netdev - Re: [PATCH net-next v5 0/5] Introduce NETIF_F_GRO

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: <CACKFLikWp55v8kyLOUVKVevHDyjRKAKiBFogPRg393MKyshKDQ@mail.gmail.com>
Date:   Tue, 8 Jan 2019 02:58:23 -0800
From:   Michael Chan <michael.chan@...adcom.com>
To:     Shay Agroskin <shayag@...lanox.com>
Cc:     "davem@...emloft.net" <davem@...emloft.net>,
        "netdev@...r.kernel.org" <netdev@...r.kernel.org>,
        "andrew.gospodarek@...adcom.com" <andrew.gospodarek@...adcom.com>,
        Tariq Toukan <tariqt@...lanox.com>,
        Eran Ben Elisha <eranbe@...lanox.com>,
        Saeed Mahameed <saeedm@...lanox.com>
Subject: Re: [PATCH net-next v5 0/5] Introduce NETIF_F_GRO_HW

On Mon, Jan 7, 2019 at 6:00 AM Shay Agroskin <shayag@...lanox.com> wrote:

> a) All segments (aggregated packets) must be of the same size (except possibly the last one).
> (This in order to know each segments size, when re-segmenting an aggregated packet)
>
> b) IP ID must be incrementing unless DF is
> (To have  the whole 4th layer, in order to know if a packet belongs to a certain flow)
>
> c) Also, all the other fields need to be the same to belong to the same flow and be aggregated.
>
> Any thoughts? Do I miss anything here ?

In addition, the GRO SKB needs to be setup properly.  For example, the
gso_type, gso_size, gso_segs, CHECKSUM_PARTIAL, etc, all have to be
setup.  Hardware needs to provide all the necessary information to set
this up.  In case this GRO SKB is re-routed to an output device, TSO
or GSO needs to be performed on the packet and the original packet
stream should be re-constituted exactly.