Hi, On Wed, 24 Apr 2013 11:26:14 -0700 H Hartley Sweeten <[email protected]> wrote: > > After merging the final tree, the next-20130424 build (powerpc > allyesconfig) failed like this: > > drivers/staging/comedi/drivers/ni_labpc.c: In function 'labpc_ai_cmd': > drivers/staging/comedi/drivers/ni_labpc.c:980:9: error: > implicit declaration of function 'virt_to_bus' > [-Werror=implicit-function-declaration] > > The virt_to_bus() is only needed for the ISA DMA support in this driver. > > On powerpc, CONFIG_COMEDI_NI_LABPC_ISA cannot be enabled due to the > depends on VIRT_TO_BUS but the PCI driver, ni_labpc_pci, can be enabled. > That driver uses the ni_labpc driver for the common support code shared > by the ISA, PCI, and PCMCIA boards. > > The ISA specific support, and the optional ISA DMA support, are currently > still in the common ni_labpc driver. The ISA specific code is protected > by #if IS_ENABLED(CONFIG_COMEDI_NI_LABPC_ISA) and the ISA DMA support > is protected by #ifdef CONFIG_ISA_DMA_API. This allows the ISA support > to be enabled on architectures that support VIRT_TO_BUS and optionally > enables ISA DMA support if ISA_DMA_API is enabled. > > Unfortunately, the ISA DMA code uses virt_to_bus(). This results in > the build failure for architectures that enable ISA_DMA_API but do not > have VIRT_TO_BUS. > > Add a new member to the private data, dma_addr, to hold the phys_addr_t > returned by virt_to_bus() and initialize it in the ISA specific > labpc_attach(). > > For architectures that enable ISA_DMA_API but not VIRT_TO_BUS, this > will fix the build error. This is also safe for architectures the > enable both options but don't enable COMEDI_NI_LABPC_ISA because the > dma channel (devpriv->dma_chan) is only initialized in the ISA > specific labpc_attach(). > > Signed-off-by: H Hartley Sweeten <[email protected]> > Reported-by: Stephen Rothwell <[email protected]> > Cc: Ian Abbott <[email protected]> > Cc: Greg Kroah-Hartman <[email protected]> > --- > drivers/staging/comedi/drivers/ni_labpc.c | 8 +++++--- > drivers/staging/comedi/drivers/ni_labpc.h | 1 + > 2 files changed, 6 insertions(+), 3 deletions(-) > > diff --git a/drivers/staging/comedi/drivers/ni_labpc.c > b/drivers/staging/comedi/drivers/ni_labpc.c > index 3d978f3..77a7bb6 100644 > --- a/drivers/staging/comedi/drivers/ni_labpc.c > +++ b/drivers/staging/comedi/drivers/ni_labpc.c > @@ -976,8 +976,7 @@ static int labpc_ai_cmd(struct comedi_device *dev, struct > comedi_subdevice *s) > /* clear flip-flop to make sure 2-byte registers for > * count and address get set correctly */ > clear_dma_ff(devpriv->dma_chan); > - set_dma_addr(devpriv->dma_chan, > - virt_to_bus(devpriv->dma_buffer)); > + set_dma_addr(devpriv->dma_chan, devpriv->dma_addr); > /* set appropriate size of transfer */ > devpriv->dma_transfer_size = labpc_suggest_transfer_size(cmd); > if (cmd->stop_src == TRIG_COUNT && > @@ -1089,7 +1088,7 @@ static void labpc_drain_dma(struct comedi_device *dev) > devpriv->count -= num_points; > > /* set address and count for next transfer */ > - set_dma_addr(devpriv->dma_chan, virt_to_bus(devpriv->dma_buffer)); > + set_dma_addr(devpriv->dma_chan, devpriv->dma_addr); > set_dma_count(devpriv->dma_chan, leftover * sample_size); > release_dma_lock(flags); > > @@ -1741,6 +1740,9 @@ static int labpc_attach(struct comedi_device *dev, > struct comedi_devconfig *it) > unsigned long dma_flags; > > devpriv->dma_chan = dma_chan; > + devpriv->dma_addr = > + virt_to_bus(devpriv->dma_buffer); > + > dma_flags = claim_dma_lock(); > disable_dma(devpriv->dma_chan); > set_dma_mode(devpriv->dma_chan, DMA_MODE_READ); > diff --git a/drivers/staging/comedi/drivers/ni_labpc.h > b/drivers/staging/comedi/drivers/ni_labpc.h > index 615f16f..4b691f5 100644 > --- a/drivers/staging/comedi/drivers/ni_labpc.h > +++ b/drivers/staging/comedi/drivers/ni_labpc.h > @@ -82,6 +82,7 @@ struct labpc_private { > unsigned int divisor_b1; > unsigned int dma_chan; /* dma channel to use */ > u16 *dma_buffer; /* buffer ai will dma into */ > + phys_addr_t dma_addr; > /* transfer size in bytes for current transfer */ > unsigned int dma_transfer_size; > /* we are using dma/fifo-half-full/etc. */
I applied this patch as fix patch after the staging tree today and it seems to compile fine. -- Cheers, Stephen Rothwell [email protected]
pgpvCFRJxXEWe.pgp
Description: PGP signature
_______________________________________________ devel mailing list [email protected] http://driverdev.linuxdriverproject.org/mailman/listinfo/devel
