libunwind-devel
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Libunwind-devel] Unwinding from optimzied shared library on linux


From: Scott Biersdorff
Subject: [Libunwind-devel] Unwinding from optimzied shared library on linux
Date: Thu, 4 Sep 2014 00:12:50 +0000

Hi,

 

I am attempting to unwind from an optimized shared (non-stripped) library compiled with debugging information. However I cannot unwind pass the second entry on the call stack. Ideally I would like to unwind all the way back to main and I understand libunwind has techniques it uses when and if the frame pointers/dwarf information is unavailable and I want to make sure that I’m using libunwind in such a way that gives it is the best possibility to use these techniques. Here are some details:

 

Linux x86_64

Libunwind version 1.1

Library name: libsatlas.so

Leaf Symobol name:  ATL_spKBmm (after this location unw_step() returns 0)

 

Actual stack (from gdb):

 

#0  0x00007ffff7851e00 in ATL_spKBmm () from /usr/local/atlas/lib/libsatlas.so

#1  0x00007ffff7917830 in ATL_smmJIK2 () from /usr/local/atlas/lib/libsatlas.so

#2  0x00007ffff79187ad in ATL_smmJIK () from /usr/local/atlas/lib/libsatlas.so

#3  0x00007ffff790fb7b in ATL_sgemm () from /usr/local/atlas/lib/libsatlas.so

#4  0x00007ffff769a831 in atl_f77wrap_sgemm_ () from /usr/local/atlas/lib/libsatlas.so

#5  0x00007ffff7699a64 in sgemm_ () from /usr/local/atlas/lib/libsatlas.so

#6  0x00000000004008e5 in fa () at sgemm_port.f90:39

#7  0x000000000040091d in MAIN__ () at sgemm_port.f90:59

 

I’ve also attached debugging information from libunwind. This is the information printed at the last attempt to unwind:

 

>_Ux86_64_step: (cursor=0x7fff8ec56d10, ip=0x00007f321ed00a1d, cfa=0x00007fff8ec57728)

>_Ux86_64_step: [RBP=0x7fff8ec571f8] = 0x4620 (cfa = 0x7fff8ec57728) -> 0x0

  >_Ux86_64_step: NULL %rbp loc, returning 0

 

Thanks for any insight.

 

-          Scott

Attachment: libunwind-debug.txt
Description: libunwind-debug.txt


reply via email to

[Prev in Thread] Current Thread [Next in Thread]