Re: Hard lockup during vif restart tests.

Michal Kazior michal.kaz...@tieto.com writes: Why do we reset the firmware/NIC when we admin down/up the vif (when a single vif is active)? Couldn't we just keep the firmware active in this state and not risk lockup due to reset? If you put down last interface mac80211 calls drv_stop().

[PATCH 7/9] ath10k: clean up phyerr code

Make the phyerr structures more compact and easier to understand. Also add constness. Signed-off-by: Michal Kazior michal.kaz...@tieto.com --- drivers/net/wireless/ath/ath10k/spectral.c | 34 --- drivers/net/wireless/ath/ath10k/spectral.h | 8 +-- drivers/net/wireless/ath/ath10k/wmi.c

[PATCH 1/9] ath10k: fix tx/rx chainmask init

Firmware reports the number of RF chains so use that for initialization of supp_{tx,rx}_chainmask instead of using a macro for 3x3 chips. This should make tx/rx chainmask reports correct for chips other than 3x3. Signed-off-by: Michal Kazior michal.kaz...@tieto.com ---

[PATCH 2/9] ath10k: remove unused pdev_set_channel command

This command is not used anymore and most firmware revisions do not seem to handle it well. Channel switching is done via vdev restarting. Signed-off-by: Michal Kazior michal.kaz...@tieto.com --- drivers/net/wireless/ath/ath10k/wmi.c | 36 ---

[PATCH 6/9] ath10k: deduplicate wmi service ready logic

The logic responsible for processing the event is no different across different firmware binaries. The difference that needs to be dealt with is the ABI of data structures. The intermediate structure uses __le32 to avoid extra memory allocations to byteswap variable-length substructures (i.e.

[PATCH 9/9] ath10k: re-work scan start command building

This gets rid of the ugly scan structure building and uses a saner way to do it. Signed-off-by: Michal Kazior michal.kaz...@tieto.com --- drivers/net/wireless/ath/ath10k/wmi.c | 191 ++ drivers/net/wireless/ath/ath10k/wmi.h | 100 +++--- 2 files

[PATCH 5/9] ath10k: relocate wmi attach/deatch functions

Init functions should be placed at the end of files in most cases to avoid forward declarations for static functions. Signed-off-by: Michal Kazior michal.kaz...@tieto.com --- drivers/net/wireless/ath/ath10k/wmi.c | 77 +-- 1 file changed, 38 insertions(+), 39

[PATCH 4/9] ath10k: deduplicate host mem chunk code

Simplify the code by deduplicating structure definitions and code. Signed-off-by: Michal Kazior michal.kaz...@tieto.com --- drivers/net/wireless/ath/ath10k/wmi.c | 103 +- drivers/net/wireless/ath/ath10k/wmi.h | 30 +++--- 2 files changed, 34 insertions(+),

[PATCH 0/3] ath10k: debug improvements

Hi, This adds extra prints and information for debugging purposes. Michal Kazior (3): ath10k: print wmi version info ath10k: dump hex bytes with dev string prefix ath10k: add debug dump for pci rx drivers/net/wireless/ath/ath10k/debug.c | 29 ++---

[PATCH 3/3] ath10k: add debug dump for pci rx

This makes it easier to debug the device-target communication at a very low level. Signed-off-by: Michal Kazior michal.kaz...@tieto.com --- drivers/net/wireless/ath/ath10k/pci.c | 6 ++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/wireless/ath/ath10k/pci.c

[PATCH 1/3] ath10k: print wmi version info

HTT version is already printed so print WMI version as well for consistency. Signed-off-by: Michal Kazior michal.kaz...@tieto.com --- drivers/net/wireless/ath/ath10k/debug.c | 8 ++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/ath/ath10k/debug.c

Re: Hard lockup during vif restart tests.

On 09/18/2014 12:31 AM, Kalle Valo wrote: Michal Kazior michal.kaz...@tieto.com writes: Why do we reset the firmware/NIC when we admin down/up the vif (when a single vif is active)? Couldn't we just keep the firmware active in this state and not risk lockup due to reset? If you put down

Re: [PATCH 1/9] ath10k: fix tx/rx chainmask init

On 09/18/2014 06:21 AM, Michal Kazior wrote: Firmware reports the number of RF chains so use that for initialization of supp_{tx,rx}_chainmask instead of using a macro for 3x3 chips. This should make tx/rx chainmask reports correct for chips other than 3x3. diff --git