memory alignment problems with -current on amd64? [Found Cause]
atkin901 at yahoo.com
Thu Feb 12 09:16:36 PST 2009
Alan Cox wrote:
> Do you know why NX is disabled on this processor? If possible, could you
> re-enable it and vm.pmap.pg_ps_enabled, and see if you still have the same
I'm not sure why it's off, but I re-enabled it in BIOS with the same result
(still resets or gives a bus error).
For the processor, I can't seem to find anything that gives the revision.
Is the Id and stepping good enough?
Ports misc/cpuid seems to give the same information that's in the verbose
Still can't get the buildworld bus error to dump core for me. I inserted
a 'ulimit -a' command into some targets in Makefile.inc and it shows
unlimited for the Make environment.
However, I note that it doesn't say (core dumped) when the error occurs.
example, my latest failure:
peigen.c: In function '_bfd_pei_only_swap_filehdr_out':
peigen.c:2089: internal compiler error: Bus error: 10
Please submit a full bug report,
with preprocessed source if appropriate.
With an deliberately induced bus error, a program will dump core.
> On Wed, Feb 11, 2009 at 5:26 PM, Mark Atkinson <atkin901 at yahoo.com> wrote:
>> Alan Cox wrote:
>> > On Tue, Feb 10, 2009 at 2:20 PM, Mark Atkinson <atkin901 at yahoo.com>
>> > [snip]
>> >> Well, taking the information I knew -- OCT 15th == good, Mid DEC ==
>> >> BAD,
>> >> I trolled every commit logged between. Eventually I found this one:
>> >> http://svn.freebsd.org/viewvc/base?view=revision&revision=185715
>> >> http://docs.freebsd.org/cgi/mid.cgi?200812061937.mB6JbqAI003273
>> >> I set vm.pmap.pg_ps_enabled="0" in /boot/loader.conf, and
>> >> was able to complete buildworld and -j16 buildworld and -j8
>> >> buildkernel no problem.
>> >> It appears superpage mapping causes alignment problems on this box.
>> > Can you please provide more detailed information about this machine, in
>> > particular, the processor including the revision? It would also be
>> > helpful to see what gdb says about a couple of these crashes,
>> > specifically, the machine registers at the time of the exception.
>> Is there something specifically preventing cores during buildworld? I
>> find one after a bus error. I'll try to find something to dump the
>> revision for me. Here's the verbose boot for the processor.
>> CPU: Quad-Core AMD Opteron(tm) Processor 2352 (2100.09-MHz K8-class CPU)
>> Origin = "AuthenticAMD" Id = 0x100f23 Stepping = 3
>> AMD Features=0xee400800<SYSCALL,MMX+,FFXSR,Page1GB,RDTSCP,LM,3DNow
>> TSC: P-state invariant
>> Cores per package: 4
>> L1 2MB data TLB: 48 entries, fully associative
>> L1 2MB instruction TLB: 16 entries, fully associative
>> L1 4KB data TLB: 48 entries, fully associative
>> L1 4KB instruction TLB: 32 entries, fully associative
>> L1 data cache: 64 kbytes, 64 bytes/line, 1 lines/tag, 2-way associative
>> L1 instruction cache: 64 kbytes, 64 bytes/line, 1 lines/tag, 2-way
>> L2 2MB data TLB: 128 entries, 2-way associative
>> L2 2MB instruction TLB: 0 entries, 2-way associative
>> L2 4KB data TLB: 512 entries, 4-way associative
>> L2 4KB instruction TLB: 512 entries, 4-way associative
>> L2 unified cache: 512 kbytes, 64 bytes/line, 1 lines/tag, 16-way
>> usable memory = 10720198656 (10223 MB)
>> Physical memory chunk(s):
>> 0x0000000000001000 - 0x000000000009bfff, 634880 bytes (155 pages)
>> 0x0000000000f55000 - 0x00000000cfe4dfff, 3471806464 bytes (847609 pages)
>> 0x00000000cfe56000 - 0x00000000cfe56fff, 4096 bytes (1 pages)
>> 0x0000000100000000 - 0x000000029d212fff, 6931165184 bytes (1692179 pages)
>> Mark Atkinson
>> atkin901 at yahoo.com
>> freebsd-current at freebsd.org mailing list
>> To unsubscribe, send any mail to
>> "freebsd-current-unsubscribe at freebsd.org"
> freebsd-current at freebsd.org mailing list
> To unsubscribe, send any mail to "freebsd-current-unsubscribe at freebsd.org"
atkin901 at yahoo.com
More information about the freebsd-current