On Thu, Nov 08, 2007 at 03:19:52PM -0500, Mark Lord wrote: > Jeff Garzik wrote: > >On Thu, Nov 08, 2007 at 02:52:26PM -0500, Mark Lord wrote: > >>Jeff Garzik wrote: > >>>.. > >>>2) This chip includes target mode support. Very nice, well done! > >>>I hope that standard AHCI eventually supports this nice feature! > >>.. > >> > >>Speaking of which. Do we have a strategy as to how to implement/support > >>the target side of target mode on controllers which can do it? > >> > >>The Marvell chips also have a target mode feature, and I'd like to add > >>support for it soon-ish, but it's now clear how you would like it plumbed > >>into libata. > >> > >>It's almost like a separate driver/subsystem, except that would be very > >>silly. > > > >I'm letting the SCSI folks do the heavy lifting, implementing SCSI > >target mode -- an effort already quite well along. > > > >We should be able to piggyback off of that work. > .. > > MMmm.. I wonder what the most common use case is for target mode? > > Everybody I've dealt with thus far uses it as a high-speed local comms > interface, > which would suggest that it might be done as a network interface (ethernet > emulation). > > But that would confusingly go across driver subsystems, > despite that this is how it actually is used. The low-level driver itself will just be a dumb DMA send/receive engine, with submit/completion APIs highly similar to the existing ones. Then you can easily provide a network interface interface (not a typo) on top of that. The biggest use case I've seen is in the embedded space, where you really are creating a SCSI (or ATA) target, that appears to the initiator/client to be a real SCSI-or-ATA device. There are certainly other uses: networking, creating a cheap SATA bus analyzer, creating a cheap SATA bridge, ... My main goal is to ensure that the low-level driver is as simple as possible, which permits upper layers to actually figure out what purposes it shall use. Modern SATA is just a DMA engine with PHY control anyway (just like networking), so we really just need to be sure to abstract away initiator-mode (aka host mode) specifics in drivers that support target mode. Jeff - To unsubscribe from this list: send the line "unsubscribe linux-ide" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
