linux-kernel - Re: [PATCH] mwifiex: Add quirk to disable deep sleep with certain hardware revision

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, 28 Oct 2021 11:07:11 +0300
From:   Andy Shevchenko <andy.shevchenko@...il.com>
To:     Jonas Dreßler <verdre@...d.nl>
Cc:     Amitkumar Karwar <amitkarwar@...il.com>,
        Ganapathi Bhat <ganapathi017@...il.com>,
        Xinming Hu <huxinming820@...il.com>,
        Kalle Valo <kvalo@...eaurora.org>,
        "David S. Miller" <davem@...emloft.net>,
        Jakub Kicinski <kuba@...nel.org>,
        Tsuchiya Yuto <kitakar@...il.com>,
        "open list:TI WILINK WIRELES..." <linux-wireless@...r.kernel.org>,
        netdev <netdev@...r.kernel.org>,
        Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
        Maximilian Luz <luzmaximilian@...il.com>,
        Andy Shevchenko <andriy.shevchenko@...ux.intel.com>,
        Bjorn Helgaas <bhelgaas@...gle.com>,
        Pali Rohár <pali@...nel.org>
Subject: Re: [PATCH] mwifiex: Add quirk to disable deep sleep with certain
 hardware revision

On Thu, Oct 28, 2021 at 10:38 AM Jonas Dreßler <verdre@...d.nl> wrote:
>
> The 88W8897 PCIe+USB card in the hardware revision 20 apparently has a
> hardware issue where the card wakes up from deep sleep randomly and very
> often, somewhat depending on the card activity, maybe the hardware has a
> floating wakeup pin or something.
>
> Those continuous wakeups prevent the card from entering host sleep when
> the computer suspends. And because the host won't answer to events from
> the card anymore while it's suspended, the firmwares internal
> powersaving state machine seems to get confused and the card can't sleep

power saving

> anymore at all after that.
>
> Since we can't work around that hardware bug in the firmware, let's
> get the hardware revision string from the firmware and match it with
> known bad revisions. Then disable auto deep sleep for those revisions,
> which makes sure we no longer get those spurious wakeups.

...

> +static void maybe_quirk_fw_disable_ds(struct mwifiex_adapter *adapter)
> +{
> +       struct mwifiex_private *priv = mwifiex_get_priv(adapter, MWIFIEX_BSS_ROLE_STA);
> +       struct mwifiex_ver_ext ver_ext;

> +       set_bit(MWIFIEX_IS_REQUESTING_FW_VEREXT, &adapter->work_flags);

This does not bring atomicity to this function.
You need test_and_set_bit().

Otherwise the bit may very well be cleared already here. And function
may enter here again.

If this state machine is protected by lock or so, then why not use
__set_bit() to show this clearly?

> +       memset(&ver_ext, 0, sizeof(ver_ext));
> +       ver_ext.version_str_sel = 1;
> +       mwifiex_send_cmd(priv, HostCmd_CMD_VERSION_EXT,
> +                        HostCmd_ACT_GEN_GET, 0, &ver_ext, false);
> +}


-- 
With Best Regards,
Andy Shevchenko