Sender: andrew@hewittfamily.org.uk
Content-Type: text/plain;
        charset=us-ascii
Mime-Version: 1.0 (Mac OS X Mail 13.4 \(3608.120.23.2.7\))
Subject: Re: [PATCH v3] ath10k: Fix the MTU size on QCA9377 SDIO
From:   Christian Hewitt <andrew@hewittfamily.org.uk>
In-Reply-To: <87sfvcl7t0.fsf@codeaurora.org>
Date:   Thu, 2 Dec 2021 13:13:33 +0400
Cc:     Fabio Estevam <festevam@denx.de>, ath10k@lists.infradead.org,
        linux-wireless@vger.kernel.org, wgong@codeaurora.org
Content-Transfer-Encoding: quoted-printable
Message-Id: <DFDFA699-65BD-47AC-852D-09ABF44567BD@hewittfamily.org.uk>
References: <20211124131047.713756-1-festevam@denx.de>
 <87sfvcl7t0.fsf@codeaurora.org>
To:     Kalle Valo <kvalo@kernel.org>
Precedence: bulk


> On 1 Dec 2021, at 6:27 pm, Kalle Valo <kvalo@kernel.org> wrote:
>=20
> Fabio Estevam <festevam@denx.de> writes:
>=20
>> On an imx6dl-pico-pi board with a QCA9377 SDIO chip, simply trying to
>> connect via ssh to another machine causes:
>>=20
>> [   55.824159] ath10k_sdio mmc1:0001:1: failed to transmit packet, =
dropping: -12
>> [   55.832169] ath10k_sdio mmc1:0001:1: failed to submit frame: -12
>> [   55.838529] ath10k_sdio mmc1:0001:1: failed to push frame: -12
>> [   55.905863] ath10k_sdio mmc1:0001:1: failed to transmit packet, =
dropping: -12
>> [   55.913650] ath10k_sdio mmc1:0001:1: failed to submit frame: -12
>> [   55.919887] ath10k_sdio mmc1:0001:1: failed to push frame: -12
>>=20
>> , leading to an ssh connection failure.
>>=20
>> One user inspected the size of frames on Wireshark and reported
>> the followig:
>>=20
>> "I was able to narrow the issue down to the mtu. If I set the mtu for
>> the wlan0 device to 1486 instead of 1500, the issue does not happen.
>>=20
>> The size of frames that I see on Wireshark is exactly 1500 after
>> setting it to 1486."
>>=20
>> Clearing the HI_ACS_FLAGS_ALT_DATA_CREDIT_SIZE avoids the problem and
>> the ssh command works successfully after that.
>>=20
>> Introduce a 'credit_size_workaround' field to ath10k_hw_params for
>> the QCA9377 SDIO, so that the HI_ACS_FLAGS_ALT_DATA_CREDIT_SIZE
>> is not set in this case.
>>=20
>> Tested with QCA9377 SDIO with firmware =
WLAN.TF.1.1.1-00061-QCATFSWPZ-1.
>>=20
>> Fixes: 2f918ea98606 ("ath10k: enable alt data of TX path for sdio")
>> Signed-off-by: Fabio Estevam <festevam@denx.de>
>> ---
>> Changes since v2:
>> - Set the credit_size_workaround field as true for QCA9377 SDIO.
>>=20
>> drivers/net/wireless/ath/ath10k/core.c | 4 +++-
>> drivers/net/wireless/ath/ath10k/hw.h   | 3 +++
>> 2 files changed, 6 insertions(+), 1 deletion(-)
>>=20
>> diff --git a/drivers/net/wireless/ath/ath10k/core.c =
b/drivers/net/wireless/ath/ath10k/core.c
>> index 72a366aa9f60..8a325ae97b0e 100644
>> --- a/drivers/net/wireless/ath/ath10k/core.c
>> +++ b/drivers/net/wireless/ath/ath10k/core.c
>> @@ -571,6 +571,7 @@ static const struct ath10k_hw_params =
ath10k_hw_params_list[] =3D {
>> 		.ast_skid_limit =3D 0x10,
>> 		.num_wds_entries =3D 0x20,
>> 		.uart_pin_workaround =3D true,
>> +		.credit_size_workaround =3D true,
>=20
> I prefer to have also the false cases for every hardware so in the
> pending branch I added those:
>=20
> =
https://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git/commit/?h=3D=
pending&id=3Dafbf52bffb36bc25e7a1e81e1f975bb75696d3c8

^ for the patch in the pending branch, tested with an Amlogic S905D
TV box with QCA9377 SDIO module:

Tested-by: Christian Hewitt <christianshewitt@gmail.com>