Date: Wed, 26 Apr 2006 00:24:22 -0600 From: Scott Long <scottl@samsco.org> To: Matthew Jacob <mj@feral.com> Cc: src-committers@FreeBSD.org, jhb@FreeBSD.org, Bruce Evans <bde@zeta.org.au>, cvs-src@FreeBSD.org, cvs-all@FreeBSD.org, Warner Losh <imp@bsdimp.com> Subject: Re: cvs commit: src/sys/dev/bce if_bcereg.h Message-ID: <444F1216.5070303@samsco.org> In-Reply-To: <20060425230508.X66143@ns1.feral.com> References: <444E7750.206@samsco.org> <200604251540.00170.jhb@freebsd.org> <444E7BFE.4040800@samsco.org> <20060425.173236.74726638.imp@bsdimp.com> <444EB6A1.3060901@samsco.org> <20060426103623.M1847@epsplex.bde.org> <20060425223519.F65802@ns1.feral.com> <444F0923.8050508@samsco.org> <20060425224750.K65869@ns1.feral.com> <444F0D58.9020000@samsco.org> <20060425230508.X66143@ns1.feral.com>
next in thread | previous in thread | raw e-mail | index | archive | help
Matthew Jacob wrote: >> 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. > > > You could still have a device that you program with > 2^32 and it'll > take care of the segment issues. > >> So, I think that we are pretty safe with this typedef for >> the next 5-10 years. > > > Nope. I give it 3 years max. > >> Of course, I'll be honored when Linus calls me a >> moron for this 7 years from now =-) >> >> Scott >> >> Oh, I'm sure that you could contrive a silly device today to prove your point. But really, what are you going to do other than DMA completely randomly-associated memory pages that just happen to neighbor each other? It's not like the kernel or any user process can own more than 4GB of memory on i386+PAE. Scott
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?444F1216.5070303>