print_backtrace not printing full stack

[Mike Mason]

Hmm... I didn't think about the user portion of the stack being missing. Perhaps open() isn't a good example.  I tried probing the entry to open()and printing the backtrace.  Saw the same results.  Then I tried a few other probe points, including schedule() in sched.c.  No matter where I probe, I only get one line of the stack.

Mike

Frank Ch. Eigler wrote:
> Mike Mason <mmlnx@us.ibm.com> writes:
> 
>> Is there some trick to getting print_backtrace to work?  The following
>> script:
>> probe syscall.open.return { [...]
>>                  print_backtrace();
>> I get one line from the stack and that's it. I assume I should see the
>> full stack.
> 
> If by "full stack" you mean to include the user-space program that
> performed open(2), then unfortunately we can't do that yet.  We also
> know that kretprobes did or does have problems with corrupting
> backtraces for even plain nested kernel-side probes.  To some extent,
> one might work around this by storing the backtrace at the point of
> syscall entry thusly:
> 
> global bt
> probe syscall.open { bt[tid()] = backtrace() }
> probe syscall.open.return { if (...) { print_stack (bt[tid()]) } 
>                             /* delete bt[tid()] */ }
> 
> - FChE