On 09/17/2007 02:26 PM, Krzysztof Helt wrote:
Look at the code. Shifting the fm_port address by 8 (Rene's) is correct way to do as the OPL3 is searched at fm_port and fm_port +2, but the OPL4 is searched at fm_port and fm_port -8 (which will be the fm_port before shifting).
Ah, damn, crap. Yes, forget the version I just sent. Original (attached) was correct. Thanks for paying attention.
Is the OPL4 located at 0x380 and 0x388 or 0x378 and 0x380? If the former, the Rene's patch is correct.
The OPL4 is at 0x380, with its OPL3 compatible part at 0x388. Could you add an Acked-by?
=== opti9xx: adjust OPL3 FM resource value
The OPTi ISA-PnP chips advertise their OPL4 base at 0x380 (to 0x3f0) through pnp and put their on-chip OPL3 at +8. The driver assumes the provided value is the ALBase (OPL3 address) though and checks for an OPL4 at -8, which means that simply adding 8 to the pnp provides value works to fix detection of both OPL3 and OPL4.
Problem spotted on 931 and 933 by Krzysztof Helt and confirmed on 924 and 925 (together all OPTi ISA-PnP chips) by me.
Signed-off-by; Rene Herman rene.herman@gmail.com ===
Rene.
diff --git a/sound/isa/opti9xx/opti92x-ad1848.c b/sound/isa/opti9xx/opti92x-ad1848.c index 60c120f..8bda47a 100644 --- a/sound/isa/opti9xx/opti92x-ad1848.c +++ b/sound/isa/opti9xx/opti92x-ad1848.c @@ -1732,11 +1732,11 @@ static int __devinit snd_card_opti9xx_pnp(struct snd_opti9xx *chip,
#ifdef OPTi93X port = pnp_port_start(pdev, 0) - 4; - fm_port = pnp_port_start(pdev, 1); + fm_port = pnp_port_start(pdev, 1) + 8; #else if (pid->driver_data != 0x0924) port = pnp_port_start(pdev, 1); - fm_port = pnp_port_start(pdev, 2); + fm_port = pnp_port_start(pdev, 2) + 8; #endif /* OPTi93X */ irq = pnp_irq(pdev, 0); dma1 = pnp_dma(pdev, 0);