linux-kernel - Broadcom WiFi SDIO performance regression after commit "mmc: sdhci: Remove finish

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-next>] [day] [month] [year] [list]

Message-ID: <5cf1af89-6026-09ad-7f20-82e19ad49fa1@gmail.com>
Date:   Thu, 27 Aug 2020 09:07:02 +0300
From:   Dmitry Osipenko <digetx@...il.com>
To:     Adrian Hunter <adrian.hunter@...el.com>,
        Ulf Hansson <ulf.hansson@...aro.org>,
        Arend van Spriel <arend.vanspriel@...adcom.com>,
        Franky Lin <franky.lin@...adcom.com>,
        Hante Meuleman <hante.meuleman@...adcom.com>,
        Chi-Hsien Lin <chi-hsien.lin@...ress.com>,
        Wright Feng <wright.feng@...ress.com>,
        brcm80211-dev-list@...ress.com,
        brcm80211-dev-list.pdl@...adcom.com,
        "linux-tegra@...r.kernel.org" <linux-tegra@...r.kernel.org>,
        linux-mmc <linux-mmc@...r.kernel.org>,
        Linux Kernel Mailing List <linux-kernel@...r.kernel.org>
Subject: Broadcom WiFi SDIO performance regression after commit "mmc: sdhci:
 Remove finish_tasklet"

Hello!

I was debugging WiFi performance problems on Acer A500 tablet device
that has BCM4329 WiFi chip which is connected to NVIDIA Terga20 SoC via
SDIO and found that the following commit causes a solid 5-10 Mbit/s of
WiFi throughput regression after 5.2 kernel:

commit c07a48c2651965e84d35cf193dfc0e5f7892d612
Author: Adrian Hunter <adrian.hunter@...el.com>
Date:   Fri Apr 5 15:40:20 2019 +0300

    mmc: sdhci: Remove finish_tasklet

    Remove finish_tasklet. Requests that require DMA-unmapping or
sdhci_reset
    are completed either in the IRQ thread or a workqueue if the
completion is
    not initiated by the IRQ.

Reverting the offending commit on top of recent linux-next resolves the
problem.

Ulf / Adrian, do you have any ideas what could be done in regards to
restoring the SDIO performance? Should we just revert the offending commit?