Received-SPF: pass (google.com: domain of linux-kernel+bounces-8257-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45d1:ec00::1 as permitted sender) client-ip=2604:1380:45d1:ec00::1;
Date: Thu, 21 Dec 2023 12:01:38 +0100
From: Lukas Wunner <lukas@wunner.de>
To: Ethan Zhao <haifeng.zhao@linux.intel.com>
Cc: bhelgaas@google.com, baolu.lu@linux.intel.com, dwmw2@infradead.org,
	will@kernel.org, robin.murphy@arm.com, linux-pci@vger.kernel.org,
	iommu@lists.linux.dev, linux-kernel@vger.kernel.org
Subject: Re: [PATCH v4 2/2] iommu/vt-d: don's issue devTLB flush request when
 device is disconnected
Message-ID: <20231221110138.GA27755@wunner.de>
References: <20231220005153.3984502-1-haifeng.zhao@linux.intel.com>
 <20231220005153.3984502-3-haifeng.zhao@linux.intel.com>
 <20231221103940.GA12714@wunner.de>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20231221103940.GA12714@wunner.de>
User-Agent: Mutt/1.10.1 (2018-07-13)

On Thu, Dec 21, 2023 at 11:39:40AM +0100, Lukas Wunner wrote:
> On Tue, Dec 19, 2023 at 07:51:53PM -0500, Ethan Zhao wrote:
> > For those endpoint devices connect to system via hotplug capable ports,
> > users could request a warm reset to the device by flapping device's link
> > through setting the slot's link control register, as pciehpt_ist() DLLSC
> > interrupt sequence response, pciehp will unload the device driver and
> > then power it off. thus cause an IOMMU devTLB flush request for device to
> > be sent and a long time completion/timeout waiting in interrupt context.
> 
> I think the problem is in the "waiting in interrupt context".

I'm wondering whether Intel IOMMUs possibly have a (perhaps undocumented)
capability to reduce the Invalidate Completion Timeout to a sane value?
Could you check whether that's supported?

Granted, the Implementation Note you've pointed to allows 1 sec + 50%,
but that's not even a "must", it's a "should".  So devices are free to
take even longer.  We have to cut off at *some* point.

Thanks,

Lukas