cvs commit: src/sys/dev/bce if_bcereg.h

Scott Long scottl at
Wed Apr 26 06:04:22 UTC 2006

Matthew Jacob wrote:
>>> I'm afraid I don't understand the 'unreasonable' argument here. Linux 
>>> is eating your lunch today. Do you want it to eat your dessert as well?
>>> -matt
>> bus_size_t is used for things like measuring transfer segment size. 
>> There is little chance that Linux, Windows, FreeBSD, or any other OS
>> is ever going to try to DMA more than 2^32 bytes of data in a single
>> bus transaction.  Maybe you could contrive a silly infiniband device
>> to do it.  Anyways, it has no bearing on whether the CPU, memory
>> controller, or PCI buses can do 64 bit addressing.
> Oh, sorry, yes, I agree it's *unlikely* that anything will DMA more than 
> 2^32 bytes at a time right now. I'm really really tired and lost lock. 
> Sorry.

And actually, it's 100% impossible to do a transfer larger than 2^32 on
PCI Express due to the protocol requiring that a transfer not cross a
4GB boundary.  So, I think that we are pretty safe with this typedef for
the next 5-10 years.  Of course, I'll be honored when Linus calls me a
moron for this 7 years from now =-)


More information about the cvs-src mailing list