11 Dec
2015
11 Dec
'15
10:51 a.m.
On Fri, 11 Dec 2015 10:25:27 +0100, Vinod Koul wrote:
On Fri, Dec 11, 2015 at 09:54:42AM +0100, Takashi Iwai wrote:
+static void update_pci_dword(struct pci_dev *pci,
unsigned int reg, u32 mask, u32 val)+{
- u32 data;
- pci_read_config_dword(pci, reg, &data);
- data &= ~mask;
- data |= (val & mask);
- pci_write_config_dword(pci, reg, data);
+}
+void snd_hdac_ext_bus_enable_miscbdcge(struct device *dev, bool enable) +{
- struct pci_dev *pci = to_pci_dev(dev);
- u32 val;
- val = enable ? AZX_CGCTL_MISCBDCGE_MASK : 0;
- update_pci_dword(pci, AZX_PCIREG_CGCTL, AZX_CGCTL_MISCBDCGE_MASK, val);
+} +EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_enable_miscbdcge);
PCI access doesn't belong in the HDA-core in general. It's over the abstraction level of HD-audio controller.
Okay but this is part of HDA controller and I think we might be using this bit so move to core for common usage.
No, PCI isn't common. Look through sound/hda directory once. sound/hda/* is the place to handle the HD-audio bus itself.
I can move to driver if you feel that is better approach
Yes, it's better.
Takashi