Messages in this thread Patch in this message | | | Date | Wed, 1 Apr 2009 19:42:58 -0400 (EDT) | From | Steven Rostedt <> | Subject | Re: [PATCH][GIT PULL] tracing/wakeup: move access to wakeup_cpu into spinlock |
| |
On Fri, 27 Mar 2009, Maneesh Soni wrote: > > Hi Steven, > > > > I still the oops with the patch, > > > > BUG: unable to handle kernel NULL pointer dereference at 0000000000000008 > > IP: [<ffffffff802d2259>] probe_wakeup_sched_switch+0xd2/0x1ac > > PGD 1d68e9067 PUD 1e6cdf067 PMD 0 > > Oops: 0000 [#1] SMP > > last sysfs file: /sys/devices/pci0000:0c/0000:0c:00.0/irq > > CPU 5 > > Modules linked in: autofs4 hidp rfcomm l2cap bluetooth iptable_filter ip_tables ip6t_REJECT xt_tcpudp ip6table_filter ip6_tables x_tables ipv6 dm_mirror dm_region_hash dm_log dm_multipath scsi_dh dm_mod sbs sbshc battery ac parport_pc lp parport sg sr_mod ide_cd_mod cdrom serio_raw acpi_memhotplug button tg3 libphy i2c_piix4 i2c_core pcspkr usb_storage uhci_hcd ohci_hcd ehci_hcd aacraid sd_mod scsi_mod ext3 jbd > > Pid: 6095, comm: cat Not tainted 2.6.29-tip-test #2 eserver xSeries 366-[88632RA]- > > RIP: 0010:[<ffffffff802d2259>] [<ffffffff802d2259>] probe_wakeup_sched_switch+0xd2/0x1ac > > RSP: 0000:ffff8801e6d03ea0 EFLAGS: 00010046 > > RAX: 0000000000000000 RBX: ffff8800281989a0 RCX: 0000000000000046 > > RDX: ffff8800281989a0 RSI: ffffffff8020d56d RDI: ffffffff811de480 > > RBP: ffff8801e6d03ed0 R08: 0000000000000000 R09: 0000000000000000 > > R10: 0000000000000000 R11: 0000000000000001 R12: 0000000000000046 > > R13: ffff88022f232820 R14: 0000000000000000 R15: 0000000000000005 > > FS: 00007f98b94cb6e0(0000) GS:ffff88002818b000(0000) knlGS:0000000000000000 > > CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b > > CR2: 0000000000000008 CR3: 0000000224595000 CR4: 00000000000006e0 > > DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 > > DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 > > Process cat (pid: 6095, threadinfo ffff8801e6d02000, task ffff8801d6935040) > > Stack: > > ffff8801d6935040 ffff880224981230 ffff88002819dd40 0000003b4ae00aa0 > > 00007fffc14df830 ffff88002819dd40 ffff8801e6d03f70 ffffffff806f8264 > > 0000000000000002 ffff8801e6d03f48 ffff8801d6935040 ffff88022f232820 > > Call Trace: > > [<ffffffff806f8264>] schedule+0xd99/0x10f9 > > [<ffffffff806fb61b>] ? trace_hardirqs_on_thunk+0x3a/0x3c > > [<ffffffff8027d2cb>] ? delayed_work_timer_fn+0x0/0x38 > > [<ffffffff8020d56d>] retint_careful+0x12/0x2e > > Code: 2d ad de f2 00 75 77 48 63 05 ac de f2 00 48 8b 4d 00 45 89 f0 48 8b 3d 8e de f2 00 48 8b 71 08 48 8b 5c c7 28 48 8b 01 4c 89 e1 <48> 8b 50 08 e8 f6 9f ff ff 48 8b 3d 6f de f2 00 48 8b 75 d0 45 > > RIP [<ffffffff802d2259>] probe_wakeup_sched_switch+0xd2/0x1ac > > RSP <ffff8801e6d03ea0> > > CR2: 0000000000000008 > >
> 0xffffffff802d2208 <probe_wakeup_sched_switch+129>: lock xadd %ax,0xf2debf(%rip) # 0xffffffff812000d0 <wakeup_lock> > 0xffffffff802d2211 <probe_wakeup_sched_switch+138>: cmp %ah,%al > 0xffffffff802d2213 <probe_wakeup_sched_switch+140>: je 0xffffffff802d221f <probe_wakeup_sched_switch+152> > 0xffffffff802d2215 <probe_wakeup_sched_switch+142>: pause > 0xffffffff802d2217 <probe_wakeup_sched_switch+144>: mov 0xf2deb3(%rip),%al # 0xffffffff812000d0 <wakeup_lock> > 0xffffffff802d221d <probe_wakeup_sched_switch+150>: jmp 0xffffffff802d2211 <probe_wakeup_sched_switch+138> > 0xffffffff802d221f <probe_wakeup_sched_switch+152>: cmpl $0x0,0x9fb02a(%rip) # 0xffffffff80ccd250 <tracer_enabled> > 0xffffffff802d2226 <probe_wakeup_sched_switch+159>: je 0xffffffff802d22ac <probe_wakeup_sched_switch+293> > 0xffffffff802d222c <probe_wakeup_sched_switch+165>: cmp 0xf2dead(%rip),%r13 # 0xffffffff812000e0 <wakeup_task> > 0xffffffff802d2233 <probe_wakeup_sched_switch+172>: jne 0xffffffff802d22ac <probe_wakeup_sched_switch+293> > 0xffffffff802d2235 <probe_wakeup_sched_switch+174>: movslq 0xf2deac(%rip),%rax # 0xffffffff812000e8 <wakeup_cpu> > 0xffffffff802d223c <probe_wakeup_sched_switch+181>: mov 0x0(%rbp),%rcx > 0xffffffff802d2240 <probe_wakeup_sched_switch+185>: mov %r14d,%r8d > 0xffffffff802d2243 <probe_wakeup_sched_switch+188>: mov 0xf2de8e(%rip),%rdi # 0xffffffff812000d8 <wakeup_trace> > 0xffffffff802d224a <probe_wakeup_sched_switch+195>: mov 0x8(%rcx),%rsi > 0xffffffff802d224e <probe_wakeup_sched_switch+199>: mov 0x28(%rdi,%rax,8),%rbx > 0xffffffff802d2253 <probe_wakeup_sched_switch+204>: mov (%rcx),%rax > 0xffffffff802d2256 <probe_wakeup_sched_switch+207>: mov %r12,%rcx > 0xffffffff802d2259 <probe_wakeup_sched_switch+210>: mov 0x8(%rax),%rdx <<<<<<<<<===================== Here. > 0xffffffff802d225d <probe_wakeup_sched_switch+214>: callq 0xffffffff802cc258 <trace_function> > 0xffffffff802d2262 <probe_wakeup_sched_switch+219>: mov 0xf2de6f(%rip),%rdi # 0xffffffff812000d8 <wakeup_trace> > 0xffffffff802d2269 <probe_wakeup_sched_switch+226>: mov -0x30(%rbp),%rsi > 0xffffffff802d226d <probe_wakeup_sched_switch+230>: mov %r14d,%r8d > 0xffffffff802d2270 <probe_wakeup_sched_switch+233>: mov %r13,%rdx > 0xffffffff802d2273 <probe_wakeup_sched_switch+236>: mov %r12,%rcx > 0xffffffff802d2276 <probe_wakeup_sched_switch+239>: callq 0xffffffff802cd5b---Type <return> to continue, or q <return> to quit--- > 2 <tracing_sched_switch_trace>
> It seems CALLER_ADDR is not correct?
Hi Maneesh,
Could you try this patch and see if it keeps your system from crashing?
Thanks,
-- Steve
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index a331ec3..dbf3f8f 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -917,10 +917,15 @@ retint_careful: TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) pushq %rdi - CFI_ADJUST_CFA_OFFSET 8 + pushq %rbp + call 1f +1: mov %rsp, %rbp + CFI_ADJUST_CFA_OFFSET 24 call schedule + addq $8, %rsp /* skip call */ + popq %rbp popq %rdi - CFI_ADJUST_CFA_OFFSET -8 + CFI_ADJUST_CFA_OFFSET -24 GET_THREAD_INFO(%rcx) DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF
| |