Message ID | 20211124131047.713756-1-festevam@denx.de (mailing list archive) |
---|---|
State | Accepted |
Commit | 09b8cd69edcf2be04a781e1781e98e52a775c9ad |
Delegated to: | Kalle Valo |
Headers | show |
Series | [v3] ath10k: Fix the MTU size on QCA9377 SDIO | expand |
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
> On 1 Dec 2021, at 6:27 pm, Kalle Valo <kvalo@kernel.org> wrote: > > 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 ^ 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>
Hi Kalle, On 01/12/2021 11:27, Kalle Valo wrote: > 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 It looks good. Thanks for the adjustment. Thanks, Fabio Estevam
Fabio Estevam <festevam@denx.de> wrote: > 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> > Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com> Patch applied to ath-next branch of ath.git, thanks. 09b8cd69edcf ath10k: Fix the MTU size on QCA9377 SDIO
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, .dynamic_sar_support = false, }, { @@ -715,6 +716,7 @@ static void ath10k_send_suspend_complete(struct ath10k *ar) static int ath10k_init_sdio(struct ath10k *ar, enum ath10k_firmware_mode mode) { + bool mtu_workaround = ar->hw_params.credit_size_workaround; int ret; u32 param = 0; @@ -732,7 +734,7 @@ static int ath10k_init_sdio(struct ath10k *ar, enum ath10k_firmware_mode mode) param |= HI_ACS_FLAGS_SDIO_REDUCE_TX_COMPL_SET; - if (mode == ATH10K_FIRMWARE_MODE_NORMAL) + if (mode == ATH10K_FIRMWARE_MODE_NORMAL && !mtu_workaround) param |= HI_ACS_FLAGS_ALT_DATA_CREDIT_SIZE; else param &= ~HI_ACS_FLAGS_ALT_DATA_CREDIT_SIZE; diff --git a/drivers/net/wireless/ath/ath10k/hw.h b/drivers/net/wireless/ath/ath10k/hw.h index 6b03c7787e36..591ef7416b61 100644 --- a/drivers/net/wireless/ath/ath10k/hw.h +++ b/drivers/net/wireless/ath/ath10k/hw.h @@ -618,6 +618,9 @@ struct ath10k_hw_params { */ bool uart_pin_workaround; + /* Workaround for the credit size calculation */ + bool credit_size_workaround; + /* tx stats support over pktlog */ bool tx_stats_over_pktlog;
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(-)