[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <20200329204501.GF4675@SDF.ORG>
Date: Sun, 29 Mar 2020 20:45:01 +0000
From: George Spelvin <lkml@....ORG>
To: Jason Gunthorpe <jgg@...pe.ca>
Cc: Bernard Metzler <BMT@...ich.ibm.com>, linux-kernel@...r.kernel.org,
Doug Ledford <dledford@...hat.com>, linux-rdma@...r.kernel.org,
Faisal Latif <faisal.latif@...el.com>,
Shiraz Saleem <shiraz.saleem@...el.com>,
Bart Van Assche <bvanassche@....org>, lkml@....org
Subject: Re: [RFC PATCH v1 42/50] drivers/ininiband: Use get_random_u32()
On Sun, Mar 29, 2020 at 05:02:13PM -0300, Jason Gunthorpe wrote:
> On Sun, Mar 29, 2020 at 04:52:04PM +0000, George Spelvin wrote:
>> Many intra-machine networks (like infiniband) are specifically not
>> designed to be robust in the face of malicious actors on the network.
>
> This is not really true at all..
Eep, this came out wrong! Let me clarify:
Many intra-machine networks like SCSI, LPC, HyperTransport, QuickPath,
and I2C are specifically not designed to be robust in the face of malicious
actors on the network/bus.
I don't know, *and was wondering*, whether this is true of Infiniband.
Does that make more sense?
Powered by blists - more mailing lists