Date: Tue, 17 Apr 2018 10:24:11 -0500 From: Kyle Evans <kevans@freebsd.org> To: Dan Allen <danallen46@gmail.com> Cc: FreeBSD-STABLE Mailing List <freebsd-stable@freebsd.org> Subject: Re: amd64 kernel crash introduced between 20180329 & 20180408 Message-ID: <CACNAnaGEHmFY2DyndNECkd7%2BmFHeNgF81mKkg5yZBehb935O-A@mail.gmail.com> In-Reply-To: <4EE33A98-C010-4D79-A502-19D009384B0D@gmail.com> References: <B8E3D49E-60B1-41FD-A40F-5B0E856483CC@gmail.com> <CACNAnaGV%2B6htEnZaxdVJuqetwd=cbu4xhd1XF2RFZNwAMLG5XA@mail.gmail.com> <4EE33A98-C010-4D79-A502-19D009384B0D@gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Tue, Apr 17, 2018 at 10:18 AM, Dan Allen <danallen46@gmail.com> wrote: > > >> On 17 Apr 2018, at 8:49 AM, Kyle Evans <kevans@freebsd.org> wrote: >> >> As "the guy most likely to have broken boot code in stable," may I ask >> what leads you specifically to amd64 boot code? Mostly curious if >> there's something beyond "i386 works well" that lead you to this >> conclusion. > > It is partly just a hunch. > > I installed 11.0 for use with qemu a while ago. I did binary upgrades for patches using > freebsd-update. When 11.1 came out, it would not work correctly, again with the same > kind of behavior. Then, I got some later snapshots that worked again, notably the 20180329 > build. When the next snapshot came out, things broke. I also tried my own builds, same story. > > I even got both source trees together - 20180329 and 20180408 - and did a diff on the entire > trees, and I noticed activity in the boot & kernel code. It could just as likely be something in the > kernel as well, but none of this happens with the i386 build. > >> When you say it crashes and does a kernel dump- you're landing at a >> ddb prompt, yeah? What does executing bt at that prompt look like? > > No, I am not ever given a prompt. I get to watch a mini-dump happen and then an automatic > reboot. It is a kernel panic. Here is what I see: > Ahh, fun. =) I'm inclined to think it's probably not a boot code problem, but it is suspicious. Can you set vm.pmap.pti=0 at the loader prompt and see if this affects your situation at all, just to rule that out?
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CACNAnaGEHmFY2DyndNECkd7%2BmFHeNgF81mKkg5yZBehb935O-A>