Date: Mon, 4 Feb 2008 09:02:56 -0700 From: John E Hein <jhein@timing.com> To: John Baldwin <jhb@freebsd.org> Cc: cvs-src@freebsd.org, Scott Long <scottl@samsco.org>, src-committers@freebsd.org, cvs-all@freebsd.org, grehan@freebsd.org Subject: Re: cvs commit: src/sys/dev/pci pci.c Message-ID: <18343.14128.272002.870082@gromit.timing.com> In-Reply-To: <200802040944.43812.jhb@freebsd.org> References: <200802012031.m11KV9NZ095246@repoman.freebsd.org> <47A3DCC1.2030700@freebsd.org> <18342.42877.245961.707684@gromit.timing.com> <200802040944.43812.jhb@freebsd.org>
next in thread | previous in thread | raw e-mail | index | archive | help
John Baldwin wrote at 09:44 -0500 on Feb 4, 2008: > We can blacklist those bridges just like we blacklist the AMD HT8131 bridge > which is broken. That's okay with me. We might use a PCIe switch to split an x16 lane (used normally for PEG) into two x8 lanes (used for our own nefarious purposes including MSI for sure). These should all pass PCIe-deviceness through the switch to a root complex (in all the targets we've looked at using), however, and so should be unaffected by your new PCIe detection, regardless of blacklisting a PCI or PCI-X to PCIe bridge.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?18343.14128.272002.870082>