Not so much a bug report as getting a known issue logged somewhere more visible than just the code itself. Basically, this driver doesn't support LBA48, and for safety disables drives attached to it that require LBA48.
The manufacturer has currently got Linux drivers posted, but I'm not sure what the status of them is ( http://www.initio.com/drivers/Linux.SATA.drvr.2.6.15.zip ) I've not got easy access to incremental versions of the source to see if they've simply zipped up the then-current version (they are almost certainly based upon the kernel sources), or have actually put some effort into updating it themselves, but as the version has been upped to 0.5, and the current kernel source is 0.3, I suspect they may have actually done something, even if only that. It still contains a comment about LBA48 though, but doesn't contain Tejun Heo's disabling patch. Whether this is because they've fixed the issue or simply grabbed before he added it, I cannot say.
Working on it. ADMA mode is now working for ATA DMA commands but the vendor driver is a bit less mature than I would have liked and it's pretty unreliable now. Let's see how it goes...
As always, it turned out to be much more work than I expected but it's working now. http://article.gmane.org/gmane.linux.ide/31136 You can also pull from the following git tree. http://git.kernel.org/?p=linux/kernel/git/tj/libata-dev.git;a=shortlog;h=inic162x git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata-dev.git inic162x Resolving as CODE_FIX. Thanks.