I noted this /after /svn updating my 11.x box to the most-current -STABLE:

    A bug was diagnosed in interaction of the |pmap_activate()| function
    and TLB shootdownIPI handler on amd64 systems which
    have PCID features but do not implement theINVPCID instruction. On
    such machines, such as SandyBridge™ and IvyBridge™
    microarchitectures, set the loader
    tunable |vm.pmap.pcid_enabled=0| during boot:

    set vm.pmap.pcid_enabled=0

    Add this line to |/boot/loader.conf| for the change to persist
    across reboots:

    To check if the system is affected, check dmesg(8)
 for PCID listed
    in the "Features2", and absence of INVPCID in the "Structured
    Extended Features". If the PCID feature is not present,
    or INVPCID is present, system is not affected.

Well, I'm allegedly subject to this:

Copyright (c) 1992-2016 The FreeBSD Project.
Copyright (c) 1979, 1980, 1983, 1986, 1988, 1989, 1991, 1992, 1993, 1994
        The Regents of the University of California. All rights reserved.
FreeBSD is a registered trademark of The FreeBSD Foundation.
FreeBSD 11.0-STABLE #13 r307318M: Fri Oct 14 09:23:46 CDT 2016
    k...@newfs.denninger.net:/usr/obj/usr/src/sys/KSD-SMP amd64
FreeBSD clang version 3.8.0 (tags/RELEASE_380/final 262564) (based on
LLVM 3.8.0)
VT(vga): text 80x25
CPU: Intel(R) Xeon(R) CPU           E5620  @ 2.40GHz (2400.13-MHz
K8-class CPU)
  Origin="GenuineIntel"  Id=0x206c2  Family=0x6  Model=0x2c  Stepping=2
  AMD Features=0x2c100800<SYSCALL,NX,Page1GB,RDTSCP,LM>
  AMD Features2=0x1<LAHF>
  TSC: P-state invariant, performance statistics

And I do _*not*_ have it turned off at this moment.

vm.pmap.invpcid_works: 0
vm.pmap.pcid_enabled: 1

But.... I've also yet to see any sort of misbehavior.

So the questions are:

1. What's the misbehavior I should expect to see if this is not shut off
(and it isn't)?

2. Should I take this machine down immediately to reboot it with
vm.pmap.pcid_enabled=0 in /boot/loader.conf?

A svn log perusal didn't see anything post the errata date that appears
to be related.... which makes me wonder.

Thanks in advance!

Karl Denninger
k...@denninger.net <mailto:k...@denninger.net>
/The Market Ticker/
/[S/MIME encrypted email preferred]/

Attachment: smime.p7s
Description: S/MIME Cryptographic Signature

Reply via email to