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]
Date:   Thu, 12 Jan 2023 12:41:55 -0700
From:   "Subash Abhinov Kasiviswanathan (KS)" <quic_subashab@...cinc.com>
To:     Daniele Palmas <dnlplm@...il.com>,
        David Miller <davem@...emloft.net>,
        Jakub Kicinski <kuba@...nel.org>,
        Paolo Abeni <pabeni@...hat.com>,
        "Eric Dumazet" <edumazet@...gle.com>,
        Sean Tranchetti <quic_stranche@...cinc.com>,
        Jonathan Corbet <corbet@....net>,
        Alexander Lobakin <alexandr.lobakin@...el.com>,
        Gal Pressman <gal@...dia.com>, Dave Taht <dave.taht@...il.com>
CC:     Bjørn Mork <bjorn@...k.no>,
        Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        <netdev@...r.kernel.org>
Subject: Re: [PATCH net-next v4 2/3] net: qualcomm: rmnet: add tx packets
 aggregation



On 1/11/2023 6:05 AM, Daniele Palmas wrote:
> Add tx packets aggregation.
> 
> Bidirectional TCP throughput tests through iperf with low-cat
> Thread-x based modems revelead performance issues both in tx
> and rx.
> 
> The Windows driver does not show this issue: inspecting USB
> packets revealed that the only notable change is the driver
> enabling tx packets aggregation.
> 
> Tx packets aggregation is by default disabled and can be enabled
> by increasing the value of ETHTOOL_A_COALESCE_TX_MAX_AGGR_FRAMES.
> 
> The maximum aggregated size is by default set to a reasonably low
> value in order to support the majority of modems.
> 
> This implementation is based on patches available in Code Aurora
> repositories (msm kernel) whose main authors are
> 
> Subash Abhinov Kasiviswanathan <subashab@...eaurora.org>
> Sean Tranchetti <stranche@...eaurora.org>
> 
> Signed-off-by: Daniele Palmas <dnlplm@...il.com>
> ---
> Hi all,
> 
> in v4 I should have met all Paolo's remarks, besides the one related
> to removing the scheduled work, since according to my understanding
> of the code in dev_queue_xmit it's not possible to avoid the
> WARN_ONCE when called directly from the timer function.
> 
> Context at https://lore.kernel.org/netdev/CAGRyCJGHSPO+i_xKHGbNg+Hki5tQC3_6Kc8RNcHWN6pxQdjODw@mail.gmail.com/
> 
> v4
> - Solved race when accessing egress_agg_params
> - Removed duplicated code for error in rmnet_map_tx_aggregate

Hi Daniele

I see that you are calling dev_queue_xmit from the worker thread context 
only so I assume you aren't running into any warnings anymore.


Reviewed-by: Subash Abhinov Kasiviswanathan <quic_subashab@...cinc.com>

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ