drm/amdgpu: Fix error RCU usage

Submitted by Xie, AlexBin on July 20, 2017, 2:27 a.m.

Details

Message ID 1500517655-10357-1-git-send-email-AlexBin.Xie@amd.com
State New
Headers show
Series "drm/amdgpu: Fix error RCU usage" ( rev: 1 ) in AMD X.Org drivers

Not browsing as part of any series.

Commit Message

Xie, AlexBin July 20, 2017, 2:27 a.m.
In RCU read-side critical sections, blocking or sleeping is prohibited.

Reported by: Dave Airlie

[  141.965723] =============================
[  141.965724] WARNING: suspicious RCU usage
[  141.965726] 4.12.0-rc7 #221 Not tainted
[  141.965727] -----------------------------
[  141.965728] /home/airlied/devel/kernel/linux-2.6/include/linux/rcupdate.h:531
Illegal context switch in RCU read-side critical section!
[  141.965730]
               other info that might help us debug this:

[  141.965731]
               rcu_scheduler_active = 2, debug_locks = 0
[  141.965732] 1 lock held by amdgpu_cs:0/1332:
[  141.965733]  #0:  (rcu_read_lock){......}, at: [<ffffffffa01a0d07>]
amdgpu_bo_list_get+0x0/0x109 [amdgpu]
[  141.965774]
               stack backtrace:
[  141.965776] CPU: 6 PID: 1332 Comm: amdgpu_cs:0 Not tainted 4.12.0-rc7 #221
[  141.965777] Hardware name: To be filled by O.E.M. To be filled by
O.E.M./M5A97 R2.0, BIOS 2603 06/26/2015
[  141.965778] Call Trace:
[  141.965782]  dump_stack+0x68/0x92
[  141.965785]  lockdep_rcu_suspicious+0xf7/0x100
[  141.965788]  ___might_sleep+0x56/0x1fc
[  141.965790]  __might_sleep+0x68/0x6f
[  141.965793]  __mutex_lock+0x4e/0x7b5
[  141.965817]  ? amdgpu_bo_list_get+0xa4/0x109 [amdgpu]
[  141.965820]  ? lock_acquire+0x125/0x1b9
[  141.965844]  ? amdgpu_bo_list_set+0x464/0x464 [amdgpu]
[  141.965846]  mutex_lock_nested+0x16/0x18
[  141.965848]  ? mutex_lock_nested+0x16/0x18
[  141.965872]  amdgpu_bo_list_get+0xa4/0x109 [amdgpu]
[  141.965895]  amdgpu_cs_ioctl+0x4a0/0x17dd [amdgpu]
[  141.965898]  ? radix_tree_node_alloc.constprop.11+0x77/0xab
[  141.965916]  drm_ioctl+0x264/0x393 [drm]
[  141.965939]  ? amdgpu_cs_find_mapping+0x83/0x83 [amdgpu]
[  141.965942]  ? trace_hardirqs_on_caller+0x16a/0x186

Signed-off-by: Alex Xie <AlexBin.Xie@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

Patch hide | download patch | download mbox

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
index dc87962..565ca90 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
@@ -198,12 +198,15 @@  amdgpu_bo_list_get(struct amdgpu_fpriv *fpriv, int id)
 	result = idr_find(&fpriv->bo_list_handles, id);
 
 	if (result) {
-		if (kref_get_unless_zero(&result->refcount))
+		if (kref_get_unless_zero(&result->refcount)) {
+			rcu_read_unlock();
 			mutex_lock(&result->lock);
-		else
+		}
+		else {
+			rcu_read_unlock();
 			result = NULL;
+		}
 	}
-	rcu_read_unlock();
 
 	return result;
 }

Comments

On 20 July 2017 at 12:27, Alex Xie <AlexBin.Xie@amd.com> wrote:
> In RCU read-side critical sections, blocking or sleeping is prohibited.
>

Seems to work here.

Tested-by: Dave Airlie <airlied@redhat.com>

> Reported by: Dave Airlie
>
> [  141.965723] =============================
> [  141.965724] WARNING: suspicious RCU usage
> [  141.965726] 4.12.0-rc7 #221 Not tainted
> [  141.965727] -----------------------------
> [  141.965728] /home/airlied/devel/kernel/linux-2.6/include/linux/rcupdate.h:531
> Illegal context switch in RCU read-side critical section!
> [  141.965730]
>                other info that might help us debug this:
>
> [  141.965731]
>                rcu_scheduler_active = 2, debug_locks = 0
> [  141.965732] 1 lock held by amdgpu_cs:0/1332:
> [  141.965733]  #0:  (rcu_read_lock){......}, at: [<ffffffffa01a0d07>]
> amdgpu_bo_list_get+0x0/0x109 [amdgpu]
> [  141.965774]
>                stack backtrace:
> [  141.965776] CPU: 6 PID: 1332 Comm: amdgpu_cs:0 Not tainted 4.12.0-rc7 #221
> [  141.965777] Hardware name: To be filled by O.E.M. To be filled by
> O.E.M./M5A97 R2.0, BIOS 2603 06/26/2015
> [  141.965778] Call Trace:
> [  141.965782]  dump_stack+0x68/0x92
> [  141.965785]  lockdep_rcu_suspicious+0xf7/0x100
> [  141.965788]  ___might_sleep+0x56/0x1fc
> [  141.965790]  __might_sleep+0x68/0x6f
> [  141.965793]  __mutex_lock+0x4e/0x7b5
> [  141.965817]  ? amdgpu_bo_list_get+0xa4/0x109 [amdgpu]
> [  141.965820]  ? lock_acquire+0x125/0x1b9
> [  141.965844]  ? amdgpu_bo_list_set+0x464/0x464 [amdgpu]
> [  141.965846]  mutex_lock_nested+0x16/0x18
> [  141.965848]  ? mutex_lock_nested+0x16/0x18
> [  141.965872]  amdgpu_bo_list_get+0xa4/0x109 [amdgpu]
> [  141.965895]  amdgpu_cs_ioctl+0x4a0/0x17dd [amdgpu]
> [  141.965898]  ? radix_tree_node_alloc.constprop.11+0x77/0xab
> [  141.965916]  drm_ioctl+0x264/0x393 [drm]
> [  141.965939]  ? amdgpu_cs_find_mapping+0x83/0x83 [amdgpu]
> [  141.965942]  ? trace_hardirqs_on_caller+0x16a/0x186
>
> Signed-off-by: Alex Xie <AlexBin.Xie@amd.com>
> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c | 9 ++++++---
>  1 file changed, 6 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
> index dc87962..565ca90 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
> @@ -198,12 +198,15 @@ amdgpu_bo_list_get(struct amdgpu_fpriv *fpriv, int id)
>         result = idr_find(&fpriv->bo_list_handles, id);
>
>         if (result) {
> -               if (kref_get_unless_zero(&result->refcount))
> +               if (kref_get_unless_zero(&result->refcount)) {
> +                       rcu_read_unlock();
>                         mutex_lock(&result->lock);
> -               else
> +               }
> +               else {
> +                       rcu_read_unlock();
>                         result = NULL;
> +               }
>         }
> -       rcu_read_unlock();
>
>         return result;
>  }
> --
> 2.7.4
>
> _______________________________________________
> amd-gfx mailing list
> amd-gfx@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/amd-gfx
On 2017年07月20日 10:27, Alex Xie wrote:
> In RCU read-side critical sections, blocking or sleeping is prohibited.
>
> Reported by: Dave Airlie
>
> [  141.965723] =============================
> [  141.965724] WARNING: suspicious RCU usage
> [  141.965726] 4.12.0-rc7 #221 Not tainted
> [  141.965727] -----------------------------
> [  141.965728] /home/airlied/devel/kernel/linux-2.6/include/linux/rcupdate.h:531
> Illegal context switch in RCU read-side critical section!
> [  141.965730]
>                 other info that might help us debug this:
>
> [  141.965731]
>                 rcu_scheduler_active = 2, debug_locks = 0
> [  141.965732] 1 lock held by amdgpu_cs:0/1332:
> [  141.965733]  #0:  (rcu_read_lock){......}, at: [<ffffffffa01a0d07>]
> amdgpu_bo_list_get+0x0/0x109 [amdgpu]
> [  141.965774]
>                 stack backtrace:
> [  141.965776] CPU: 6 PID: 1332 Comm: amdgpu_cs:0 Not tainted 4.12.0-rc7 #221
> [  141.965777] Hardware name: To be filled by O.E.M. To be filled by
> O.E.M./M5A97 R2.0, BIOS 2603 06/26/2015
> [  141.965778] Call Trace:
> [  141.965782]  dump_stack+0x68/0x92
> [  141.965785]  lockdep_rcu_suspicious+0xf7/0x100
> [  141.965788]  ___might_sleep+0x56/0x1fc
> [  141.965790]  __might_sleep+0x68/0x6f
> [  141.965793]  __mutex_lock+0x4e/0x7b5
> [  141.965817]  ? amdgpu_bo_list_get+0xa4/0x109 [amdgpu]
> [  141.965820]  ? lock_acquire+0x125/0x1b9
> [  141.965844]  ? amdgpu_bo_list_set+0x464/0x464 [amdgpu]
> [  141.965846]  mutex_lock_nested+0x16/0x18
> [  141.965848]  ? mutex_lock_nested+0x16/0x18
> [  141.965872]  amdgpu_bo_list_get+0xa4/0x109 [amdgpu]
> [  141.965895]  amdgpu_cs_ioctl+0x4a0/0x17dd [amdgpu]
> [  141.965898]  ? radix_tree_node_alloc.constprop.11+0x77/0xab
> [  141.965916]  drm_ioctl+0x264/0x393 [drm]
> [  141.965939]  ? amdgpu_cs_find_mapping+0x83/0x83 [amdgpu]
> [  141.965942]  ? trace_hardirqs_on_caller+0x16a/0x186
>
> Signed-off-by: Alex Xie <AlexBin.Xie@amd.com>
> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c | 9 ++++++---
>   1 file changed, 6 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
> index dc87962..565ca90 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
> @@ -198,12 +198,15 @@ amdgpu_bo_list_get(struct amdgpu_fpriv *fpriv, int id)
>   	result = idr_find(&fpriv->bo_list_handles, id);
>   
>   	if (result) {
> -		if (kref_get_unless_zero(&result->refcount))
> +		if (kref_get_unless_zero(&result->refcount)) {
> +			rcu_read_unlock();
>   			mutex_lock(&result->lock);
> -		else
> +		}
> +		else {
> +			rcu_read_unlock();
>   			result = NULL;
> +		}
>   	}
> -	rcu_read_unlock();
how about result==NULL case? will lost rcu unlock, right?

David Zhou
>   
>   	return result;
>   }
I am working on v2 while you are point out this. Thanks.


On 2017-07-19 10:33 PM, zhoucm1 wrote:
>
>
> On 2017年07月20日 10:27, Alex Xie wrote:
>> In RCU read-side critical sections, blocking or sleeping is prohibited.
>>
>> Reported by: Dave Airlie
>>
>> [  141.965723] =============================
>> [  141.965724] WARNING: suspicious RCU usage
>> [  141.965726] 4.12.0-rc7 #221 Not tainted
>> [  141.965727] -----------------------------
>> [  141.965728] 
>> /home/airlied/devel/kernel/linux-2.6/include/linux/rcupdate.h:531
>> Illegal context switch in RCU read-side critical section!
>> [  141.965730]
>>                 other info that might help us debug this:
>>
>> [  141.965731]
>>                 rcu_scheduler_active = 2, debug_locks = 0
>> [  141.965732] 1 lock held by amdgpu_cs:0/1332:
>> [  141.965733]  #0:  (rcu_read_lock){......}, at: [<ffffffffa01a0d07>]
>> amdgpu_bo_list_get+0x0/0x109 [amdgpu]
>> [  141.965774]
>>                 stack backtrace:
>> [  141.965776] CPU: 6 PID: 1332 Comm: amdgpu_cs:0 Not tainted 
>> 4.12.0-rc7 #221
>> [  141.965777] Hardware name: To be filled by O.E.M. To be filled by
>> O.E.M./M5A97 R2.0, BIOS 2603 06/26/2015
>> [  141.965778] Call Trace:
>> [  141.965782]  dump_stack+0x68/0x92
>> [  141.965785]  lockdep_rcu_suspicious+0xf7/0x100
>> [  141.965788]  ___might_sleep+0x56/0x1fc
>> [  141.965790]  __might_sleep+0x68/0x6f
>> [  141.965793]  __mutex_lock+0x4e/0x7b5
>> [  141.965817]  ? amdgpu_bo_list_get+0xa4/0x109 [amdgpu]
>> [  141.965820]  ? lock_acquire+0x125/0x1b9
>> [  141.965844]  ? amdgpu_bo_list_set+0x464/0x464 [amdgpu]
>> [  141.965846]  mutex_lock_nested+0x16/0x18
>> [  141.965848]  ? mutex_lock_nested+0x16/0x18
>> [  141.965872]  amdgpu_bo_list_get+0xa4/0x109 [amdgpu]
>> [  141.965895]  amdgpu_cs_ioctl+0x4a0/0x17dd [amdgpu]
>> [  141.965898]  ? radix_tree_node_alloc.constprop.11+0x77/0xab
>> [  141.965916]  drm_ioctl+0x264/0x393 [drm]
>> [  141.965939]  ? amdgpu_cs_find_mapping+0x83/0x83 [amdgpu]
>> [  141.965942]  ? trace_hardirqs_on_caller+0x16a/0x186
>>
>> Signed-off-by: Alex Xie <AlexBin.Xie@amd.com>
>> ---
>>   drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c | 9 ++++++---
>>   1 file changed, 6 insertions(+), 3 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c 
>> b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
>> index dc87962..565ca90 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
>> @@ -198,12 +198,15 @@ amdgpu_bo_list_get(struct amdgpu_fpriv *fpriv, 
>> int id)
>>       result = idr_find(&fpriv->bo_list_handles, id);
>>         if (result) {
>> -        if (kref_get_unless_zero(&result->refcount))
>> +        if (kref_get_unless_zero(&result->refcount)) {
>> +            rcu_read_unlock();
>>               mutex_lock(&result->lock);
>> -        else
>> +        }
>> +        else {
>> +            rcu_read_unlock();
>>               result = NULL;
>> +        }
>>       }
>> -    rcu_read_unlock();
> how about result==NULL case? will lost rcu unlock, right?
>
> David Zhou
>>         return result;
>>   }
>
> _______________________________________________
> amd-gfx mailing list
> amd-gfx@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/amd-gfx
> -----Original Message-----

> From: amd-gfx [mailto:amd-gfx-bounces@lists.freedesktop.org] On Behalf

> Of Alex Xie

> Sent: Wednesday, July 19, 2017 10:28 PM

> To: amd-gfx@lists.freedesktop.org

> Cc: Xie, AlexBin

> Subject: [PATCH] drm/amdgpu: Fix error RCU usage

> 

> In RCU read-side critical sections, blocking or sleeping is prohibited.

> 

> Reported by: Dave Airlie

> 

> [  141.965723] =============================

> [  141.965724] WARNING: suspicious RCU usage

> [  141.965726] 4.12.0-rc7 #221 Not tainted

> [  141.965727] -----------------------------

> [  141.965728] /home/airlied/devel/kernel/linux-

> 2.6/include/linux/rcupdate.h:531

> Illegal context switch in RCU read-side critical section!

> [  141.965730]

>                other info that might help us debug this:

> 

> [  141.965731]

>                rcu_scheduler_active = 2, debug_locks = 0

> [  141.965732] 1 lock held by amdgpu_cs:0/1332:

> [  141.965733]  #0:  (rcu_read_lock){......}, at: [<ffffffffa01a0d07>]

> amdgpu_bo_list_get+0x0/0x109 [amdgpu]

> [  141.965774]

>                stack backtrace:

> [  141.965776] CPU: 6 PID: 1332 Comm: amdgpu_cs:0 Not tainted 4.12.0-rc7

> #221

> [  141.965777] Hardware name: To be filled by O.E.M. To be filled by

> O.E.M./M5A97 R2.0, BIOS 2603 06/26/2015

> [  141.965778] Call Trace:

> [  141.965782]  dump_stack+0x68/0x92

> [  141.965785]  lockdep_rcu_suspicious+0xf7/0x100

> [  141.965788]  ___might_sleep+0x56/0x1fc

> [  141.965790]  __might_sleep+0x68/0x6f

> [  141.965793]  __mutex_lock+0x4e/0x7b5

> [  141.965817]  ? amdgpu_bo_list_get+0xa4/0x109 [amdgpu]

> [  141.965820]  ? lock_acquire+0x125/0x1b9

> [  141.965844]  ? amdgpu_bo_list_set+0x464/0x464 [amdgpu]

> [  141.965846]  mutex_lock_nested+0x16/0x18

> [  141.965848]  ? mutex_lock_nested+0x16/0x18

> [  141.965872]  amdgpu_bo_list_get+0xa4/0x109 [amdgpu]

> [  141.965895]  amdgpu_cs_ioctl+0x4a0/0x17dd [amdgpu]

> [  141.965898]  ? radix_tree_node_alloc.constprop.11+0x77/0xab

> [  141.965916]  drm_ioctl+0x264/0x393 [drm]

> [  141.965939]  ? amdgpu_cs_find_mapping+0x83/0x83 [amdgpu]

> [  141.965942]  ? trace_hardirqs_on_caller+0x16a/0x186

> 

> Signed-off-by: Alex Xie <AlexBin.Xie@amd.com>

> ---

>  drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c | 9 ++++++---

>  1 file changed, 6 insertions(+), 3 deletions(-)

> 

> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c

> b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c

> index dc87962..565ca90 100644

> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c

> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c

> @@ -198,12 +198,15 @@ amdgpu_bo_list_get(struct amdgpu_fpriv *fpriv,

> int id)

>  	result = idr_find(&fpriv->bo_list_handles, id);

> 

>  	if (result) {

> -		if (kref_get_unless_zero(&result->refcount))

> +		if (kref_get_unless_zero(&result->refcount)) {

> +			rcu_read_unlock();

>  			mutex_lock(&result->lock);

> -		else

> +		}

> +		else {


Coding style,  open paren should be on same line as else.  E.g.,
} else {

Alex

> +			rcu_read_unlock();

>  			result = NULL;

> +		}

>  	}

> -	rcu_read_unlock();

> 

>  	return result;

>  }

> --

> 2.7.4

> 

> _______________________________________________

> amd-gfx mailing list

> amd-gfx@lists.freedesktop.org

> https://lists.freedesktop.org/mailman/listinfo/amd-gfx