On Tue, 31 Jan 2006 11:19:12 +0900
MASUDA Hideo <h-masuda@ootani.nagata.kobe.jp> wrote:

> Hi all,
> 
>  I got the M/B with nForce430 ATA133/SATAII chip.
>  Under NetBSD/i386 3.0, HDD access is very poor performance.
> According to dmesg, HDD is recognized as DMA mode-2 (DMA33).
> 
> viaide0 at pci0 dev 13 function 0
> viaide0: NVIDIA nForce430 IDE Controller (rev. 0xa1)
> viaide0: bus-master DMA support present
> viaide0: primary channel configured to compatibility mode
> viaide0: primary channel interrupting at ioapic0 pin 14 (irq 14)
> atabus0 at viaide0 channel 0
> viaide0: secondary channel configured to compatibility mode
> viaide0: secondary channel interrupting at ioapic0 pin 15 (irq 15)
> atabus1 at viaide0 channel 1
> 	(snip)
> wd0 at atabus0 drive 0: <HDT722525DLAT80>
> wd0: drive supports 16-sector PIO transfers, LBA48 addressing
> wd0: 232 GB, 484521 cyl, 16 head, 63 sec, 512 bytes/sect x 488397168
> sectors wd0: 32-bit data port
> wd0: drive supports PIO mode 4, DMA mode 2, Ultra-DMA mode 6
> (Ultra/133) wd0(viaide0:0:0): using PIO mode 4, DMA mode 2 (using DMA)
> wd1 at atabus1 drive 0: <ST3250823A>
> wd1: drive supports 16-sector PIO transfers, LBA48 addressing
> wd1: 232 GB, 484521 cyl, 16 head, 63 sec, 512 bytes/sect x 488397168
> sectors wd1: 32-bit data port
> wd1: drive supports PIO mode 4, DMA mode 2, Ultra-DMA mode 5
> (Ultra/100) wd1(viaide0:1:0): using PIO mode 4, DMA mode 2 (using DMA)
> 
>  I think that this causes the quirks (?) in dev/pci/viaide.c, and
> apply the patch (this may be applied for current (rev. 1.27))
> as following:
> 
> Index: viaide.c
> ===================================================================
> RCS file: /cvs/cvsroot/src/sys/dev/pci/viaide.c,v
> retrieving revision 1.24.2.1
> diff -u -r1.24.2.1 viaide.c
> --- viaide.c    5 Jan 2006 22:17:39 -0000       1.24.2.1
> +++ viaide.c    31 Jan 2006 02:09:24 -0000
> @@ -340,6 +340,9 @@
>                 case PCI_PRODUCT_NVIDIA_NFORCE3_ATA133:
>                 case PCI_PRODUCT_NVIDIA_NFORCE3_250_ATA133:
>                 case PCI_PRODUCT_NVIDIA_NFORCE4_ATA133:
> +               case PCI_PRODUCT_NVIDIA_NFORCE430_ATA133:
> +               case PCI_PRODUCT_NVIDIA_NFORCE430_SATA1:
> +               case PCI_PRODUCT_NVIDIA_NFORCE430_SATA2:
>                         sc->sc_wdcdev.sc_atac.atac_udma_cap = 6;
>                         break;
>                 }

Thanks for your patch. I think you don't need to match the
SATA controllers here, because they will be set to UDMA-6 in
the via_sata_chip_map() function. 

The ATA controllers will exec the via_chip_map() function, so you
only need to match against PCI_PRODUCT_NVIDIA_NFORCE430_ATA133.

Please correct me if I'm wrong.

Best regards.