| Message ID | cover.1686057365.git.siyanteng@loongson.cn |
|---|---|
| Headers | show |
| Series | Add Loongson HD Audio support | expand |
On Tue, 06 Jun 2023 15:25:28 +0200, Yanteng Si wrote: > > On loongson controller, RIRBSTS.RINTFL cannot be cleared, > azx_interrupt() is called all the time. We disable RIRB > interrupt, and use polling mode by default. > > Signed-off-by: Yanteng Si <siyanteng@loongson.cn> > Signed-off-by: Yingkun Meng <mengyingkun@loongson.cn> > --- > include/sound/hdaudio.h | 1 + > sound/hda/hdac_controller.c | 5 ++++- > sound/pci/hda/hda_intel.c | 4 ++++ > 3 files changed, 9 insertions(+), 1 deletion(-) > > diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h > index 97f09acae302..a1dcc7f97d08 100644 > --- a/include/sound/hdaudio.h > +++ b/include/sound/hdaudio.h > @@ -346,6 +346,7 @@ struct hdac_bus { > bool reverse_assign:1; /* assign devices in reverse order */ > bool corbrp_self_clear:1; /* CORBRP clears itself after reset */ > bool polling_mode:1; > + bool no_intr_polling_mode:1; It isn't clear enough what this flag does. It's basically prohibiting the RIRB IRQ (hence requiring the polling mode), right? Write it in the comment. > diff --git a/sound/hda/hdac_controller.c b/sound/hda/hdac_controller.c > index 3c7af6558249..705e09cc50ac 100644 > --- a/sound/hda/hdac_controller.c > +++ b/sound/hda/hdac_controller.c > @@ -79,7 +79,10 @@ void snd_hdac_bus_init_cmd_io(struct hdac_bus *bus) > /* set N=1, get RIRB response interrupt for new entry */ > snd_hdac_chip_writew(bus, RINTCNT, 1); > /* enable rirb dma and response irq */ > - snd_hdac_chip_writeb(bus, RIRBCTL, AZX_RBCTL_DMA_EN | AZX_RBCTL_IRQ_EN); > + if (bus->no_intr_polling_mode) > + snd_hdac_chip_writeb(bus, RIRBCTL, AZX_RBCTL_DMA_EN); > + else > + snd_hdac_chip_writeb(bus, RIRBCTL, AZX_RBCTL_DMA_EN | AZX_RBCTL_IRQ_EN); > /* Accept unsolicited responses */ > snd_hdac_chip_updatel(bus, GCTL, AZX_GCTL_UNSOL, AZX_GCTL_UNSOL); > spin_unlock_irq(&bus->reg_lock); > diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c > index 9c353dc7740c..1e8993836fc6 100644 > --- a/sound/pci/hda/hda_intel.c > +++ b/sound/pci/hda/hda_intel.c > @@ -1875,6 +1875,10 @@ static int azx_first_init(struct azx *chip) > if (chip->driver_type == AZX_DRIVER_GFHDMI) > bus->polling_mode = 1; > > + if (chip->driver_type == AZX_DRIVER_LOONGSON) { > + bus->no_intr_polling_mode = 1; > + } Don't you need to set the bus->polling_mode? thanks, Takashi
在 2023/6/6 21:39, Takashi Iwai 写道: > On Tue, 06 Jun 2023 15:25:28 +0200, > Yanteng Si wrote: >> On loongson controller, RIRBSTS.RINTFL cannot be cleared, >> azx_interrupt() is called all the time. We disable RIRB >> interrupt, and use polling mode by default. >> >> Signed-off-by: Yanteng Si <siyanteng@loongson.cn> >> Signed-off-by: Yingkun Meng <mengyingkun@loongson.cn> >> --- >> include/sound/hdaudio.h | 1 + >> sound/hda/hdac_controller.c | 5 ++++- >> sound/pci/hda/hda_intel.c | 4 ++++ >> 3 files changed, 9 insertions(+), 1 deletion(-) >> >> diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h >> index 97f09acae302..a1dcc7f97d08 100644 >> --- a/include/sound/hdaudio.h >> +++ b/include/sound/hdaudio.h >> @@ -346,6 +346,7 @@ struct hdac_bus { >> bool reverse_assign:1; /* assign devices in reverse order */ >> bool corbrp_self_clear:1; /* CORBRP clears itself after reset */ >> bool polling_mode:1; >> + bool no_intr_polling_mode:1; > It isn't clear enough what this flag does. It's basically prohibiting > the RIRB IRQ (hence requiring the polling mode), right? Write it in > the comment. OK! > >> diff --git a/sound/hda/hdac_controller.c b/sound/hda/hdac_controller.c >> index 3c7af6558249..705e09cc50ac 100644 >> --- a/sound/hda/hdac_controller.c >> +++ b/sound/hda/hdac_controller.c >> @@ -79,7 +79,10 @@ void snd_hdac_bus_init_cmd_io(struct hdac_bus *bus) >> /* set N=1, get RIRB response interrupt for new entry */ >> snd_hdac_chip_writew(bus, RINTCNT, 1); >> /* enable rirb dma and response irq */ >> - snd_hdac_chip_writeb(bus, RIRBCTL, AZX_RBCTL_DMA_EN | AZX_RBCTL_IRQ_EN); >> + if (bus->no_intr_polling_mode) >> + snd_hdac_chip_writeb(bus, RIRBCTL, AZX_RBCTL_DMA_EN); >> + else >> + snd_hdac_chip_writeb(bus, RIRBCTL, AZX_RBCTL_DMA_EN | AZX_RBCTL_IRQ_EN); >> /* Accept unsolicited responses */ >> snd_hdac_chip_updatel(bus, GCTL, AZX_GCTL_UNSOL, AZX_GCTL_UNSOL); >> spin_unlock_irq(&bus->reg_lock); >> diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c >> index 9c353dc7740c..1e8993836fc6 100644 >> --- a/sound/pci/hda/hda_intel.c >> +++ b/sound/pci/hda/hda_intel.c >> @@ -1875,6 +1875,10 @@ static int azx_first_init(struct azx *chip) >> if (chip->driver_type == AZX_DRIVER_GFHDMI) >> bus->polling_mode = 1; >> >> + if (chip->driver_type == AZX_DRIVER_LOONGSON) { >> + bus->no_intr_polling_mode = 1; >> + } > Don't you need to set the bus->polling_mode? Yes, I do. Although it works now, some messages will print. Thanks, Yanteng > > > thanks, > > Takashi
v2: * Handling with two new flags added to struct hdac_bus. v1: * The Loongson HDA controller is compatible with High Definition Audio Specification Revision 1.0a. See <https://loongson.github.io/LoongArch-Documentation/Loongson- 7A1000-usermanual-EN.html#hda-controller> Yanteng Si (4): ALSA: hda: Add Loongson LS7A HD-Audio support ALSA: hda: Using polling mode for loongson controller by default ALSA: hda: Workaround for SDnCTL register on loongson controller ALSA: hda/intel: Workaround for WALLCLK register for loongson controller include/linux/pci_ids.h | 3 +++ include/sound/hdaudio.h | 2 ++ sound/hda/hdac_controller.c | 5 ++++- sound/hda/hdac_device.c | 1 + sound/hda/hdac_stream.c | 6 +++++- sound/pci/hda/hda_intel.c | 15 +++++++++++++++ sound/pci/hda/patch_hdmi.c | 1 + 7 files changed, 31 insertions(+), 2 deletions(-)