Re: [LOCKDEP] cpufreq: possible circular locking dependency detected

From: Sergey Senozhatsky
Date: Tue Jul 16 2013 - 06:44:46 EST


On (07/16/13 14:03), Srivatsa S. Bhat wrote:
> >> So here is the solution:
> >>
> >> On 3.11-rc1, apply these patches in the order mentioned below, and check
> >> whether it fixes _all_ problems (both the warnings about IPI as well as the
> >> lockdep splat).
> >>
> >> 1. Patch given in: https://lkml.org/lkml/2013/7/11/661
> >> (Just apply patch 1, not the entire patchset).
> >>
> >> 2. Apply the patch shown below, on top of the above patch:
> >>
> >> ---------------------------------------------------------------------------
> >>
> >
> > Hello Srivatsa,
> > Thanks, I'll test a bit later -- in the morning. (laptop stopped resuming from
> > suspend, probably radeon dmp).
> >
> >
>
> Sure, thanks!
>
> >
> > Shouldn't we also kick the console lock?
> >
> >
> > kernel/printk.c | 3 +++
> > 1 file changed, 3 insertions(+)
> >
> > diff --git a/kernel/printk.c b/kernel/printk.c
> > index d37d45c..3e20233 100644
> > --- a/kernel/printk.c
> > +++ b/kernel/printk.c
> > @@ -1926,8 +1926,11 @@ static int __cpuinit console_cpu_notify(struct notifier_block *self,
> > {
> > switch (action) {
> > case CPU_ONLINE:
> > + case CPU_ONLINE_FROZEN:
> > case CPU_DEAD:
> > + case CPU_DEAD_FROZEN:
> > case CPU_DOWN_FAILED:
> > + case CPU_DOWN_FAILED_FROZEN:
> > case CPU_UP_CANCELED:
> > console_lock();
> > console_unlock();
> >
> >
>
> No need. suspend_console() and resume_console() already handle it
> properly in the suspend/resume case, from what I can see.
>

I've managed to wake up my laptop from suspend, and something's not right.


# for i in {1..5}; do \
echo 0 > /sys/devices/system/cpu/cpu3/online; \
echo 0 > /sys/devices/system/cpu/cpu2/online; \
echo 1 > /sys/devices/system/cpu/cpu3/online; \
echo 0 > /sys/devices/system/cpu/cpu1/online; \
echo 1 > /sys/devices/system/cpu/cpu1/online; \
echo 1 > /sys/devices/system/cpu/cpu2/online; \
done
# systemctl suspend
-> resume


[ 227.329656] ACPI: Preparing to enter system sleep state S3
[ 227.353334] PM: Saving platform NVS memory

[ 227.355403] ======================================================
[ 227.355404] [ INFO: possible circular locking dependency detected ]
[ 227.355407] 3.11.0-rc1-dbg-01398-gf537e41-dirty #1838 Not tainted
[ 227.355408] -------------------------------------------------------
[ 227.355411] systemd-sleep/2280 is trying to acquire lock:
[ 227.355426] (cpu_add_remove_lock){+.+.+.}, at: [<ffffffff8104dab4>]
disable_nonboot_cpus+0x24/0x120
[ 227.355427]
but task is already holding lock:
[ 227.355434] (console_lock){+.+.+.}, at: [<ffffffff8104c956>]
suspend_console+0x26/0x40
[ 227.355435]
which lock already depends on the new lock.

[ 227.355436]
the existing dependency chain (in reverse order) is:
[ 227.355441]
-> #2 (console_lock){+.+.+.}:
[ 227.355448] [<ffffffff810b8fb4>] lock_acquire+0xa4/0x200
[ 227.355452] [<ffffffff8104b197>] console_lock+0x77/0x80
[ 227.355456] [<ffffffff8104cf91>] console_cpu_notify+0x31/0x40
[ 227.355462] [<ffffffff8107cd6d>] notifier_call_chain+0x5d/0x110
[ 227.355466] [<ffffffff8107ce2e>] __raw_notifier_call_chain+0xe/0x10
[ 227.355469] [<ffffffff8104d5a3>] cpu_notify+0x23/0x50
[ 227.355473] [<ffffffff8104d5de>] cpu_notify_nofail+0xe/0x20
[ 227.355482] [<ffffffff815fafad>] _cpu_down+0x1ad/0x330
[ 227.355486] [<ffffffff815fb166>] cpu_down+0x36/0x50
[ 227.355493] [<ffffffff814ad8cd>] cpu_subsys_offline+0x1d/0x30
[ 227.355498] [<ffffffff814a8de5>] device_offline+0x95/0xc0
[ 227.355502] [<ffffffff814a8ee2>] store_online+0x42/0x90
[ 227.355506] [<ffffffff814a64f8>] dev_attr_store+0x18/0x30
[ 227.355513] [<ffffffff811ec71b>] sysfs_write_file+0xdb/0x150
[ 227.355517] [<ffffffff8117a68d>] vfs_write+0xbd/0x1e0
[ 227.355522] [<ffffffff8117ad7c>] SyS_write+0x4c/0xa0
[ 227.355527] [<ffffffff8160cbfe>] tracesys+0xd0/0xd5
[ 227.355531]
-> #1 (cpu_hotplug.lock){+.+.+.}:
[ 227.355535] [<ffffffff810b8fb4>] lock_acquire+0xa4/0x200
[ 227.355541] [<ffffffff81605b47>] mutex_lock_nested+0x67/0x410
[ 227.355545] [<ffffffff8104d54b>] cpu_hotplug_begin+0x2b/0x60
[ 227.355549] [<ffffffff8104d61a>] _cpu_up+0x2a/0x170
[ 227.355552] [<ffffffff8104d7b9>] cpu_up+0x59/0x80
[ 227.355558] [<ffffffff81cf51b6>] smp_init+0x64/0x95
[ 227.355566] [<ffffffff81cdaf21>] kernel_init_freeable+0x84/0x191
[ 227.355570] [<ffffffff815fa34e>] kernel_init+0xe/0x180
[ 227.355574] [<ffffffff8160c9ac>] ret_from_fork+0x7c/0xb0
[ 227.355578]
-> #0 (cpu_add_remove_lock){+.+.+.}:
[ 227.355582] [<ffffffff810b8106>] __lock_acquire+0x1766/0x1d30
[ 227.355586] [<ffffffff810b8fb4>] lock_acquire+0xa4/0x200
[ 227.355590] [<ffffffff81605b47>] mutex_lock_nested+0x67/0x410
[ 227.355594] [<ffffffff8104dab4>] disable_nonboot_cpus+0x24/0x120
[ 227.355601] [<ffffffff810a0973>] suspend_devices_and_enter+0x1f3/0x680
[ 227.355605] [<ffffffff810a0fd2>] pm_suspend+0x1d2/0x240
[ 227.355609] [<ffffffff8109fa19>] state_store+0x79/0xf0
[ 227.355614] [<ffffffff81312dbf>] kobj_attr_store+0xf/0x20
[ 227.355618] [<ffffffff811ec71b>] sysfs_write_file+0xdb/0x150
[ 227.355621] [<ffffffff8117a68d>] vfs_write+0xbd/0x1e0
[ 227.355624] [<ffffffff8117ad7c>] SyS_write+0x4c/0xa0
[ 227.355628] [<ffffffff8160cbfe>] tracesys+0xd0/0xd5
[ 227.355629]
other info that might help us debug this:

[ 227.355635] Chain exists of:
cpu_add_remove_lock --> cpu_hotplug.lock --> console_lock

[ 227.355637] Possible unsafe locking scenario:

[ 227.355638] CPU0 CPU1
[ 227.355639] ---- ----
[ 227.355642] lock(console_lock);
[ 227.355644] lock(cpu_hotplug.lock);
[ 227.355647] lock(console_lock);
[ 227.355650] lock(cpu_add_remove_lock);
[ 227.355651]
*** DEADLOCK ***

[ 227.355653] 5 locks held by systemd-sleep/2280:
[ 227.355661] #0: (sb_writers#6){.+.+.+}, at: [<ffffffff8117a78b>] vfs_write+0x1bb/0x1e0
[ 227.355668] #1: (&buffer->mutex){+.+.+.}, at: [<ffffffff811ec67c>] sysfs_write_file+0x3c/0x150
[ 227.355676] #2: (s_active#110){.+.+.+}, at: [<ffffffff811ec703>] sysfs_write_file+0xc3/0x150
[ 227.355683] #3: (pm_mutex){+.+.+.}, at: [<ffffffff810a0e32>] pm_suspend+0x32/0x240
[ 227.355690] #4: (console_lock){+.+.+.}, at: [<ffffffff8104c956>] suspend_console+0x26/0x40
[ 227.355691]
stack backtrace:
[ 227.355695] CPU: 0 PID: 2280 Comm: systemd-sleep Not tainted 3.11.0-rc1-dbg-01398-gf537e41-dirty #1838
[ 227.355697] Hardware name: Acer Aspire 5741G /Aspire 5741G , BIOS V1.20 02/08/2011
[ 227.355703] ffffffff82208680 ffff88015151bbc8 ffffffff81603038 ffffffff822073f0
[ 227.355707] ffff88015151bc08 ffffffff815ffdaa ffff880153389fa0 ffff88015338a788
[ 227.355712] 1d81e4832c04c441 ffff88015338a760 ffff88015338a788 ffff880153389fa0
[ 227.355713] Call Trace:
[ 227.355719] [<ffffffff81603038>] dump_stack+0x4e/0x82
[ 227.355723] [<ffffffff815ffdaa>] print_circular_bug+0x2b6/0x2c5
[ 227.355727] [<ffffffff810b8106>] __lock_acquire+0x1766/0x1d30
[ 227.355733] [<ffffffff81054aec>] ? walk_system_ram_range+0x5c/0x140
[ 227.355737] [<ffffffff810b63f4>] ? mark_held_locks+0x94/0x140
[ 227.355741] [<ffffffff810b8fb4>] lock_acquire+0xa4/0x200
[ 227.355745] [<ffffffff8104dab4>] ? disable_nonboot_cpus+0x24/0x120
[ 227.355749] [<ffffffff8104dab4>] ? disable_nonboot_cpus+0x24/0x120
[ 227.355753] [<ffffffff81605b47>] mutex_lock_nested+0x67/0x410
[ 227.355757] [<ffffffff8104dab4>] ? disable_nonboot_cpus+0x24/0x120
[ 227.355761] [<ffffffff81607e9e>] ? mutex_unlock+0xe/0x10
[ 227.355768] [<ffffffff8135bd2f>] ? acpi_os_get_iomem+0x4c/0x54
[ 227.355772] [<ffffffff8104dab4>] disable_nonboot_cpus+0x24/0x120
[ 227.355777] [<ffffffff810a0973>] suspend_devices_and_enter+0x1f3/0x680
[ 227.355780] [<ffffffff815fefc6>] ? printk+0x67/0x69
[ 227.355785] [<ffffffff810a0fd2>] pm_suspend+0x1d2/0x240
[ 227.355789] [<ffffffff8109fa19>] state_store+0x79/0xf0
[ 227.355792] [<ffffffff81312dbf>] kobj_attr_store+0xf/0x20
[ 227.355796] [<ffffffff811ec71b>] sysfs_write_file+0xdb/0x150
[ 227.355799] [<ffffffff8117a68d>] vfs_write+0xbd/0x1e0
[ 227.355804] [<ffffffff81198490>] ? fget_light+0x320/0x4b0
[ 227.355808] [<ffffffff8117ad7c>] SyS_write+0x4c/0xa0
[ 227.355811] [<ffffffff8160cbfe>] tracesys+0xd0/0xd5
[ 227.355814] Disabling non-boot CPUs ...
[ 227.357731] smpboot: CPU 1 is now offline
[ 227.461072] smpboot: CPU 2 is now offline
[ 227.565119] smpboot: CPU 3 is now offline



Just to make sure I didn't miss anything:

git diff -u -p drivers/cpufreq/

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 0937b8d..7dcfa68 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1942,13 +1942,15 @@ static int __cpuinit cpufreq_cpu_callback(struct notifier_block *nfb,
if (dev) {
switch (action) {
case CPU_ONLINE:
+ case CPU_ONLINE_FROZEN:
cpufreq_add_dev(dev, NULL);
break;
case CPU_DOWN_PREPARE:
- case CPU_UP_CANCELED_FROZEN:
+ case CPU_DOWN_PREPARE_FROZEN:
__cpufreq_remove_dev(dev, NULL);
break;
case CPU_DOWN_FAILED:
+ case CPU_DOWN_FAILED_FROZEN:
cpufreq_add_dev(dev, NULL);
break;
}
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index 4645876..7b839a8 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -25,7 +25,6 @@
#include <linux/slab.h>
#include <linux/types.h>
#include <linux/workqueue.h>
-#include <linux/cpu.h>

#include "cpufreq_governor.h"

@@ -137,10 +136,8 @@ void gov_queue_work(struct dbs_data *dbs_data, struct cpufreq_policy *policy,
if (!all_cpus) {
__gov_queue_work(smp_processor_id(), dbs_data, delay);
} else {
- get_online_cpus();
for_each_cpu(i, policy->cpus)
__gov_queue_work(i, dbs_data, delay);
- put_online_cpus();
}
}
EXPORT_SYMBOL_GPL(gov_queue_work);
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index cd9e817..12225d1 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -353,13 +353,11 @@ static int __cpuinit cpufreq_stat_cpu_callback(struct notifier_block *nfb,
cpufreq_update_policy(cpu);
break;
case CPU_DOWN_PREPARE:
+ case CPU_DOWN_PREPARE_FROZEN:
cpufreq_stats_free_sysfs(cpu);
break;
case CPU_DEAD:
- cpufreq_stats_free_table(cpu);
- break;
- case CPU_UP_CANCELED_FROZEN:
- cpufreq_stats_free_sysfs(cpu);
+ case CPU_DEAD_FROZEN:
cpufreq_stats_free_table(cpu);
break;
}


-ss
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/