Hi, With 2.6.31.6-rt19, I have an application which reliably triggers a system freeze on a dual-processor system. Prior to the lockup, there's this spam in logs: Dec 29 14:48:07 Ubuntu kernel: [ 346.332026] BUG: using smp_processor_id() in preemptible [00000000] code: SmartTool/4191 Dec 29 14:48:07 Ubuntu kernel: [ 346.332205] caller is __schedule+0x13/0xa70 Dec 29 14:48:07 Ubuntu kernel: [ 346.332210] Pid: 4191, comm: SmartTool Not tainted 2.6.31.6-rt19-ceng1 #1 Dec 29 14:48:07 Ubuntu kernel: [ 346.332214] Call Trace: Dec 29 14:48:07 Ubuntu kernel: [ 346.332224] [<c031dd09>] debug_smp_processor_id+0xb9/0xd0 Dec 29 14:48:07 Ubuntu kernel: [ 346.332229] [<c0568583>] __schedule+0x13/0xa70 Dec 29 14:48:07 Ubuntu kernel: [ 346.332236] [<c014c984>] ? irq_exit+0x54/0x90 Dec 29 14:48:07 Ubuntu kernel: [ 346.332243] [<c011d486>] ? smp_apic_timer_interrupt+0x56/0x90 Dec 29 14:48:07 Ubuntu kernel: [ 346.332249] [<c010332a>] work_resched+0x5/0x19 Dec 29 14:48:07 Ubuntu kernel: [ 346.332256] BUG: using smp_processor_id() in preemptible [00000000] code: SmartTool/4191 Dec 29 14:48:07 Ubuntu kernel: [ 346.332425] caller is __schedule+0x6a/0xa70 Dec 29 14:48:07 Ubuntu kernel: [ 346.332429] Pid: 4191, comm: SmartTool Not tainted 2.6.31.6-rt19-ceng1 #1 Dec 29 14:48:07 Ubuntu kernel: [ 346.332432] Call Trace: Dec 29 14:48:07 Ubuntu kernel: [ 346.332437] [<c031dd09>] debug_smp_processor_id+0xb9/0xd0 Dec 29 14:48:07 Ubuntu kernel: [ 346.332443] [<c05685da>] __schedule+0x6a/0xa70 Dec 29 14:48:07 Ubuntu kernel: [ 346.332449] [<c014c984>] ? irq_exit+0x54/0x90 Dec 29 14:48:07 Ubuntu kernel: [ 346.332454] [<c011d486>] ? smp_apic_timer_interrupt+0x56/0x90 Dec 29 14:48:07 Ubuntu kernel: [ 346.332460] [<c010332a>] work_resched+0x5/0x19 Dec 29 14:48:09 Ubuntu kernel: [ 349.658309] __ratelimit: 2 callbacks suppressed These two traces repeat constantly in the logs - I suppose the crash occurred when a migration eventually occurred in the middle of this. The processes running are polling several usb-serial devices. This does not occur with 2.6.29.6-rt24, or with SMP disabled (including after disabling a CPU at runtime). I'll try to get some ftrace results; in the meantime, any ideas? Kernel log, lspci, lsmod, and config at http://fushizen.net/~bd/rt-oops.tar.gz Thanks, Bryan Donlan -- To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
