Re: [PATCH][GIT PULL] tracing: Fix compile issue for trace_sched_wakeup.c

[Ingo Molnar <mingo@elte.hu>]

* Ingo Molnar <mingo@elte.hu> wrote:

> and here's a new crash with a new config:
> 
> [   11.810471] Testing event timer_expire_exit: OK
> [   11.850475] Testing event timer_cancel: OK
> [   11.890508] Testing event hrtimer_init: OK
> [   11.930469] Testing event hrtimer_start: OK
> [   11.970475] Testing event hrtimer_expire_entry: 
> [   11.980002] BUG: unable to handle kernel NULL pointer dereference at (null)
> [   11.980010] IP: [<(null)>] (null)
> [   11.980010] *pde = 00000000 
> [   11.980010] Oops: 0000 [#1] SMP 
> [   11.980010] last sysfs file: 
> [   11.980010] Modules linked in:
> [   11.980010] 
> [   11.980010] Pid: 0, comm: swapper Not tainted 2.6.36-tip-05833-g9db2fad-dirty #52316 A8N-E/System Product Name
> [   11.980010] EIP: 0060:[<00000000>] EFLAGS: 00010046 CPU: 0
> [   11.980010] EIP is at 0x0
> [   11.980010] EAX: f6806a94 EBX: f6806a94 ECX: 00010000 EDX: 00000096
> [   11.980010] ESI: f65bdf50 EDI: f6806a00 EBP: f6806a30 ESP: c13dff04
> [   11.980010]  DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068
> [   11.980010] Process swapper (pid: 0, ti=c13de000 task=c13e2f20 task.ti=c13de000)
> [   11.980010] Stack:
> [   11.980010]  c103d297 00000000 c10460c1 c13dff4c ca105369 00000002 ffffffff 7fffffff
> [   11.980010]  c103d52b ca105369 00000002 ca105369 0000002c f6806a00 00000000 f6806a04
> [   11.980010]  ca105369 00000002 ca105369 00000002 00000000 f6805dac 00000000 c1420788
> [   11.980010] Call Trace:
> [   11.980010]  [<c103d297>] ? __run_hrtimer+0x91/0x105
> [   11.980010]  [<c10460c1>] ? tick_sched_timer+0x0/0x1a1
> [   11.980010]  [<c103d52b>] ? hrtimer_interrupt+0x108/0x20a
> [   11.980010]  [<c1012294>] ? smp_apic_timer_interrupt+0x66/0x75
> [   11.980010]  [<c12c202a>] ? apic_timer_interrupt+0x36/0x3c
> [   11.980010]  [<c10163f0>] ? native_safe_halt+0x2/0x3
> [   11.980010]  [<c10072c6>] ? default_idle+0x66/0x91
> [   11.980010]  [<c10020f6>] ? cpu_idle+0x98/0xda
> [   11.980010]  [<c142280a>] ? start_kernel+0x2f7/0x2fc
> [   11.980010] Code:  Bad EIP value.
> [   11.980010] EIP: [<00000000>] 0x0 SS:ESP 0068:c13dff04
> [   11.980010] CR2: 0000000000000000
> [   11.980010] ---[ end trace 74b10a949febd52e ]---
> [   11.980011] BUG: unable to handle kernel NULL pointer dereference at (null)
> [   11.980011] IP: [<(null)>] (null)
> [   11.980011] *pde = 00000000 
> [   11.980011] Oops: 0000 [#2] SMP 
> [   11.980011] last sysfs file: 
> [   11.980011] Modules linked in:
> [   11.980011] 
> [   11.980011] Pid: 0, comm: kworker/0:0 Tainted: G      D     2.6.36-tip-05833-g9db2fad-dirty #52316 A8N-E/System Product Name
> [   11.980011] EIP: 0060:[<00000000>] EFLAGS: 00010046 CPU: 1
> [   11.980011] EIP is at 0x0
> [   11.980011] EAX: f6a06a94 EBX: f6a06a94 ECX: 00010000 EDX: 00000092
> [   11.980011] ESI: f65bdf50 EDI: f6a06a00 EBP: f6a06a30 ESP: f6479ec0
> [   11.980011]  DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068
> [   11.980011] Process kworker/0:0 (pid: 0, ti=f6478000 task=f64364e0 task.ti=f6478000)
> [   11.980011] Stack:
> [   11.980011]  c103d297 00000000 c10460c1 f6479f08 ca1058de 00000002 ffffffff 7fffffff
> [   11.980011]  c103d52b ca1058de 00000002 ca1058de 0000002c f6a06a00 00000000 f6a06a04
> [   11.980011]  ca1058de 00000002 ca1058de 00000002 00000000 f6a05dac 00000001 c1420788
> [   11.980011] Call Trace:
> [   11.980011]  [<c103d297>] ? __run_hrtimer+0x91/0x105
> [   11.980011]  [<c10460c1>] ? tick_sched_timer+0x0/0x1a1
> [   11.980011]  [<c103d52b>] ? hrtimer_interrupt+0x108/0x20a
> [   11.980011]  [<c1012294>] ? smp_apic_timer_interrupt+0x66/0x75
> [   11.980011]  [<c12c202a>] ? apic_timer_interrupt+0x36/0x3c
> [   11.980011]  [<c10163f0>] ? native_safe_halt+0x2/0x3
> [   11.980011]  [<c10072c6>] ? default_idle+0x66/0x91
> [   11.980011]  [<c10020f6>] ? cpu_idle+0x98/0xda
> [   11.980011]  [<c14501ce>] ? start_secondary+0x200/0x205
> [   11.980011] Code:  Bad EIP value.
> [   11.980011] EIP: [<00000000>] 0x0 SS:ESP 0068:f6479ec0
> [   11.980011] CR2: 0000000000000000
> [   11.980011] ---[ end trace 74b10a949febd52f ]---
> [   11.980011] Kernel panic - not syncing: Fatal exception in interrupt
> [   11.980011] Pid: 0, comm: kworker/0:0 Tainted: G      D     2.6.36-tip-05833-g9db2fad-dirty #52316
> [   11.980011] Call Trace:
> [   11.980011]  [<c12bfaa3>] ? panic+0x4d/0x13a
> [   11.980011]  [<c12c2b31>] ? oops_end+0x72/0x7c
> [   11.980011]  [<c1017475>] ? no_context+0x10d/0x117
> [   11.980011]  [<c12c42d7>] ? do_page_fault+0x0/0x37c
> [   11.980011]  [<c1017591>] ? bad_area_nosemaphore+0xa/0xc
> [   11.980011]  [<c12c44a4>] ? do_page_fault+0x1cd/0x37c
> [   11.980011]  [<c105a808>] ? rb_reserve_next_event+0x289/0x336
> [   11.980011]  [<c113ea0c>] ? trace_hardirqs_off_thunk+0xc/0x10
> [   11.980011]  [<c12c42d7>] ? do_page_fault+0x0/0x37c
> [   11.980011]  [<c12c42d7>] ? do_page_fault+0x0/0x37c
> [   11.980011]  [<c12c21ec>] ? error_code+0x6c/0x74
> [   11.980011]  [<c103d297>] ? __run_hrtimer+0x91/0x105
> [   11.980011]  [<c10460c1>] ? tick_sched_timer+0x0/0x1a1
> [   11.980011]  [<c103d52b>] ? hrtimer_interrupt+0x108/0x20a
> [   11.980011]  [<c1012294>] ? smp_apic_timer_interrupt+0x66/0x75
> [   11.980011]  [<c12c202a>] ? apic_timer_interrupt+0x36/0x3c
> [   11.980011]  [<c10163f0>] ? native_safe_halt+0x2/0x3
> [   11.980011]  [<c10072c6>] ? default_idle+0x66/0x91
> [   11.980011]  [<c10020f6>] ? cpu_idle+0x98/0xda
> [   11.980011]  [<c14501ce>] ? start_secondary+0x200/0x205
> [   11.980010] Kernel panic - not syncing: Fatal exception in interrupt
> [   11.980010] Pid: 0, comm: swapper Tainted: G      D     2.6.36-tip-05833-g9db2fad-dirty #52316
> [   11.980010] Call Trace:
> [   11.980010]  [<c12bfaa3>] ? panic+0x4d/0x13a
> [   11.980010]  [<c12c2b31>] ? oops_end+0x72/0x7c
> [   11.980010]  [<c1017475>] ? no_context+0x10d/0x117
> [   11.980010]  [<c12c42d7>] ? do_page_fault+0x0/0x37c
> [   11.980010]  [<c1017591>] ? bad_area_nosemaphore+0xa/0xc
> [   11.980010]  [<c12c44a4>] ? do_page_fault+0x1cd/0x37c
> [   11.980010]  [<c105a808>] ? rb_reserve_next_event+0x289/0x336
> [   11.980010]  [<c113ea0c>] ? trace_hardirqs_off_thunk+0xc/0x10
> [   11.980010]  [<c12c42d7>] ? do_page_fault+0x0/0x37c
> [   11.980010]  [<c12c42d7>] ? do_page_fault+0x0/0x37c
> [   11.980010]  [<c12c21ec>] ? error_code+0x6c/0x74
> [   11.980010]  [<c103d297>] ? __run_hrtimer+0x91/0x105
> [   11.980010]  [<c10460c1>] ? tick_sched_timer+0x0/0x1a1
> [   11.980010]  [<c103d52b>] ? hrtimer_interrupt+0x108/0x20a
> [   11.980010]  [<c1012294>] ? smp_apic_timer_interrupt+0x66/0x75
> [   11.980010]  [<c12c202a>] ? apic_timer_interrupt+0x36/0x3c
> [   11.980010]  [<c10163f0>] ? native_safe_halt+0x2/0x3
> [   11.980010]  [<c10072c6>] ? default_idle+0x66/0x91
> [   11.980010]  [<c10020f6>] ? cpu_idle+0x98/0xda
> [   11.980010]  [<c142280a>] ? start_kernel+0x2f7/0x2fc

Here's the disassembly of the crash site:

c103d282:       89 da                   mov    %ebx,%edx
c103d284:       8b 4c 24 04             mov    0x4(%esp),%ecx
c103d288:       ff 16                   call   *(%esi)
c103d28a:       83 c6 08                add    $0x8,%esi
c103d28d:       83 3e 00                cmpl   $0x0,(%esi)
c103d290:       eb eb                   jmp    c103d27d <__run_hrtimer+0x77>
c103d292:       89 d8                   mov    %ebx,%eax
c103d294:       ff 14 24                call   *(%esp)
c103d297:       89 04 24                mov    %eax,(%esp)
c103d29a:       e9 00 00 00 00          jmp    c103d29f <__run_hrtimer+0x99>
c103d29f:       eb 19                   jmp    c103d2ba <__run_hrtimer+0xb4>
c103d2a1:       8b 35 50 f1 40 c1       mov    0xc140f150,%esi
c103d2a7:       85 f6                   test   %esi,%esi
c103d2a9:       74 0f                   je     c103d2ba <__run_hrtimer+0xb4>
c103d2ab:       8b 46 04                mov    0x4(%esi),%eax
c103d2ae:       89 da                   mov    %ebx,%edx
c103d2b0:       ff 16                   call   *(%esi)
c103d2b2:       83 c6 08                add    $0x8,%esi
c103d2b5:       83 3e 00                cmpl   $0x0,(%esi)
c103d2b8:       eb ef                   jmp    c103d2a9 <__run_hrtimer+0xa3>
c103d2ba:       89 f8                   mov    %edi,%eax
c103d2bc:       e8 ea 43 28 00          call   c12c16ab <_raw_spin_lock>
c103d2c1:       83 3c 24 00             cmpl   $0x0,(%esp)

(gdb) list *0xc103d297
0xc103d297 is in __run_hrtimer (kernel/hrtimer.c:1227).
1222		 * they get migrated to another cpu, therefore its safe to unlock
1223		 * the timer base.
1224		 */
1225		raw_spin_unlock(&cpu_base->lock);
1226		trace_hrtimer_expire_entry(timer, now);
1227		restart = fn(timer);
1228		trace_hrtimer_expire_exit(timer);
1229		raw_spin_lock(&cpu_base->lock);
1230	
1231		/*
(gdb) list *0xc103d294
0xc103d294 is in __run_hrtimer (kernel/hrtimer.c:1227).
1222		 * they get migrated to another cpu, therefore its safe to unlock
1223		 * the timer base.
1224		 */
1225		raw_spin_unlock(&cpu_base->lock);
1226		trace_hrtimer_expire_entry(timer, now);
1227		restart = fn(timer);
1228		trace_hrtimer_expire_exit(timer);
1229		raw_spin_lock(&cpu_base->lock);
1230	
1231		/*

i.e. the 'fn(timer)' call crashed.

Thanks,

	Ingo