diff options
author | KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> | 2011-04-15 20:39:01 +0900 |
---|---|---|
committer | Ingo Molnar <mingo@elte.hu> | 2011-04-15 20:28:19 +0200 |
commit | 7d6b46707f2491a94f4bd3b4329d2d7f809e9368 (patch) | |
tree | e5a5085c170c1dd673788a9f48c96cf13102be93 /arch | |
parent | 9d90e49da57fe73a2f35334fdd2fb60dbf3933ed (diff) | |
download | op-kernel-dev-7d6b46707f2491a94f4bd3b4329d2d7f809e9368.zip op-kernel-dev-7d6b46707f2491a94f4bd3b4329d2d7f809e9368.tar.gz |
x86, NUMA: Fix fakenuma boot failure
Currently, numa=fake boot parameter is broken. If it's used,
kernel may panic due to devide by zero error depending on CPU
configuration
Call Trace:
[<ffffffff8104ad4c>] find_busiest_group+0x38c/0xd30
[<ffffffff81086aff>] ? local_clock+0x6f/0x80
[<ffffffff81050533>] load_balance+0xa3/0x600
[<ffffffff81050f53>] idle_balance+0xf3/0x180
[<ffffffff81550092>] schedule+0x722/0x7d0
[<ffffffff81550538>] ? wait_for_common+0x128/0x190
[<ffffffff81550a65>] schedule_timeout+0x265/0x320
[<ffffffff81095815>] ? lock_release_holdtime+0x35/0x1a0
[<ffffffff81550538>] ? wait_for_common+0x128/0x190
[<ffffffff8109bb6c>] ? __lock_release+0x9c/0x1d0
[<ffffffff815534e0>] ? _raw_spin_unlock_irq+0x30/0x40
[<ffffffff815534e0>] ? _raw_spin_unlock_irq+0x30/0x40
[<ffffffff81550540>] wait_for_common+0x130/0x190
[<ffffffff81051920>] ? try_to_wake_up+0x510/0x510
[<ffffffff8155067d>] wait_for_completion+0x1d/0x20
[<ffffffff8107f36c>] kthread_create_on_node+0xac/0x150
[<ffffffff81077bb0>] ? process_scheduled_works+0x40/0x40
[<ffffffff8155045f>] ? wait_for_common+0x4f/0x190
[<ffffffff8107a283>] __alloc_workqueue_key+0x1a3/0x590
[<ffffffff81e0cce2>] cpuset_init_smp+0x6b/0x7b
[<ffffffff81df3d07>] kernel_init+0xc3/0x182
[<ffffffff8155d5e4>] kernel_thread_helper+0x4/0x10
[<ffffffff81553cd4>] ? retint_restore_args+0x13/0x13
[<ffffffff81df3c44>] ? start_kernel+0x400/0x400
[<ffffffff8155d5e0>] ? gs_change+0x13/0x13
The divede by zero is caused by the following line,
group->cpu_power==0:
kernel/sched_fair.c::update_sg_lb_stats()
/* Adjust by relative CPU power of the group */
sgs->avg_load = (sgs->group_load * SCHED_LOAD_SCALE) / group->cpu_power;
This regression was caused by commit e23bba6044 ("x86-64, NUMA: Unify
emulated distance mapping") because it changes cpu -> node
mapping in the process of dropping fake_physnodes().
old) all cpus are assinged node 0
now) cpus are assigned round robin
(the logic is implemented by numa_init_array())
Note: The change in behavior only happens if the system doesn't
have neither ACPI SRAT table nor AMD northbridge NUMA
information.
Round robin assignment doesn't work because init_numa_sched_groups_power()
assumes all logical cpus in the same physical cpu share the same node
(then it only accounts for group_first_cpu()), and the simple round robin
breaks the above assumption.
Thus, this patch implements a reassignment of node-ids if buggy firmware
or numa emulation makes wrong cpu node map. Tt enforce all logical cpus
in the same physical cpu share the same node.
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: Tejun Heo <tj@kernel.org>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Shaohui Zheng <shaohui.zheng@intel.com>
Cc: David Rientjes <rientjes@google.com>
Cc: H. Peter Anvin <hpa@linux.intel.com>
Link: http://lkml.kernel.org/r/20110415203928.1303.A69D9226@jp.fujitsu.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'arch')
-rw-r--r-- | arch/x86/kernel/smpboot.c | 23 |
1 files changed, 23 insertions, 0 deletions
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index c2871d3..8ed8908 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -312,6 +312,26 @@ void __cpuinit smp_store_cpu_info(int id) identify_secondary_cpu(c); } +static void __cpuinit check_cpu_siblings_on_same_node(int cpu1, int cpu2) +{ + int node1 = early_cpu_to_node(cpu1); + int node2 = early_cpu_to_node(cpu2); + + /* + * Our CPU scheduler assumes all logical cpus in the same physical cpu + * share the same node. But, buggy ACPI or NUMA emulation might assign + * them to different node. Fix it. + */ + if (node1 != node2) { + pr_warning("CPU %d in node %d and CPU %d in node %d are in the same physical CPU. forcing same node %d\n", + cpu1, node1, cpu2, node2, node2); + + numa_remove_cpu(cpu1); + numa_set_node(cpu1, node2); + numa_add_cpu(cpu1); + } +} + static void __cpuinit link_thread_siblings(int cpu1, int cpu2) { cpumask_set_cpu(cpu1, cpu_sibling_mask(cpu2)); @@ -320,6 +340,7 @@ static void __cpuinit link_thread_siblings(int cpu1, int cpu2) cpumask_set_cpu(cpu2, cpu_core_mask(cpu1)); cpumask_set_cpu(cpu1, cpu_llc_shared_mask(cpu2)); cpumask_set_cpu(cpu2, cpu_llc_shared_mask(cpu1)); + check_cpu_siblings_on_same_node(cpu1, cpu2); } @@ -361,10 +382,12 @@ void __cpuinit set_cpu_sibling_map(int cpu) per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) { cpumask_set_cpu(i, cpu_llc_shared_mask(cpu)); cpumask_set_cpu(cpu, cpu_llc_shared_mask(i)); + check_cpu_siblings_on_same_node(cpu, i); } if (c->phys_proc_id == cpu_data(i).phys_proc_id) { cpumask_set_cpu(i, cpu_core_mask(cpu)); cpumask_set_cpu(cpu, cpu_core_mask(i)); + check_cpu_siblings_on_same_node(cpu, i); /* * Does this new cpu bringup a new core? */ |