Received-SPF: pass (google.com: domain of linux-wireless-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
MIME-Version: 1.0
References: <20211028073729.24408-1-verdre@v0yd.nl>
In-Reply-To: <20211028073729.24408-1-verdre@v0yd.nl>
From:   Andy Shevchenko <andy.shevchenko@gmail.com>
Date:   Thu, 28 Oct 2021 11:07:11 +0300
Message-ID: <CAHp75Ve3Rp7AziB8k8ESM41xEV8uNWD21Wh_MPcRqfDcJ0QR-w@mail.gmail.com>
Subject: Re: [PATCH] mwifiex: Add quirk to disable deep sleep with certain
 hardware revision
To:     =?UTF-8?Q?Jonas_Dre=C3=9Fler?= <verdre@v0yd.nl>
Cc:     Amitkumar Karwar <amitkarwar@gmail.com>,
        Ganapathi Bhat <ganapathi017@gmail.com>,
        Xinming Hu <huxinming820@gmail.com>,
        Kalle Valo <kvalo@codeaurora.org>,
        "David S. Miller" <davem@davemloft.net>,
        Jakub Kicinski <kuba@kernel.org>,
        Tsuchiya Yuto <kitakar@gmail.com>,
        "open list:TI WILINK WIRELES..." <linux-wireless@vger.kernel.org>,
        netdev <netdev@vger.kernel.org>,
        Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
        Maximilian Luz <luzmaximilian@gmail.com>,
        Andy Shevchenko <andriy.shevchenko@linux.intel.com>,
        Bjorn Helgaas <bhelgaas@google.com>,
        =?UTF-8?Q?Pali_Roh=C3=A1r?= <pali@kernel.org>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
Precedence: bulk

On Thu, Oct 28, 2021 at 10:38 AM Jonas Dre=C3=9Fler <verdre@v0yd.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 =3D mwifiex_get_priv(adapter, MWIFIE=
X_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 =3D 1;
> +       mwifiex_send_cmd(priv, HostCmd_CMD_VERSION_EXT,
> +                        HostCmd_ACT_GEN_GET, 0, &ver_ext, false);
> +}


--=20
With Best Regards,
Andy Shevchenko