[ath9k-devel] randconfig build error with next-20140519, in drivers/net/wireless/ath/ath9k/dfs.c

[Rajkumar Manoharan <rmanohar@qti.qualcomm.com>]

On Wed, May 21, 2014 at 10:12:26PM +1000, Julian Calaby wrote:
> Hi Rajkumar,
> 
> On Wed, May 21, 2014 at 9:01 PM, Rajkumar Manoharan
> <rmanohar@qti.qualcomm.com> wrote:
> > On Mon, May 19, 2014 at 09:31:16AM -0700, Jim Davis wrote:
> >> Building with the attached random configuration file,
> >>
> >> In file included from drivers/net/wireless/ath/ath9k/eeprom.h:22:0,
> >>                  from drivers/net/wireless/ath/ath9k/hw.h:27,
> >>                  from drivers/net/wireless/ath/ath9k/dfs.c:18:
> >> drivers/net/wireless/ath/ath9k/dfs.c: In function ?ath9k_dfs_process_phyerr?:
> >> drivers/net/wireless/ath/ath9k/dfs.c:185:14: error: ?struct ath_softc?
> >> has no member named ?debug?
> >>     pe.ts - sc->debug.stats.dfs_stats.last_ts);
> >>               ^
> >> drivers/net/wireless/ath/ath9k/../ath.h:273:41: note: in definition of
> >> macro ?ath_dbg?
> >>    ath_printk(KERN_DEBUG, common, fmt, ##__VA_ARGS__); \
> >>                                          ^
> >> drivers/net/wireless/ath/ath9k/dfs.c:186:5: error: ?struct ath_softc?
> >> has no member named ?debug?
> >>    sc->debug.stats.dfs_stats.last_ts = pe.ts;
> >>      ^
> >> make[5]: *** [drivers/net/wireless/ath/ath9k/dfs.o] Error 1
> >
> > Please select CONFIG_ATH9K_DEBUGFS.
> 
> The point of randconfig builds is to ensure that there it's really
> unlikely that there are any config combinations that don't build, even
> if they're utterly insane.
> 
> You should really change the ath9k Kconfig rules or move or add ifdefs
> to prevent this from being possible.
>
Completely agree. But ath9k Kconfig has proper dependecy for
ATH9K_DFS_DEBUGFS. I am wondering how it is selected w/o ATH9K_DEBUGFS.

config ATH9K_DFS_DEBUGFS
        def_bool y
	depends on ATH9K_DEBUGFS && ATH9K_DFS_CERTIFIED

Should it be like this?

config ATH9K_DFS_DEBUGFS
	def_bool y if (ATH9K_DEBUGFS && ATH9K_DFS_CERTIFIED)

-Rajkumar