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:[<ffffffff810add15>] [<ffffffff810add15>] try_to_wake_up_local+0x115/0x130 ...... [ 6155.452019] Call Trace: [ 6155.452019] [<ffffffff8166fc14>] __schedule+0x764/0x880 [ 6155.452019] [<ffffffff81670059>] schedule+0x29/0x70 [ 6155.452019] [<ffffffff8166de65>] schedule_timeout+0x235/0x2d0 [ 6155.452019] [<ffffffff810db57d>] ? mark_held_locks+0x8d/0x140 [ 6155.452019] [<ffffffff810dd463>] ? __lock_release+0x133/0x1a0 [ 6155.452019] [<ffffffff81671c50>] ? _raw_spin_unlock_irq+0x30/0x50 [ 6155.452019] [<ffffffff810db8f5>] ? trace_hardirqs_on_caller+0x105/0x190 [ 6155.452019] [<ffffffff8166fefb>] wait_for_common+0x12b/0x180 [ 6155.452019] [<ffffffff810b0b30>] ? try_to_wake_up+0x2f0/0x2f0 [ 6155.452019] [<ffffffff8167002d>] wait_for_completion+0x1d/0x20 [ 6155.452019] [<ffffffff8110008a>] stop_one_cpu+0x8a/0xc0 [ 6155.452019] [<ffffffff810abd40>] ? __migrate_task+0x1a0/0x1a0 [ 6155.452019] [<ffffffff810a6ab8>] ? complete+0x28/0x60 [ 6155.452019] [<ffffffff810b0fd8>] set_cpus_allowed_ptr+0x128/0x130 [ 6155.452019] [<ffffffff81036785>] cmci_rediscover+0xf5/0x140 [ 6155.452019] [<ffffffff816643c0>] mce_cpu_callback+0x18d/0x19d [ 6155.452019] [<ffffffff81676187>] notifier_call_chain+0x67/0x150 [ 6155.452019] [<ffffffff810a03de>] __raw_notifier_call_chain+0xe/0x10 [ 6155.452019] [<ffffffff81070470>] __cpu_notify+0x20/0x40 [ 6155.452019] [<ffffffff810704a5>] cpu_notify_nofail+0x15/0x30 [ 6155.452019] [<ffffffff81655182>] _cpu_down+0x262/0x2e0 [ 6155.452019] [<ffffffff81655236>] cpu_down+0x36/0x50 [ 6155.452019] [<ffffffff813d3eaa>] acpi_processor_remove+0x50/0x11e [ 6155.452019] [<ffffffff813a6978>] acpi_device_remove+0x90/0xb2 [ 6155.452019] [<ffffffff8143cbec>] __device_release_driver+0x7c/0xf0 [ 6155.452019] [<ffffffff8143cd6f>] device_release_driver+0x2f/0x50 [ 6155.452019] [<ffffffff813a7870>] acpi_bus_remove+0x32/0x6d [ 6155.452019] [<ffffffff813a7932>] acpi_bus_trim+0x87/0xee [ 6155.452019] [<ffffffff813a7a21>] acpi_bus_hot_remove_device+0x88/0x16b [ 6155.452019] [<ffffffff813a33ee>] acpi_os_execute_deferred+0x27/0x34 [ 6155.452019] [<ffffffff81090589>] process_one_work+0x219/0x680 [ 6155.452019] [<ffffffff81090528>] ? process_one_work+0x1b8/0x680 [ 6155.452019] [<ffffffff813a33c7>] ? acpi_os_wait_events_complete+0x23/0x23 [ 6155.452019] [<ffffffff810923be>] worker_thread+0x12e/0x320 [ 6155.452019] [<ffffffff81092290>] ? manage_workers+0x110/0x110 [ 6155.452019] [<ffffffff81098396>] kthread+0xc6/0xd0 [ 6155.452019] [<ffffffff8167c4c4>] kernel_thread_helper+0x4/0x10 [ 6155.452019] [<ffffffff81671f30>] ? retint_restore_args+0x13/0x13 [ 6155.452019] [<ffffffff810982d0>] ? __init_kthread_worker+0x70/0x70 [ 6155.452019] [<ffffffff8167c4c0>] ? 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 <tangchen@cn.fujitsu.com> Signed-off-by: Miao Xie <miaox@cn.fujitsu.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
This commit is contained in:
parent
8f0d8163b5
commit
85b97637bb
|
@ -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)))
|
||||
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);
|
||||
if (cpu == smp_processor_id()) {
|
||||
cmci_rediscover_work_func(NULL);
|
||||
continue;
|
||||
}
|
||||
|
||||
work_on_cpu(cpu, cmci_rediscover_work_func, NULL);
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
|
|
Loading…
Reference in New Issue