Bug 4307 - execution of current.stp in systemtap-20070331 snapshot causes system to freeze on ppc64.
Summary: execution of current.stp in systemtap-20070331 snapshot causes system to free...
Status: RESOLVED WORKSFORME
Alias: None
Product: systemtap
Classification: Unclassified
Component: runtime (show other bugs)
Version: unspecified
: P2 normal
Target Milestone: ---
Assignee: Unassigned
URL:
Keywords:
Depends on:
Blocks:
 
Reported: 2007-04-02 10:20 UTC by Srinivasa DS
Modified: 2010-02-26 01:51 UTC (History)
1 user (show)

See Also:
Host:
Target:
Build:
Last reconfirmed:

Attachments
Add an attachment (proposed patch, testcase, etc.)

Note You need to log in before you can comment on or make changes to this bug.
Description Srinivasa DS 2007-04-02 10:20:19 UTC 
I have this environment systemtap-20070331 snapshot,kernel-2.6.21-rc3,
elfutils-0.125 arch=ppc64.

But execution of current.stp in systemtap-20070331 snapshot is giving spinlock
lockup and softlockup bug. And system is getting freezed.
======================================================
UG: spinlock lockup on CPU#0, sshd/2380, c0000000007da608
Call Trace:
[C0000000076134C0] [C00000000000FAB0] .show_stack+0x68/0x1b0 (unreliable)
[C000000007613560] [C0000000001AF9E8] ._raw_spin_lock+0x140/0x17c
[C000000007613600] [C00000000036B40C] ._spin_lock+0x10/0x24
[C000000007613680] [C00000000006066C] .task_rq_lock+0x68/0xcc
[C000000007613720] [C00000000002B71C] .kretprobe_trampoline_holder+0x0/0x8
[C000000007613810] [C00000000002B71C] .kretprobe_trampoline_holder+0x0/0x8
[C0000000076138C0] [C00000000002B71C] .kretprobe_trampoline_holder+0x0/0x8
[C000000007613970] [C00000000002B71C] .kretprobe_trampoline_holder+0x0/0x8
[C000000007613AC0] [C000000000201358] .pty_write+0x74/0x90
[C000000007613B40] [C0000000001FE05C] .write_chan+0x378/0x448
[C000000007613C20] [C0000000001F9EA0] .tty_write+0x1a0/0x278
[C000000007613CF0] [C0000000000E6938] .vfs_write+0x120/0x1f0
[C000000007613D90] [C0000000000E7368] .sys_write+0x4c/0x8c
[C000000007613E30] [C0000000000086B4] syscall_exit+0x0/0x40
BUG: spinlock lockup on CPU#6, klogd/1887, c0000000007da608
Call Trace:
[C00000000FD173F0] [C00000000000FAB0] .show_stack+0x68/0x1b0 (unreliable)
[C00000000FD17490] [C0000000001AF9E8] ._raw_spin_lock+0x140/0x17c
[C00000000FD17530] [C00000000036B40C] ._spin_lock+0x10/0x24
[C00000000FD175B0] [C00000000006066C] .task_rq_lock+0x68/0xcc
[C00000000FD17650] [C00000000002B71C] .kretprobe_trampoline_holder+0x0/0x8
[C00000000FD17740] [C00000000002B71C] .kretprobe_trampoline_holder+0x0/0x8
[C00000000FD177F0] [C00000000002B71C] .kretprobe_trampoline_holder+0x0/0x8
[C00000000FD178A0] [C00000000002B71C] .kretprobe_trampoline_holder+0x0/0x8
[C00000000FD17930] [C00000000035CF80] .unix_dgram_sendmsg+0x524/0x638
[C00000000FD17A30] [C0000000002C9CE4] .sock_aio_write+0x164/0x19c
[C00000000FD17B60] [C0000000000E5FF0] .do_sync_write+0xc4/0x124
[C00000000FD17CF0] [C0000000000E6954] .vfs_write+0x13c/0x1f0
[C00000000FD17D90] [C0000000000E7368] .sys_write+0x4c/0x8c
[C00000000FD17E30] [C0000000000086B4] syscall_exit+0x0/0x40
=============================================================

But What I observed is, previous week systemtap is not giving any problem at all.
Could the recent transport changes be the reason for this?
Comment 1 Frank Ch. Eigler 2007-04-02 17:06:53 UTC 
This is probably a sideeffect of the inline->function changes committed last week.
That is, the script now includes inline functions where it used not to.  Chances
are that both this test script as well as the probing blacklist need to be changed.
Comment 2 Frank Ch. Eigler 2007-04-02 21:12:44 UTC 
Another data point: I see this kind of crash (with tracebacks showing
kretprobe_trampoline) on several platforms, but only with very recent
kernels.  Contrary to your apparent experience, it does not go away with
a slightly older systemtap snapshot.  It is as if something has changed
for the worse in recent kernels.
Comment 3 Frank Ch. Eigler 2010-02-26 01:51:46 UTC 
no recent similar reports on ppc