[PATCH] sched: fix llc shared map unreleased during cpu hotplug

[PATCH] sched: fix llc shared map unreleased during cpu hotplug

[Wanpeng Li]

[  220.262093] BUG: unable to handle kernel NULL pointer dereference at 0000000000000004
[  220.262104] IP: [<ffffffff810e7ac9>] find_busiest_group+0x2b9/0xa30
[  220.262111] PGD 5a9d5067 PUD 13067 PMD 0
[  220.262117] Oops: 0000 [#3] SMP
[...]
[  220.262245] Call Trace:
[  220.262252]  [<ffffffff810e8396>] load_balance+0x156/0x980
[  220.262259]  [<ffffffff816eeffe>] ? _raw_spin_unlock_irqrestore+0x2e/0xa0
[  220.262266]  [<ffffffff810e9aa3>] idle_balance+0xe3/0x150
[  220.262270]  [<ffffffff816ec4e7>] __schedule+0x797/0x8d0
[  220.262277]  [<ffffffff816ec934>] schedule+0x24/0x70
[  220.262283]  [<ffffffff816e9cd9>] schedule_timeout+0x119/0x1f0
[  220.262294]  [<ffffffff810bb6e0>] ? lock_timer_base+0x70/0x70
[  220.262301]  [<ffffffff816e9dc9>] schedule_timeout_uninterruptible+0x19/0x20
[  220.262308]  [<ffffffff810bd3e8>] msleep+0x18/0x20
[  220.262317]  [<ffffffff813aa11a>] lock_device_hotplug_sysfs+0x2a/0x50
[  220.262323]  [<ffffffff813aa16e>] online_store+0x2e/0x80
[  220.262358]  [<ffffffff813a873b>] dev_attr_store+0x1b/0x20
[  220.262366]  [<ffffffff812292fd>] sysfs_write_file+0xdd/0x160
[  220.262377]  [<ffffffff811b7e78>] vfs_write+0xc8/0x170
[  220.262384]  [<ffffffff811b83ca>] SyS_write+0x5a/0xa0
[  220.262388]  [<ffffffff816f76b9>] system_call_fastpath+0x16/0x1b

Last level cache shared map is built during cpu up and build sched domain 
routine takes advantage of it to setup sched domain cpu topology, however, 
llc shared map is unreleased during cpu disable which lead to invalid sched 
domain cpu topology. This patch fix it by release llc shared map correctly
during cpu disable.

Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
---
 arch/x86/kernel/smpboot.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 5492798..0134ec7 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1292,6 +1292,9 @@ static void remove_siblinginfo(int cpu)
 
 	for_each_cpu(sibling, cpu_sibling_mask(cpu))
 		cpumask_clear_cpu(cpu, cpu_sibling_mask(sibling));
+	for_each_cpu(sibling, cpu_llc_shared_mask(cpu))
+		cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling));
+	cpumask_clear(cpu_llc_shared_mask(cpu));
 	cpumask_clear(cpu_sibling_mask(cpu));
 	cpumask_clear(cpu_core_mask(cpu));
 	c->phys_proc_id = 0;
-- 
1.9.1

Re: [PATCH] sched: fix llc shared map unreleased during cpu hotplug

[Peter Zijlstra]

On Tue, Jul 22, 2014 at 03:16:31PM +0800, Wanpeng Li wrote:
> [  220.262093] BUG: unable to handle kernel NULL pointer dereference at 0000000000000004
> [  220.262104] IP: [<ffffffff810e7ac9>] find_busiest_group+0x2b9/0xa30
> [  220.262111] PGD 5a9d5067 PUD 13067 PMD 0
> [  220.262117] Oops: 0000 [#3] SMP
> [...]
> [  220.262245] Call Trace:
> [  220.262252]  [<ffffffff810e8396>] load_balance+0x156/0x980
> [  220.262259]  [<ffffffff816eeffe>] ? _raw_spin_unlock_irqrestore+0x2e/0xa0
> [  220.262266]  [<ffffffff810e9aa3>] idle_balance+0xe3/0x150
> [  220.262270]  [<ffffffff816ec4e7>] __schedule+0x797/0x8d0
> [  220.262277]  [<ffffffff816ec934>] schedule+0x24/0x70
> [  220.262283]  [<ffffffff816e9cd9>] schedule_timeout+0x119/0x1f0
> [  220.262294]  [<ffffffff810bb6e0>] ? lock_timer_base+0x70/0x70
> [  220.262301]  [<ffffffff816e9dc9>] schedule_timeout_uninterruptible+0x19/0x20
> [  220.262308]  [<ffffffff810bd3e8>] msleep+0x18/0x20
> [  220.262317]  [<ffffffff813aa11a>] lock_device_hotplug_sysfs+0x2a/0x50
> [  220.262323]  [<ffffffff813aa16e>] online_store+0x2e/0x80
> [  220.262358]  [<ffffffff813a873b>] dev_attr_store+0x1b/0x20
> [  220.262366]  [<ffffffff812292fd>] sysfs_write_file+0xdd/0x160
> [  220.262377]  [<ffffffff811b7e78>] vfs_write+0xc8/0x170
> [  220.262384]  [<ffffffff811b83ca>] SyS_write+0x5a/0xa0
> [  220.262388]  [<ffffffff816f76b9>] system_call_fastpath+0x16/0x1b
> 
> Last level cache shared map is built during cpu up and build sched domain 
> routine takes advantage of it to setup sched domain cpu topology, however, 
> llc shared map is unreleased during cpu disable which lead to invalid sched 
> domain cpu topology. This patch fix it by release llc shared map correctly
> during cpu disable.
> 
> Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
> ---
>  arch/x86/kernel/smpboot.c | 3 +++
>  1 file changed, 3 insertions(+)

While the scheduler uses this information, the code you're patching is
very much not scheduler code, therefore your subject line is entirely
wrong.