lkml.org 
[lkml]   [2011]   [Jun]   [10]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
SubjectRe: BUG on 3.0-rc on commit d72bce0e67e8afc6eb959f656013cbb577426f1e
From
Date
On Fri, 2011-06-10 at 16:11 +0200, Peter Zijlstra wrote:
> On Fri, 2011-06-10 at 08:17 -0500, Andrew Theurer wrote:
> > Looks like commit d72bce0e67e8afc6eb959f656013cbb577426f1e breaks my
> > boot:
> >
> > BUG: unable to handle kernel NULL pointer dereference at
> > 0000000000000004
> > IP: [<ffffffff8104e8b1>] find_lowest_rq+0xa1/0x150
> > PGD 0
> > Oops: 0000 [#1] SMP
> > CPU 0
> > Modules linked in:
> >
> > Pid: 1, comm: swapper Not tainted 3.0.0-rc1-00001-gd72bce0 #32 IBM
> > -[7145AC1]-/Node 1, Processor Card
> > RIP: 0010:[<ffffffff8104e8b1>] [<ffffffff8104e8b1>] find_lowest_rq
> > +0xa1/0x150
> > RSP: 0018:ffff883732925ca0 EFLAGS: 00010002
> > RAX: 0000000000000020 RBX: 0000000000000020 RCX: 0000000000000050
> > RDX: 00000000ffffffff RSI: 0000000000000050 RDI: 0000000000000050
> > RBP: ffff883732925cd0 R08: ffff883732774d38 R09: 0000000000000000
> > R10: 0000000000000001 R11: 0000000000000000 R12: 0000000000000000
> > R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000012ac0
> > FS: 0000000000000000(0000) GS:ffff88387f800000(0000)
> > knlGS:0000000000000000
> > CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
> > CR2: 0000000000000004 CR3: 0000000001a03000 CR4: 00000000000006f0
> > DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
> > DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
> > Process swapper (pid: 1, threadinfo ffff883732924000, task
> > ffff8837329234c0)
> > Stack:
> > ffff883732925cf0 0000000000000020 0000000000000020 ffff883732775300
> > 0000000000000000 0000000000000286 ffff883732925cf0 ffffffff8104e9da
> > 0000000000000022 ffff883732774b40 ffff883732925d40 ffffffff8105ae11
> > Call Trace:
> > [<ffffffff8104e9da>] select_task_rq_rt+0x7a/0x90
> > [<ffffffff8105ae11>] try_to_wake_up+0x111/0x280
> > [<ffffffff8105afd5>] wake_up_process+0x15/0x20
> > [<ffffffff814cc5c9>] rcu_cpu_notify+0xd6/0x196
> > [<ffffffff814d6625>] notifier_call_chain+0x55/0x80
> > [<ffffffff8108a77e>] __raw_notifier_call_chain+0xe/0x10
> > [<ffffffff81064560>] __cpu_notify+0x20/0x40
> > [<ffffffff814caf88>] _cpu_up+0xc7/0x10e
> > [<ffffffff814cb0a6>] cpu_up+0xd7/0xea
> > [<ffffffff81c41cab>] smp_init+0x41/0x96
> > [<ffffffff81c227d4>] kernel_init+0x1d6/0x262
> > [<ffffffff814dbc04>] kernel_thread_helper+0x4/0x10
> > [<ffffffff81c225fe>] ? do_basic_setup+0x5c/0x5c
> > [<ffffffff814dbc00>] ? gs_change+0x13/0x13
> > Code: 2a 01 00 48 89 fe 48 8b 04 c5 40 a3 bf 81 4c 89 e2 49 8b 84 07 88
> > 08 00 00 48 83 c0 38 48 89 c7 e8 b5 74 0a 00 85 c0 74 ae 89 d8
> > 0f a3 1c 24 19 d2 85 d2 75 a6 45 0f a3 2c 24 19 c0 41 be ff
> > RIP [<ffffffff8104e8b1>] find_lowest_rq+0xa1/0x150
> > RSP <ffff883732925ca0>
> > CR2: 0000000000000004
> > ---[ end trace 6afdf060c90559fd ]---
>
> >
> > This is on a Westmere-EX (4 socket, 40 cores)
>
> Hmm, how often does that happen? my wsm-ep (2*6*2) doesn't seem to
> suffer said problem. I'll try and see if I can spot the boo-boo. Also,
> happen to have a .config handy?

Does the below cure things?

---
kernel/Makefile | 1 +
kernel/sched.c | 39 +++++++++++++++++++++++----------------
2 files changed, 24 insertions(+), 16 deletions(-)

diff --git a/kernel/Makefile b/kernel/Makefile
index 2d64cfc..65eff6c 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -80,6 +80,7 @@ obj-$(CONFIG_LOCKUP_DETECTOR) += watchdog.o
obj-$(CONFIG_GENERIC_HARDIRQS) += irq/
obj-$(CONFIG_SECCOMP) += seccomp.o
obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
+obj-m += test.o
obj-$(CONFIG_TREE_RCU) += rcutree.o
obj-$(CONFIG_TREE_PREEMPT_RCU) += rcutree.o
obj-$(CONFIG_TREE_RCU_TRACE) += rcutree_trace.o
diff --git a/kernel/sched.c b/kernel/sched.c
index 5925275..a602e7e 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -6413,26 +6413,10 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
rq->calc_load_update = calc_load_update;
break;

- case CPU_ONLINE:
- /* Update our root-domain */
- raw_spin_lock_irqsave(&rq->lock, flags);
- if (rq->rd) {
- BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
-
- set_rq_online(rq);
- }
- raw_spin_unlock_irqrestore(&rq->lock, flags);
- break;
-
#ifdef CONFIG_HOTPLUG_CPU
case CPU_DYING:
sched_ttwu_pending();
- /* Update our root-domain */
raw_spin_lock_irqsave(&rq->lock, flags);
- if (rq->rd) {
- BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
- set_rq_offline(rq);
- }
migrate_tasks(cpu);
BUG_ON(rq->nr_running != 1); /* the migration thread */
raw_spin_unlock_irqrestore(&rq->lock, flags);
@@ -6461,9 +6445,21 @@ static struct notifier_block __cpuinitdata migration_notifier = {
static int __cpuinit sched_cpu_active(struct notifier_block *nfb,
unsigned long action, void *hcpu)
{
+ int cpu = (long)hcpu;
+ unsigned long flags;
+ struct rq *rq = cpu_rq(cpu);
+
switch (action & ~CPU_TASKS_FROZEN) {
case CPU_ONLINE:
case CPU_DOWN_FAILED:
+ /* Update our root-domain */
+ raw_spin_lock_irqsave(&rq->lock, flags);
+ if (rq->rd) {
+ BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
+
+ set_rq_online(rq);
+ }
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
set_cpu_active((long)hcpu, true);
return NOTIFY_OK;
default:
@@ -6474,9 +6470,20 @@ static int __cpuinit sched_cpu_active(struct notifier_block *nfb,
static int __cpuinit sched_cpu_inactive(struct notifier_block *nfb,
unsigned long action, void *hcpu)
{
+ int cpu = (long)hcpu;
+ unsigned long flags;
+ struct rq *rq = cpu_rq(cpu);
+
switch (action & ~CPU_TASKS_FROZEN) {
case CPU_DOWN_PREPARE:
set_cpu_active((long)hcpu, false);
+ /* Update our root-domain */
+ raw_spin_lock_irqsave(&rq->lock, flags);
+ if (rq->rd) {
+ BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
+ set_rq_offline(rq);
+ }
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
return NOTIFY_OK;
default:
return NOTIFY_DONE;


\
 
 \ /
  Last update: 2011-06-10 16:49    [W:2.204 / U:0.036 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site