So, this worked a while back.  I think.

Anyone seen this?  I also had similar quirks on a totally unrelated system
with a totally unrelated drive controller, but also using a CF card.  Which
makes me suspect software, especially given that this machine was booting
maybe a month ago.

geodeide0 at pci0 dev 18 function 2
geodeide0: AMD Geode SC1100 IDE controller (rev. 0x01)
geodeide0: bus-master DMA support present
geodeide0: primary channel wired to compatibility mode
geodeide0: primary channel interrupting at irq 14
atabus0 at geodeide0 channel 0
geodeide0: secondary channel wired to compatibility mode
geodeide0: secondary channel interrupting at irq 15
atabus1 at geodeide0 channel 1
wd0 at atabus0 drive 0: <SanDisk SDCFB-512>
wd0: drive supports 1-sector PIO transfers, LBA addressing
wd0: 488 MB, 993 cyl, 16 head, 63 sec, 512 bytes/sect x 1000944 sectors
wd0: 32-bit data port
wd0: drive supports PIO mode 4, DMA mode 2
wd0(geodeide0:0:0): using PIO mode 4, DMA mode 2 (using DMA data transfers)
geodeide0:0: lost interrupt
        type: ata tc_bcount: 512 tc_skip: 0
geodeide0:0:0: bus-master DMA error: missing interrupt, status=0x21
wd0d: DMA error reading fsbn 0 (wd0 bn 0; cn 0 tn 0 sn 0), retrying
geodeide0:0: lost interrupt
        type: ata tc_bcount: 512 tc_skip: 0
geodeide0:0:0: bus-master DMA error: missing interrupt, status=0x1
wd0d: DMA error reading fsbn 0 (wd0 bn 0; cn 0 tn 0 sn 0), retrying
geodeide0:0: lost interrupt
        type: ata tc_bcount: 512 tc_skip: 0