Re: linux-next: build failure after merge of the final tree (staging related)

[Greg KH <greg@kroah.com>]

On Thu, Jun 09, 2011 at 05:27:45PM +1000, Stephen Rothwell wrote:
> Hi Greg,
> 
> After merging the final tree, today's linux-next build (powerpc allyesconfig)
> failed like this:
> 
> drivers/staging/brcm80211/brcmsmac/ampdu.c: In function 'wlc_ampdu_dotxstatus':
> drivers/staging/brcm80211/brcmsmac/ampdu.c:840:17: error: invalid operands to binary ^ (have 'volatile u32 *' and 'int')
> drivers/staging/brcm80211/brcmsmac/ampdu.c:840:17: error: invalid operands to binary ^ (have 'volatile u32 *' and 'int')
> drivers/staging/brcm80211/brcmsmac/ampdu.c:848:8: error: invalid operands to binary ^ (have 'volatile u32 *' and 'int')
> drivers/staging/brcm80211/brcmsmac/ampdu.c:848:8: error: invalid operands to binary ^ (have 'volatile u32 *' and 'int')
> drivers/staging/brcm80211/brcmsmac/bmac.c: In function 'wlc_bmac_update_slot_timing':
> drivers/staging/brcm80211/brcmsmac/bmac.c:186:3: error: invalid operands to binary ^ (have 'volatile u16 *' and 'int')
> drivers/staging/brcm80211/brcmsmac/bmac.c:186:3: error: invalid operands to binary ^ (have 'volatile u16 *' and 'int')
> drivers/staging/brcm80211/brcmsmac/bmac.c:190:3: error: invalid operands to binary ^ (have 'volatile u16 *' and 'int')
> drivers/staging/brcm80211/brcmsmac/bmac.c:190:3: error: invalid operands to binary ^ (have 'volatile u16 *' and 'int')
> drivers/staging/brcm80211/brcmsmac/bmac.c: In function 'wlc_setband_inact':
> drivers/staging/brcm80211/brcmsmac/bmac.c:234:2: error: invalid operands to binary ^ (have 'volatile u32 *' and 'int')
> drivers/staging/brcm80211/brcmsmac/bmac.c:234:2: error: invalid operands to binary ^ (have 'volatile u32 *' and 'int')
> drivers/staging/brcm80211/brcmsmac/bmac.c: In function 'wlc_dpc':
> drivers/staging/brcm80211/brcmsmac/bmac.c:311:6: error: invalid operands to binary ^ (have 'volatile u32 *' and 'int')
> 
> (and lots more)

Fun :(

This looks messy.  It's a macro that is trying to be cute by doing:
#define R_REG(r) \
        ({ \
                __typeof(*(r)) __osl_v; \
                __asm__ __volatile__("sync"); \
                __osl_v = bcmsdh_reg_read(NULL, (unsigned long)(r),\
                                          sizeof(*(r))); \
                __asm__ __volatile__("sync"); \
                __osl_v; \
        })

on big-endian, non-mips platforms.  Which I really doubt has ever
been tested before.

Roland, Brett, any thoughts?

Should I just disable this module from being build on PPC as it doesn't
look like its ever been tested or run on that platform before.

> Also in several other files in drivers/staging/brcm80211/
> 
> Also:
> 
> drivers/staging/comedi/drivers.c: In function 'comedi_buf_alloc':
> drivers/staging/comedi/drivers.c:505:37: error: 'PAGE_KERNEL_NOCACHE' undeclared (first use in this function)
> In file included from drivers/staging/comedi/drivers/addi_apci_035.c:7:0:
> drivers/staging/comedi/drivers/addi-data/addi_common.c: In function 'i_ADDI_Attach':
> drivers/staging/comedi/drivers/addi-data/addi_common.c:2765:7: error: implicit declaration of function 'virt_to_bus'
> 
> (Also several other occurrences of that one)

I'll fix this up, it looks just like a #include that needs to be added.

thanks,

greg k-h