Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Sat, 29 Aug 2020 08:24:05 +0100
From:   "hch@infradead.org" <hch@infradead.org>
To:     "Limonciello, Mario" <Mario.Limonciello@dell.com>
Cc:     "hch@infradead.org" <hch@infradead.org>,
        "Derrick, Jonathan" <jonathan.derrick@intel.com>,
        "wangxiongfeng2@huawei.com" <wangxiongfeng2@huawei.com>,
        "kw@linux.com" <kw@linux.com>,
        "hkallweit1@gmail.com" <hkallweit1@gmail.com>,
        "kai.heng.feng@canonical.com" <kai.heng.feng@canonical.com>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
        "mika.westerberg@linux.intel.com" <mika.westerberg@linux.intel.com>,
        "linux-pci@vger.kernel.org" <linux-pci@vger.kernel.org>,
        "Williams, Dan J" <dan.j.williams@intel.com>,
        "bhelgaas@google.com" <bhelgaas@google.com>,
        "Huffman, Amber" <amber.huffman@intel.com>,
        "Wysocki, Rafael J" <rafael.j.wysocki@intel.com>
Subject: Re: [PATCH] PCI/ASPM: Enable ASPM for links under VMD domain
Message-ID: <20200829072405.GB6704@infradead.org>
References: <20200821123222.32093-1-kai.heng.feng@canonical.com>
 <20200825062320.GA27116@infradead.org>
 <cd5aa2fef13f14b30c139d03d5256cf93c7195dc.camel@intel.com>
 <20200827063406.GA13738@infradead.org>
 <660c8671a51eec447dc7fab22bacbc9c600508d9.camel@intel.com>
 <20200827162333.GA6822@infradead.org>
 <DM6PR19MB2636ACECA16E43638B502A6DFA550@DM6PR19MB2636.namprd19.prod.outlook.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <DM6PR19MB2636ACECA16E43638B502A6DFA550@DM6PR19MB2636.namprd19.prod.outlook.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Thu, Aug 27, 2020 at 05:49:40PM +0000, Limonciello, Mario wrote:
> Can you further elaborate what exactly you're wanting here?  VMD enable/disable
> is something that is configured in firmware setup as the firmware does the early
> configuration for the silicon related to it.  So it's up to the OEM whether to
> offer the knob to an end user.
> 
> At least for Dell this setting also does export to sysfs and can be turned on/off
> around a reboot cycle via this: https://patchwork.kernel.org/patch/11693231/.
> 
> As was mentioned earlier in this thread VMD is likely to be defaulting to "on"
> for many machines with the upcoming silicon.  Making it work well on Linux is
> preferable to again having to change firmware settings between operating systems
> like the NVME remapping thing from earlier silicon required.

And the right answer is to turn it off, but we really need to do that
at runtime, and not over a reboot cycle..