Re: [PATCH v3] ath10k: Fix the MTU size on QCA9377 SDIO

From: Kalle Valo <kvalo@kernel.org>
To: Fabio Estevam <festevam@denx.de>
Cc: ath10k@lists.infradead.org, linux-wireless@vger.kernel.org,
	wgong@codeaurora.org
Subject: Re: [PATCH v3] ath10k: Fix the MTU size on QCA9377 SDIO
Date: Wed, 01 Dec 2021 16:27:07 +0200	[thread overview]
Message-ID: <87sfvcl7t0.fsf@codeaurora.org> (raw)
In-Reply-To: <20211124131047.713756-1-festevam@denx.de> (Fabio Estevam's message of "Wed, 24 Nov 2021 10:10:47 -0300")

Fabio Estevam <festevam@denx.de> writes:

> On an imx6dl-pico-pi board with a QCA9377 SDIO chip, simply trying to
> connect via ssh to another machine causes:
>
> [   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
>
> , leading to an ssh connection failure.
>
> One user inspected the size of frames on Wireshark and reported
> the followig:
>
> "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.
>
> The size of frames that I see on Wireshark is exactly 1500 after
> setting it to 1486."
>
> Clearing the HI_ACS_FLAGS_ALT_DATA_CREDIT_SIZE avoids the problem and
> the ssh command works successfully after that.
>
> 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.
>
> Tested with QCA9377 SDIO with firmware WLAN.TF.1.1.1-00061-QCATFSWPZ-1.
>
> 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.
>
>  drivers/net/wireless/ath/ath10k/core.c | 4 +++-
>  drivers/net/wireless/ath/ath10k/hw.h   | 3 +++
>  2 files changed, 6 insertions(+), 1 deletion(-)
>
> 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[] = {
>  		.ast_skid_limit = 0x10,
>  		.num_wds_entries = 0x20,
>  		.uart_pin_workaround = true,
> +		.credit_size_workaround = true,

I prefer to have also the false cases for every hardware so in the
pending branch I added those:

https://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git/commit/?h=pending&id=afbf52bffb36bc25e7a1e81e1f975bb75696d3c8

-- 
https://patchwork.kernel.org/project/linux-wireless/list/

https://wireless.wiki.kernel.org/en/developers/documentation/submittingpatches