On Mon, Jan 24, 2022 at 05:08:15PM +0100, Greg KH wrote:
> On Mon, Jan 24, 2022 at 12:44:54PM -0300, Fabio Estevam wrote:
> > [ Upstream commit 09b8cd69edcf2be04a781e1781e98e52a775c9ad ]
> >
> > 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@xxxxxxx>
> > Signed-off-by: Kalle Valo <quic_kvalo@xxxxxxxxxxx>
> > Link: https://lore.kernel.org/r/20211124131047.713756-1-festevam@xxxxxxx
> > ---
> > Hi,
> >
> > This is the resolution for the linux-stable 5.10 tree.
>
> Now queued up, thanks.
Nope this breaks the build :(
Dropping it again.
