linux-kernel - Re: [PATCH v2 10/12] NTB: Introduce NTB MSI Test Client

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: <284dae8b-4e8a-1d7b-e806-bf7fed2a39a7@deltatee.com>
Date:   Wed, 6 Mar 2019 14:39:32 -0700
From:   Logan Gunthorpe <logang@...tatee.com>
To:     Serge Semin <fancer.lancer@...il.com>,
        linux-kernel@...r.kernel.org, linux-ntb@...glegroups.com,
        linux-pci@...r.kernel.org, iommu@...ts.linux-foundation.org,
        linux-kselftest@...r.kernel.org, Jon Mason <jdmason@...zu.us>,
        Bjorn Helgaas <bhelgaas@...gle.com>,
        Joerg Roedel <joro@...tes.org>,
        Allen Hubbe <allenbh@...il.com>,
        Dave Jiang <dave.jiang@...el.com>,
        Eric Pilmore <epilmore@...aio.com>
Subject: Re: [PATCH v2 10/12] NTB: Introduce NTB MSI Test Client



On 2019-03-06 1:44 p.m., Serge Semin wrote:
> Alas the test driver is not going to work with IDT NTB hardware,
> since it uses Spad only, which aren't supported by IDT devices. IDT NTB
> PCIe functions provide message registers to communicate with peers. See
> ntb_perf driver code for reference of portable driver design.
> 
> In order to make the test driver portable the following alterations
> are needed:
> 1) Add NTB Message register API usage together with Scratchpad+Doorbell.
> 2) When NTB MSI library is updated with functions like
> ntb_msi_peer_setup_mws()/ntb_msi_peer_clear_mws() they are needed to be
> utilized in the test driver as well to set a translation address on the
> peer side.

Per, the discussion on the previous email, we can update this later once
we actually have sensible infrastructure for it. The mess in ntb_perf is
not something I want to replicate and we don't have any interest in
creating a large amount of infrastructure to support hardware we don't
care about.

Logan