further pthread foo

[Andy Wingo]

Hello again!

Continuing on the same topic as my previous mail, which you may read
here:

  http://thread.gmane.org/gmane.lisp.guile.bugs/5340

I modified the program to do a `scm_init_guile ()' before creating any
threads.  This initializes libgc from the main thread, so all should be
well.  But then I run into a problem:

    (gdb) r
    Starting program: /tmp/many_threads 
    [Thread debugging using libthread_db enabled]
    0: create[New Thread 0x7ffff740b700 (LWP 23030)]
     join
    Program received signal SIGSEGV, Segmentation fault.
    [Switching to Thread 0x7ffff740b700 (LWP 23030)]
    0x00007ffff7a09200 in GC_malloc (bytes=16) at thread_local_alloc.c:161
    161     GC_FAST_MALLOC_GRANS(result, granules, tiny_fl, DIRECT_GRANULES,
    (gdb) thr apply all bt
    Thread 2 (Thread 0x7ffff740b700 (LWP 23030)):
    #0  0x00007ffff7a09200 in GC_malloc (bytes=16) at thread_local_alloc.c:161
    #1  0x00007ffff7d1208e in scm_cell (x=<value optimized out>, y=<value 
optimized out>) at ../libguile/inline.h:124
    #2  scm_cons (x=<value optimized out>, y=<value optimized out>) at 
pairs.c:77
    #3  0x00007ffff7cd05b7 in scm_i_with_continuation_barrier 
(body=0x7ffff7cd03a0 <c_body>, body_data=0x7ffff740adb0, 
        handler=0x7ffff7cd03c0 <c_handler>, handler_data=0x7ffff740adb0, 
pre_unwind_handler=<value optimized out>, 
        pre_unwind_handler_data=<value optimized out>) at continuations.c:444
    #4  0x00007ffff7cd0690 in scm_c_with_continuation_barrier (func=<value 
optimized out>, data=<value optimized out>)
        at continuations.c:491
    #5  0x00007ffff7a0982f in GC_call_with_gc_active (fn=0x7ffff7d48740 
<with_guile_trampoline>, client_data=0x7ffff740ae20)
        at pthread_support.c:1127
    #6  0x00007ffff7d48aed in with_gc_active (func=0x7ffff7d488e0 
<do_thread_exit>, data=0x949600, parent=<value optimized out>)
        at threads.c:97
    #7  scm_i_with_guile_and_parent (func=0x7ffff7d488e0 <do_thread_exit>, 
data=0x949600, parent=<value optimized out>)
        at threads.c:826
    #8  0x00007ffff7d48bc7 in do_thread_exit_trampoline (sb=<value optimized 
out>, v=0x949600) at threads.c:549
    #9  0x00007ffff7a03525 in GC_call_with_stack_base (fn=<value optimized 
out>, arg=<value optimized out>) at misc.c:1493
    #10 0x00007ffff7d48867 in on_thread_exit (v=0x949600) at threads.c:580
    #11 0x0000003fc86077f9 in __nptl_deallocate_tsd (arg=0x7ffff740b700) at 
pthread_create.c:154
    #12 start_thread (arg=0x7ffff740b700) at pthread_create.c:308
    #13 0x0000003fc7ee098d in clone () at 
../sysdeps/unix/sysv/linux/x86_64/clone.S:115

    Thread 1 (Thread 0x7ffff76ce700 (LWP 23027)):
    #0  0x0000003fc8607fbd in pthread_join (threadid=140737341601536, 
thread_return=0x7fffffffe018) at pthread_join.c:89
    #1  0x00007ffff7a09e47 in GC_pthread_join (thread=140737341601536, 
retval=0x7fffffffe018) at pthread_support.c:1219
    #2  0x00000000004008e7 in main () at many_threads.c:31

What is happening is that I have registered a pthread_key cleanup
handler, and I need to call a Guile function in that handler.  But quite
possibly, libgc has already torn down this thread.  So I trampoline
through a GC_call_with_stack_base, then register the current thread.  If
that returns GC_SUCCESS, later I unregister it.  In between there is the
scm_i_with_guile_and_parent call you see at frame #7.

However as you see, there is unhappiness there.  I don't know what
exactly is causing the segfault, but here's a disassembly:

    (gdb) disassemble $pc
    Dump of assembler code for function GC_malloc:
       0x00007ffff7a09180 <+0>: mov    %rbx,-0x30(%rsp)
       0x00007ffff7a09185 <+5>: mov    %r13,-0x18(%rsp)
       0x00007ffff7a0918a <+10>:        mov    %rdi,%rbx
       0x00007ffff7a0918d <+13>:        mov    %rbp,-0x28(%rsp)
       0x00007ffff7a09192 <+18>:        mov    %r12,-0x20(%rsp)
       0x00007ffff7a09197 <+23>:        mov    %r14,-0x10(%rsp)
       0x00007ffff7a0919c <+28>:        mov    %r15,-0x8(%rsp)
       0x00007ffff7a091a1 <+33>:        sub    $0x48,%rsp
       0x00007ffff7a091a5 <+37>:        mov    0x20a104(%rip),%rax        # 
0x7ffff7c132b0
       0x00007ffff7a091ac <+44>:        mov    (%rax),%r12d
       0x00007ffff7a091af <+47>:        data32 lea 0x20a3e9(%rip),%rdi        # 
0x7ffff7c135a0
       0x00007ffff7a091b7 <+55>:        data32 data32 callq 0x7ffff79f6da0 
<address@hidden>
       0x00007ffff7a091bf <+63>:        mov    (%rax),%r13
       0x00007ffff7a091c2 <+66>:        test   %r13,%r13
       0x00007ffff7a091c5 <+69>:        je     0x7ffff7a0923f <GC_malloc+191>
       0x00007ffff7a091c7 <+71>:        add    $0xf,%r12d
       0x00007ffff7a091cb <+75>:        movslq %r12d,%r12
       0x00007ffff7a091ce <+78>:        lea    (%rbx,%r12,1),%r12
       0x00007ffff7a091d2 <+82>:        shr    $0x4,%r12
       0x00007ffff7a091d6 <+86>:        cmp    $0x18,%r12
       0x00007ffff7a091da <+90>:        ja     0x7ffff7a0923f <GC_malloc+191>
       0x00007ffff7a091dc <+92>:        lea    0x18(%r12),%r14
       0x00007ffff7a091e1 <+97>:        mov    %r12,%rbp
       0x00007ffff7a091e4 <+100>:       mov    $0x10,%r15d
       0x00007ffff7a091ea <+106>:       shl    $0x4,%rbp
       0x00007ffff7a091ee <+110>:       mov    0x8(%r13,%r14,8),%rax
       0x00007ffff7a091f3 <+115>:       lea    0x8(%r13,%r14,8),%rcx
       0x00007ffff7a091f8 <+120>:       cmp    $0x11a,%rax
       0x00007ffff7a091fe <+126>:       jbe    0x7ffff7a09269 <GC_malloc+233>
    => 0x00007ffff7a09200 <+128>:       mov    (%rax),%rdx
       0x00007ffff7a09203 <+131>:       mov    %rdx,0x8(%r13,%r14,8)
       0x00007ffff7a09208 <+136>:       prefetcht0 (%rdx)
       0x00007ffff7a0920b <+139>:       movq   $0x0,(%rax)
       0x00007ffff7a09212 <+146>:       mov    0x18(%rsp),%rbx
       0x00007ffff7a09217 <+151>:       mov    0x20(%rsp),%rbp
       0x00007ffff7a0921c <+156>:       mov    0x28(%rsp),%r12
       0x00007ffff7a09221 <+161>:       mov    0x30(%rsp),%r13
       0x00007ffff7a09226 <+166>:       mov    0x38(%rsp),%r14
       0x00007ffff7a0922b <+171>:       mov    0x40(%rsp),%r15
       0x00007ffff7a09230 <+176>:       add    $0x48,%rsp
       0x00007ffff7a09234 <+180>:       retq   

    (gdb) info registers
    rax            0x1000       4096
    rbx            0x10 16
    rcx            0x6b1650     7018064
    rdx            0x2  2
    rsi            0x0  0
    rdi            0x6027e0     6301664
    rbp            0x10 0x10
    rsp            0x7ffff740acc0       0x7ffff740acc0
    r8             0x7ffff7d490b0       140737351291056
    r9             0x0  0
    r10            0x7ffff740aba0       140737341598624
    r11            0x7ffff7a097c0       140737347884992
    r12            0x1  1
    r13            0x6b1580     7017856
    r14            0x19 25
    r15            0x10 16
    rip            0x7ffff7a09200       0x7ffff7a09200 <GC_malloc+128>
    eflags         0x10212      [ AF IF RF ]
    cs             0x33 51
    ss             0x2b 43
    ds             0x0  0
    es             0x0  0
    fs             0x0  0
    gs             0x0  0

This is with current CVS.

Regards,

Andy
-- 
http://wingolog.org/