Bug#738575: Access to a Galileo board

2014-03-12 Thread Thomas Karmann
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

Bug#738575: Access to a Galileo board

2014-03-12 Thread Thomas Karmann
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

Bug#738575: Access to a Galileo board

2014-03-12 Thread Aurelien Jarno
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

Bug#738575: Access to a Galileo board

2014-03-12 Thread Aurelien Jarno
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:

Bug#738575: Access to a Galileo board

2014-03-12 Thread Thomas Karmann
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

Bug#738575: Access to a Galileo board

2014-03-12 Thread Aurelien Jarno
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

Bug#738575: Access to a Galileo board

2014-03-04 Thread Stuart Anderson
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.

Bug#738575: Access to a Galileo board

2014-03-01 Thread Aurelien Jarno
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

Bug#738575: Access to a Galileo board

2014-02-28 Thread Stuart Anderson
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: