From 85b97637bb40a9f486459dd254598759af9c3d50 Mon Sep 17 00:00:00 2001 From: Tang Chen Date: Mon, 29 Oct 2012 11:01:50 +0800 Subject: x86/mce: Do not change worker's running cpu in cmci_rediscover(). cmci_rediscover() used set_cpus_allowed_ptr() to change the current process's running cpu, and migrate itself to the dest cpu. But worker processes are not allowed to be migrated. If current is a worker, the worker will be migrated to another cpu, but the corresponding worker_pool is still on the original cpu. In this case, the following BUG_ON in try_to_wake_up_local() will be triggered: BUG_ON(rq != this_rq()); This will cause the kernel panic. The call trace is like the following: [ 6155.451107] ------------[ cut here ]------------ [ 6155.452019] kernel BUG at kernel/sched/core.c:1654! ...... [ 6155.452019] RIP: 0010:[] [] try_to_wake_up_local+0x115/0x130 ...... [ 6155.452019] Call Trace: [ 6155.452019] [] __schedule+0x764/0x880 [ 6155.452019] [] schedule+0x29/0x70 [ 6155.452019] [] schedule_timeout+0x235/0x2d0 [ 6155.452019] [] ? mark_held_locks+0x8d/0x140 [ 6155.452019] [] ? __lock_release+0x133/0x1a0 [ 6155.452019] [] ? _raw_spin_unlock_irq+0x30/0x50 [ 6155.452019] [] ? trace_hardirqs_on_caller+0x105/0x190 [ 6155.452019] [] wait_for_common+0x12b/0x180 [ 6155.452019] [] ? try_to_wake_up+0x2f0/0x2f0 [ 6155.452019] [] wait_for_completion+0x1d/0x20 [ 6155.452019] [] stop_one_cpu+0x8a/0xc0 [ 6155.452019] [] ? __migrate_task+0x1a0/0x1a0 [ 6155.452019] [] ? complete+0x28/0x60 [ 6155.452019] [] set_cpus_allowed_ptr+0x128/0x130 [ 6155.452019] [] cmci_rediscover+0xf5/0x140 [ 6155.452019] [] mce_cpu_callback+0x18d/0x19d [ 6155.452019] [] notifier_call_chain+0x67/0x150 [ 6155.452019] [] __raw_notifier_call_chain+0xe/0x10 [ 6155.452019] [] __cpu_notify+0x20/0x40 [ 6155.452019] [] cpu_notify_nofail+0x15/0x30 [ 6155.452019] [] _cpu_down+0x262/0x2e0 [ 6155.452019] [] cpu_down+0x36/0x50 [ 6155.452019] [] acpi_processor_remove+0x50/0x11e [ 6155.452019] [] acpi_device_remove+0x90/0xb2 [ 6155.452019] [] __device_release_driver+0x7c/0xf0 [ 6155.452019] [] device_release_driver+0x2f/0x50 [ 6155.452019] [] acpi_bus_remove+0x32/0x6d [ 6155.452019] [] acpi_bus_trim+0x87/0xee [ 6155.452019] [] acpi_bus_hot_remove_device+0x88/0x16b [ 6155.452019] [] acpi_os_execute_deferred+0x27/0x34 [ 6155.452019] [] process_one_work+0x219/0x680 [ 6155.452019] [] ? process_one_work+0x1b8/0x680 [ 6155.452019] [] ? acpi_os_wait_events_complete+0x23/0x23 [ 6155.452019] [] worker_thread+0x12e/0x320 [ 6155.452019] [] ? manage_workers+0x110/0x110 [ 6155.452019] [] kthread+0xc6/0xd0 [ 6155.452019] [] kernel_thread_helper+0x4/0x10 [ 6155.452019] [] ? retint_restore_args+0x13/0x13 [ 6155.452019] [] ? __init_kthread_worker+0x70/0x70 [ 6155.452019] [] ? gs_change+0x13/0x13 This patch removes the set_cpus_allowed_ptr() call, and put the cmci rediscover jobs onto all the other cpus using system_wq. This could bring some delay for the jobs. Signed-off-by: Tang Chen Signed-off-by: Miao Xie Signed-off-by: Tony Luck --- arch/x86/kernel/cpu/mcheck/mce_intel.c | 31 ++++++++++++++++++------------- 1 file changed, 18 insertions(+), 13 deletions(-) diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index 5f88abf..4f9a3cb 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -285,34 +285,39 @@ void cmci_clear(void) raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); } +static long cmci_rediscover_work_func(void *arg) +{ + int banks; + + /* Recheck banks in case CPUs don't all have the same */ + if (cmci_supported(&banks)) + cmci_discover(banks); + + return 0; +} + /* * After a CPU went down cycle through all the others and rediscover * Must run in process context. */ void cmci_rediscover(int dying) { - int banks; - int cpu; - cpumask_var_t old; + int cpu, banks; if (!cmci_supported(&banks)) return; - if (!alloc_cpumask_var(&old, GFP_KERNEL)) - return; - cpumask_copy(old, ¤t->cpus_allowed); for_each_online_cpu(cpu) { if (cpu == dying) continue; - if (set_cpus_allowed_ptr(current, cpumask_of(cpu))) + + if (cpu == smp_processor_id()) { + cmci_rediscover_work_func(NULL); continue; - /* Recheck banks in case CPUs don't all have the same */ - if (cmci_supported(&banks)) - cmci_discover(banks); - } + } - set_cpus_allowed_ptr(current, old); - free_cpumask_var(old); + work_on_cpu(cpu, cmci_rediscover_work_func, NULL); + } } /* -- cgit v1.1