Hi,
I patched out the lock instruction via hexedit and the segfaults are gone!
before:
= 507b: f0 0f b1 8b 94 21 00lock cmpxchg %ecx,0x2194(%ebx)
after:
507b: 90 nop
507c: 0f b1 8b 94 21 00 00cmpxchg %ecx,0x2194(%ebx)
Might be a bug in
Intel knows about this, see the errata (page 15):
http://downloadmirror.intel.com/23197/eng/Quark_SW_RelNotes_330232_001.pdf
With kind regards
Thomas
--
To UNSUBSCRIBE, email to debian-bugs-dist-requ...@lists.debian.org
with a subject of unsubscribe. Trouble? Contact
On Wed, Mar 12, 2014 at 04:33:45PM +0100, Thomas Karmann wrote:
Intel knows about this, see the errata (page 15):
http://downloadmirror.intel.com/23197/eng/Quark_SW_RelNotes_330232_001.pdf
Thanks for digging on this issue, that indeed explains a lot.
It's probably something we can fix in glibc
On Wed, Mar 12, 2014 at 03:31:57PM +0100, Thomas Karmann wrote:
Hi,
I patched out the lock instruction via hexedit and the segfaults are gone!
before:
= 507b: f0 0f b1 8b 94 21 00lock cmpxchg %ecx,0x2194(%ebx)
after:
507b: 90 nop
507c:
On 12.03.2014 (21:20), Aurelien Jarno wrote:
While it shows that the problem is at the CPU level, it's not really a
fix, as the bus is not locked anymore, so it might results in issues in
multithreaded solution.
The correct solution would be to apply the solution from Intel, that is
adding
On Wed, Mar 12, 2014 at 10:07:43PM +0100, Thomas Karmann wrote:
On 12.03.2014 (21:20), Aurelien Jarno wrote:
While it shows that the problem is at the CPU level, it's not really a
fix, as the bus is not locked anymore, so it might results in issues in
multithreaded solution.
The
On Sun, 2 Mar 2014, Aurelien Jarno wrote:
The test would be to run one of the affected program under gdb, add a
breakpoint on __nptl_setxid, and understand why the memory access fail.
With gdb attached, the crash does not happen. I've got some more things
to try though.
On Fri, Feb 28, 2014 at 10:43:07AM -0500, Stuart Anderson wrote:
I have access to a couple of these boards. I'll be glad to run some tests if
needed.
The test would be to run one of the affected program under gdb, add a
breakpoint on __nptl_setxid, and understand why the memory access
I have access to a couple of these boards. I'll be glad to run some tests if
needed.
Stuart
Stuart R. Anderson ander...@netsweng.com
Network Software Engineering http://www.netsweng.com/
1024D/37A79149:
9 matches
Mail list logo