After adding my (unacceptable) CPU hotplug patchset on top of 3.2.9-rt17
I hit this bug:
<3>BUG: sleeping function called from invalid context
at /home/rostedt/work/git/linux-rt.git/kernel/rtmutex.c:1264
<3>in_atomic(): 1, irqs_disabled(): 1, pid: 0, name: swapper/1
2 locks held by swapper/1/0:
#0: (stop_cpus_mutex){......}, at: [<ffffffff8108f1da>]
stop_machine_from_inactive_cpu+0x5e/0xd4
#1: (stopper_lock){......}, at: [<ffffffff8108ee75>]
queue_stop_cpus_work+0x79/0xce
Pid: 0, comm: swapper/1 Not tainted 3.2.9-test-rt17+ #30
Call Trace:
[<ffffffff8103374f>] __might_sleep+0xf6/0xfb
[<ffffffff814281f1>] rt_mutex_lock+0x21/0x34
[<ffffffff81428a87>] _mutex_lock+0x3c/0x43
[<ffffffff8108ee75>] ? queue_stop_cpus_work+0x79/0xce
[<ffffffff8108ee75>] queue_stop_cpus_work+0x79/0xce
[<ffffffff8108f21c>] stop_machine_from_inactive_cpu+0xa0/0xd4
[<ffffffff810169b6>] ? mtrr_restore+0x4a/0x4a
[<ffffffff81016fd8>] mtrr_ap_init+0x5a/0x5c
[<ffffffff814175eb>] identify_secondary_cpu+0x19/0x1b
[<ffffffff81419e5f>] smp_store_cpu_info+0x3c/0x3e
[<ffffffff8141a242>] start_secondary+0xf9/0x1d2
I wrote the following patch to work around this bug and currently the
hotplug stress test is still chugging along just fine :-)
Note, I expect this patch to be unacceptable too, but I'm posting it for
those that might be interested.
It should probably be commented too. The gist is that if the
queue_stop_cpus_work() is called from an inactive CPU (one coming on
line) it does a spin lock on the stopper_lock instead of grabbing it. I
haven't looked too deeply if this would cause deadlocks, because
honestly, I think this patch sucks :-p
-- Steve
Signed-off-by: Steven Rostedt <rostedt@xxxxxxxxxxx>
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 561ba3a..899dc12 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -158,7 +158,7 @@ static DEFINE_PER_CPU(struct cpu_stop_work, stop_cpus_work);
static void queue_stop_cpus_work(const struct cpumask *cpumask,
cpu_stop_fn_t fn, void *arg,
- struct cpu_stop_done *done)
+ struct cpu_stop_done *done, int inactive)
{
struct cpu_stop_work *work;
unsigned int cpu;
@@ -175,7 +175,11 @@ static void queue_stop_cpus_work(const struct cpumask *cpumask,
* Make sure that all work is queued on all cpus before we
* any of the cpus can execute it.
*/
- mutex_lock(&stopper_lock);
+ if (inactive)
+ while (!mutex_trylock(&stopper_lock))
+ cpu_relax();
+ else
+ mutex_lock(&stopper_lock);
for_each_cpu(cpu, cpumask)
cpu_stop_queue_work(&per_cpu(cpu_stopper, cpu),
&per_cpu(stop_cpus_work, cpu));
@@ -188,7 +192,7 @@ static int __stop_cpus(const struct cpumask *cpumask,
struct cpu_stop_done done;
cpu_stop_init_done(&done, cpumask_weight(cpumask));
- queue_stop_cpus_work(cpumask, fn, arg, &done);
+ queue_stop_cpus_work(cpumask, fn, arg, &done, 0);
wait_for_stop_done(&done);
return done.executed ? done.ret : -ENOENT;
}
@@ -601,7 +605,7 @@ int stop_machine_from_inactive_cpu(int (*fn)(void *), void *data,
set_state(&smdata, STOPMACHINE_PREPARE);
cpu_stop_init_done(&done, num_active_cpus());
queue_stop_cpus_work(cpu_active_mask, stop_machine_cpu_stop, &smdata,
- &done);
+ &done, 1);
ret = stop_machine_cpu_stop(&smdata);
/* Busy wait for completion. */
--
To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
