[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-ID: <87y2jaipwu.fsf@nanos.tec.linutronix.de>
Date: Mon, 09 Nov 2020 15:08:17 +0100
From: Thomas Gleixner <tglx@...utronix.de>
To: "Raj\, Ashok" <ashok.raj@...el.com>
Cc: Jason Gunthorpe <jgg@...dia.com>,
Dan Williams <dan.j.williams@...el.com>,
"Tian\, Kevin" <kevin.tian@...el.com>,
"Jiang\, Dave" <dave.jiang@...el.com>,
Bjorn Helgaas <helgaas@...nel.org>,
"vkoul\@kernel.org" <vkoul@...nel.org>,
"Dey\, Megha" <megha.dey@...el.com>,
"maz\@kernel.org" <maz@...nel.org>,
"bhelgaas\@google.com" <bhelgaas@...gle.com>,
"alex.williamson\@redhat.com" <alex.williamson@...hat.com>,
"Pan\, Jacob jun" <jacob.jun.pan@...el.com>,
"Liu\, Yi L" <yi.l.liu@...el.com>,
"Lu\, Baolu" <baolu.lu@...el.com>,
"Kumar\, Sanjay K" <sanjay.k.kumar@...el.com>,
"Luck\, Tony" <tony.luck@...el.com>,
"kwankhede\@nvidia.com" <kwankhede@...dia.com>,
"eric.auger\@redhat.com" <eric.auger@...hat.com>,
"parav\@mellanox.com" <parav@...lanox.com>,
"rafael\@kernel.org" <rafael@...nel.org>,
"netanelg\@mellanox.com" <netanelg@...lanox.com>,
"shahafs\@mellanox.com" <shahafs@...lanox.com>,
"yan.y.zhao\@linux.intel.com" <yan.y.zhao@...ux.intel.com>,
"pbonzini\@redhat.com" <pbonzini@...hat.com>,
"Ortiz\, Samuel" <samuel.ortiz@...el.com>,
"Hossain\, Mona" <mona.hossain@...el.com>,
"dmaengine\@vger.kernel.org" <dmaengine@...r.kernel.org>,
"linux-kernel\@vger.kernel.org" <linux-kernel@...r.kernel.org>,
"linux-pci\@vger.kernel.org" <linux-pci@...r.kernel.org>,
"kvm\@vger.kernel.org" <kvm@...r.kernel.org>,
Ashok Raj <ashok.raj@...el.com>
Subject: Re: [PATCH v4 06/17] PCI: add SIOV and IMS capability detection
On Mon, Nov 09 2020 at 12:14, Thomas Gleixner wrote:
> On Sun, Nov 08 2020 at 15:58, Ashok Raj wrote:
>> On Sun, Nov 08, 2020 at 07:47:24PM +0100, Thomas Gleixner wrote:
>> But for SIOV devices there is no PASID filtering at the remap level since
>> interrupt messages don't carry PASID in the TLP.
>
> Why do we need PASID for VMM integrity?
>
> If the device sends a message then the remap unit will see the requester
> ID of the device and if the message it sends is not
That made me look at patch 4/17 which adds DEVMSI support to the
remap code:
> + case X86_IRQ_ALLOC_TYPE_DEV_MSI:
> + irte_prepare_msg(msg, index, sub_handle);
> break;
It does not setup any requester-id filter in IRTE. How is that supposed
to be correct?
Thanks,
tglx
Powered by blists - more mailing lists