This patch fixes the lockdep warning below
[ 7.229767] DEBUG_LOCKS_WARN_ON(irqs_disabled_flags(flags))
[ 7.229776] ------------[ cut here ]------------
[ 7.229787] WARNING: CPU: 1 PID: 1 at linux-next/kernel/locking/lockdep.c:2876 loc
kdep_trace_alloc+0xe0/0xf0
[ 7.229790] Modules linked in:
[ 7.229793]
[ 7.229798] CPU: 1 PID: 1 Comm: swapper/0 Not tainted 4.8.0-11756-g86c5152 #46
...
[ 7.229900] Call trace:
[ 7.229903] Exception stack(0xffff8007da837890 to 0xffff8007da8379c0)
[ 7.229906] 7880: ffff8007da834000 0001000000000000
[ 7.229909] 78a0: ffff8007da837a70 ffff0000081111a0 00000000600000c5 000000000000003d
[ 7.229912] 78c0: 9374bc6a7f3c7832 0000000000381878 ffff000009db7ab8 000000000000002f
[ 7.229915] 78e0: ffff00000811aabc ffff000008be2548 ffff8007da837990 ffff00000811adf8
[ 7.229918] 7900: ffff8007da834000 00000000024080c0 00000000000000c0 ffff000009021000
[ 7.229921] 7920: 0000000000000000 0000000000000000 ffff000008c8f7c8 ffff8007da579810
[ 7.229923] 7940: 000000000000002f ffff8007da858000 0000000000000000 0000000000000001
[ 7.229926] 7960: 0000000000000001 0000000000000000 ffff00000811a468 0000000000000002
[ 7.229929] 7980: 656c62617369645f 0000000000038187 00000000000000ee ffff8007da837850
[ 7.229932] 79a0: ffff000009db50c0 ffff000009db569d 0000000000000006 ffff000089db568f
[ 7.229936] [<ffff0000081111a0>] lockdep_trace_alloc+0xe0/0xf0
[ 7.229940] [<ffff0000081f4950>] __kmalloc_track_caller+0x50/0x250
[ 7.229945] [<ffff00000857c088>] devres_alloc_node+0x28/0x60
[ 7.229949] [<ffff0000081220e0>] devm_request_threaded_irq+0x50/0xe0
[ 7.229955] [<ffff0000087e6220>] pcc_mbox_request_channel+0x110/0x170
[ 7.229960] [<ffff0000084b2660>] acpi_cppc_processor_probe+0x264/0x414
[ 7.229963] [<ffff0000084ae9f4>] __acpi_processor_start+0x28/0xa0
[ 7.229966] [<ffff0000084aeab0>] acpi_processor_start+0x44/0x54
[ 7.229970] [<ffff00000857897c>] driver_probe_device+0x1fc/0x2b0
[ 7.229974] [<ffff000008578ae4>] __driver_attach+0xb4/0xc0
[ 7.229977] [<ffff00000857683c>] bus_for_each_dev+0x5c/0xa0
[ 7.229980] [<ffff000008578110>] driver_attach+0x20/0x30
[ 7.229983] [<ffff000008577c20>] bus_add_driver+0x110/0x230
[ 7.229987] [<ffff000008579320>] driver_register+0x60/0x100
[ 7.229991] [<ffff000008d478b8>] acpi_processor_driver_init+0x2c/0xb0
[ 7.229996] [<ffff000008083168>] do_one_initcall+0x38/0x130
[ 7.230000] [<ffff000008d20d6c>] kernel_init_freeable+0x210/0x2b4
[ 7.230004] [<ffff000008945d90>] kernel_init+0x10/0x110
[ 7.230007] [<ffff000008082e80>] ret_from_fork+0x10/0x50
It's because the spinlock inside pcc_mbox_request_channel() is
kept too long. Adding a mutex to protect critical section of this
function. Beside of that, spinlock is still used to protect the
data of channel.
Signed-off-by: Hoan Tran <[email protected]>
---
drivers/mailbox/pcc.c | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/drivers/mailbox/pcc.c b/drivers/mailbox/pcc.c
index 08c87fa..b6cece0 100644
--- a/drivers/mailbox/pcc.c
+++ b/drivers/mailbox/pcc.c
@@ -81,6 +81,8 @@
static int *pcc_doorbell_irq;
static struct mbox_controller pcc_mbox_ctrl = {};
+static DEFINE_MUTEX(pcc_con_mutex);
+
/**
* get_pcc_channel - Given a PCC subspace idx, get
* the respective mbox_channel.
@@ -243,6 +245,7 @@ struct mbox_chan *pcc_mbox_request_channel(struct mbox_client *cl,
struct mbox_chan *chan;
unsigned long flags;
+ mutex_lock(&pcc_con_mutex);
/*
* Each PCC Subspace is a Mailbox Channel.
* The PCC Clients get their PCC Subspace ID
@@ -254,6 +257,7 @@ struct mbox_chan *pcc_mbox_request_channel(struct mbox_client *cl,
if (IS_ERR(chan) || chan->cl) {
dev_err(dev, "Channel not found for idx: %d\n", subspace_id);
+ mutex_unlock(&pcc_con_mutex);
return ERR_PTR(-EBUSY);
}
@@ -267,6 +271,8 @@ struct mbox_chan *pcc_mbox_request_channel(struct mbox_client *cl,
if (chan->txdone_method == TXDONE_BY_POLL && cl->knows_txdone)
chan->txdone_method |= TXDONE_BY_ACK;
+ spin_unlock_irqrestore(&chan->lock, flags);
+
if (pcc_doorbell_irq[subspace_id] > 0) {
int rc;
@@ -279,7 +285,7 @@ struct mbox_chan *pcc_mbox_request_channel(struct mbox_client *cl,
}
}
- spin_unlock_irqrestore(&chan->lock, flags);
+ mutex_unlock(&pcc_con_mutex);
return chan;
}
--
1.9.1
Hi Hoan,
On 10/14/2016 4:52 PM, Hoan Tran wrote:
> This patch fixes the lockdep warning below
>
> [ 7.229767] DEBUG_LOCKS_WARN_ON(irqs_disabled_flags(flags))
> [ 7.229776] ------------[ cut here ]------------
> [ 7.229787] WARNING: CPU: 1 PID: 1 at linux-next/kernel/locking/lockdep.c:2876 loc
> kdep_trace_alloc+0xe0/0xf0
> [ 7.229790] Modules linked in:
> [ 7.229793]
> [ 7.229798] CPU: 1 PID: 1 Comm: swapper/0 Not tainted 4.8.0-11756-g86c5152 #46
> ...
> [ 7.229900] Call trace:
> [ 7.229903] Exception stack(0xffff8007da837890 to 0xffff8007da8379c0)
> [ 7.229906] 7880: ffff8007da834000 0001000000000000
> [ 7.229909] 78a0: ffff8007da837a70 ffff0000081111a0 00000000600000c5 000000000000003d
> [ 7.229912] 78c0: 9374bc6a7f3c7832 0000000000381878 ffff000009db7ab8 000000000000002f
> [ 7.229915] 78e0: ffff00000811aabc ffff000008be2548 ffff8007da837990 ffff00000811adf8
> [ 7.229918] 7900: ffff8007da834000 00000000024080c0 00000000000000c0 ffff000009021000
> [ 7.229921] 7920: 0000000000000000 0000000000000000 ffff000008c8f7c8 ffff8007da579810
> [ 7.229923] 7940: 000000000000002f ffff8007da858000 0000000000000000 0000000000000001
> [ 7.229926] 7960: 0000000000000001 0000000000000000 ffff00000811a468 0000000000000002
> [ 7.229929] 7980: 656c62617369645f 0000000000038187 00000000000000ee ffff8007da837850
> [ 7.229932] 79a0: ffff000009db50c0 ffff000009db569d 0000000000000006 ffff000089db568f
> [ 7.229936] [<ffff0000081111a0>] lockdep_trace_alloc+0xe0/0xf0
> [ 7.229940] [<ffff0000081f4950>] __kmalloc_track_caller+0x50/0x250
> [ 7.229945] [<ffff00000857c088>] devres_alloc_node+0x28/0x60
> [ 7.229949] [<ffff0000081220e0>] devm_request_threaded_irq+0x50/0xe0
> [ 7.229955] [<ffff0000087e6220>] pcc_mbox_request_channel+0x110/0x170
> [ 7.229960] [<ffff0000084b2660>] acpi_cppc_processor_probe+0x264/0x414
> [ 7.229963] [<ffff0000084ae9f4>] __acpi_processor_start+0x28/0xa0
> [ 7.229966] [<ffff0000084aeab0>] acpi_processor_start+0x44/0x54
> [ 7.229970] [<ffff00000857897c>] driver_probe_device+0x1fc/0x2b0
> [ 7.229974] [<ffff000008578ae4>] __driver_attach+0xb4/0xc0
> [ 7.229977] [<ffff00000857683c>] bus_for_each_dev+0x5c/0xa0
> [ 7.229980] [<ffff000008578110>] driver_attach+0x20/0x30
> [ 7.229983] [<ffff000008577c20>] bus_add_driver+0x110/0x230
> [ 7.229987] [<ffff000008579320>] driver_register+0x60/0x100
> [ 7.229991] [<ffff000008d478b8>] acpi_processor_driver_init+0x2c/0xb0
> [ 7.229996] [<ffff000008083168>] do_one_initcall+0x38/0x130
> [ 7.230000] [<ffff000008d20d6c>] kernel_init_freeable+0x210/0x2b4
> [ 7.230004] [<ffff000008945d90>] kernel_init+0x10/0x110
> [ 7.230007] [<ffff000008082e80>] ret_from_fork+0x10/0x50
>
> It's because the spinlock inside pcc_mbox_request_channel() is
> kept too long. Adding a mutex to protect critical section of this
> function. Beside of that, spinlock is still used to protect the
> data of channel.
>
> Signed-off-by: Hoan Tran <[email protected]>
> ---
> drivers/mailbox/pcc.c | 8 +++++++-
> 1 file changed, 7 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/mailbox/pcc.c b/drivers/mailbox/pcc.c
> index 08c87fa..b6cece0 100644
> --- a/drivers/mailbox/pcc.c
> +++ b/drivers/mailbox/pcc.c
> @@ -81,6 +81,8 @@
> static int *pcc_doorbell_irq;
>
> static struct mbox_controller pcc_mbox_ctrl = {};
> +static DEFINE_MUTEX(pcc_con_mutex);
I am not sure this will work. If we are not taking the channel lock, we don't have a good
way to synchronize with the mailbox framework while we are accessing the same data.
Why don't we just move out the devm_request_irq and devm_free_irq outside the
critical section? In pcc_mbox_request_channel, we can call devm_request_irq after
releasing the spin_lock and in pcc_mbox_free_channel we can call devm_free_irq and
then take the spin_lock to access the shared data.
--
Thanks,
Prashanth
Hi Prashanth,
On Fri, Oct 14, 2016 at 4:44 PM, Prakash, Prashanth
<[email protected]> wrote:
> Hi Hoan,
>
> On 10/14/2016 4:52 PM, Hoan Tran wrote:
>> This patch fixes the lockdep warning below
>>
>> [ 7.229767] DEBUG_LOCKS_WARN_ON(irqs_disabled_flags(flags))
>> [ 7.229776] ------------[ cut here ]------------
>> [ 7.229787] WARNING: CPU: 1 PID: 1 at linux-next/kernel/locking/lockdep.c:2876 loc
>> kdep_trace_alloc+0xe0/0xf0
>> [ 7.229790] Modules linked in:
>> [ 7.229793]
>> [ 7.229798] CPU: 1 PID: 1 Comm: swapper/0 Not tainted 4.8.0-11756-g86c5152 #46
>> ...
>> [ 7.229900] Call trace:
>> [ 7.229903] Exception stack(0xffff8007da837890 to 0xffff8007da8379c0)
>> [ 7.229906] 7880: ffff8007da834000 0001000000000000
>> [ 7.229909] 78a0: ffff8007da837a70 ffff0000081111a0 00000000600000c5 000000000000003d
>> [ 7.229912] 78c0: 9374bc6a7f3c7832 0000000000381878 ffff000009db7ab8 000000000000002f
>> [ 7.229915] 78e0: ffff00000811aabc ffff000008be2548 ffff8007da837990 ffff00000811adf8
>> [ 7.229918] 7900: ffff8007da834000 00000000024080c0 00000000000000c0 ffff000009021000
>> [ 7.229921] 7920: 0000000000000000 0000000000000000 ffff000008c8f7c8 ffff8007da579810
>> [ 7.229923] 7940: 000000000000002f ffff8007da858000 0000000000000000 0000000000000001
>> [ 7.229926] 7960: 0000000000000001 0000000000000000 ffff00000811a468 0000000000000002
>> [ 7.229929] 7980: 656c62617369645f 0000000000038187 00000000000000ee ffff8007da837850
>> [ 7.229932] 79a0: ffff000009db50c0 ffff000009db569d 0000000000000006 ffff000089db568f
>> [ 7.229936] [<ffff0000081111a0>] lockdep_trace_alloc+0xe0/0xf0
>> [ 7.229940] [<ffff0000081f4950>] __kmalloc_track_caller+0x50/0x250
>> [ 7.229945] [<ffff00000857c088>] devres_alloc_node+0x28/0x60
>> [ 7.229949] [<ffff0000081220e0>] devm_request_threaded_irq+0x50/0xe0
>> [ 7.229955] [<ffff0000087e6220>] pcc_mbox_request_channel+0x110/0x170
>> [ 7.229960] [<ffff0000084b2660>] acpi_cppc_processor_probe+0x264/0x414
>> [ 7.229963] [<ffff0000084ae9f4>] __acpi_processor_start+0x28/0xa0
>> [ 7.229966] [<ffff0000084aeab0>] acpi_processor_start+0x44/0x54
>> [ 7.229970] [<ffff00000857897c>] driver_probe_device+0x1fc/0x2b0
>> [ 7.229974] [<ffff000008578ae4>] __driver_attach+0xb4/0xc0
>> [ 7.229977] [<ffff00000857683c>] bus_for_each_dev+0x5c/0xa0
>> [ 7.229980] [<ffff000008578110>] driver_attach+0x20/0x30
>> [ 7.229983] [<ffff000008577c20>] bus_add_driver+0x110/0x230
>> [ 7.229987] [<ffff000008579320>] driver_register+0x60/0x100
>> [ 7.229991] [<ffff000008d478b8>] acpi_processor_driver_init+0x2c/0xb0
>> [ 7.229996] [<ffff000008083168>] do_one_initcall+0x38/0x130
>> [ 7.230000] [<ffff000008d20d6c>] kernel_init_freeable+0x210/0x2b4
>> [ 7.230004] [<ffff000008945d90>] kernel_init+0x10/0x110
>> [ 7.230007] [<ffff000008082e80>] ret_from_fork+0x10/0x50
>>
>> It's because the spinlock inside pcc_mbox_request_channel() is
>> kept too long. Adding a mutex to protect critical section of this
>> function. Beside of that, spinlock is still used to protect the
>> data of channel.
>>
>> Signed-off-by: Hoan Tran <[email protected]>
>> ---
>> drivers/mailbox/pcc.c | 8 +++++++-
>> 1 file changed, 7 insertions(+), 1 deletion(-)
>>
>> diff --git a/drivers/mailbox/pcc.c b/drivers/mailbox/pcc.c
>> index 08c87fa..b6cece0 100644
>> --- a/drivers/mailbox/pcc.c
>> +++ b/drivers/mailbox/pcc.c
>> @@ -81,6 +81,8 @@
>> static int *pcc_doorbell_irq;
>>
>> static struct mbox_controller pcc_mbox_ctrl = {};
>> +static DEFINE_MUTEX(pcc_con_mutex);
> I am not sure this will work. If we are not taking the channel lock, we don't have a good
> way to synchronize with the mailbox framework while we are accessing the same data.
It is still using the spinlock for accessing the channel data.
>
> Why don't we just move out the devm_request_irq and devm_free_irq outside the
> critical section? In pcc_mbox_request_channel, we can call devm_request_irq after
> releasing the spin_lock and in pcc_mbox_free_channel we can call devm_free_irq and
> then take the spin_lock to access the shared data.
It's maybe I worried about a channel can be requested multiple at the
same time. But this case does not occur when each channel is used for
a single client.
I'll move the spin_lock before request_irq and free_irq() instead.
Thanks
Hoan
>
> --
> Thanks,
> Prashanth
>