	"Tested-by : Yi Lai" <yi1.lai@...el.com>, iommu@...ts.linux.dev,
	security@...nel.org, linux-kernel@...r.kernel.org,
	stable@...r.kernel.org
Subject: Re: [PATCH v2 1/1] iommu/sva: Invalidate KVA range on kernel TLB
 flush

On Fri, Jul 11, 2025 at 10:32:52AM +0200, Peter Zijlstra wrote:
> At some point the low latency folks are going to come hunting you down.
> Do you have a plan on how to deal with this; or are we throwing up our
> hands an say, the hardware sucks, deal with it?

If you turn on SVA in a process then all this same invalidation work
happens under someone's spinlock even today.. If it becomes a latency
problem for someone then it seems to be much bigger than just this bit.

Most likely the answer is that SVA and realtime are not compatible
ideas. I know I've had this conversation with some of our realtime
people and they have said they don't want to touch SVA because it
makes the device latencies indeterminate with possible faults.

Jason