When no custom lock is set to protect a GEMs GPUVA list, lockdep checks
should fall back to the GEM objects dma-resv lock. With the current
implementation we're setting the lock_dep_map of the GEM objects 'resv'
pointer (in case no custom lock_dep_map is set yet) on
drm_gem_private_object_init().

However, the GEM objects 'resv' pointer might still change after
drm_gem_private_object_init() is called, e.g. through
ttm_bo_init_reserved(). This can result in the wrong lock being tracked.

To fix this, call dma_resv_held() directly from
drm_gem_gpuva_assert_lock_held() and fall back to the GEMs lock_dep_map
pointer only if an actual custom lock is set.

Fixes: e6303f323b1a ("drm: manager to keep track of GPUs VA mappings")
Signed-off-by: Danilo Krummrich <dakr@redhat.com>
---
 include/drm/drm_gem.h | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/include/drm/drm_gem.h b/include/drm/drm_gem.h
index c0b13c43b459..bc9f6aa2f3fe 100644
--- a/include/drm/drm_gem.h
+++ b/include/drm/drm_gem.h
@@ -551,15 +551,17 @@ int drm_gem_evict(struct drm_gem_object *obj);
  * @lock: the lock used to protect the gpuva list. The locking primitive
  * must contain a dep_map field.
  *
- * Call this if you're not proctecting access to the gpuva list
- * with the dma-resv lock, otherwise, drm_gem_gpuva_init() takes care
- * of initializing lock_dep_map for you.
+ * Call this if you're not proctecting access to the gpuva list with the
+ * dma-resv lock, but with a custom lock.
  */
 #define drm_gem_gpuva_set_lock(obj, lock) \
-	if (!(obj)->gpuva.lock_dep_map) \
+	if (!WARN((obj)->gpuva.lock_dep_map, \
+		  "GEM GPUVA lock should be set only once.")) \
 		(obj)->gpuva.lock_dep_map = &(lock)->dep_map
 #define drm_gem_gpuva_assert_lock_held(obj) \
-	lockdep_assert(lock_is_held((obj)->gpuva.lock_dep_map))
+	lockdep_assert((obj)->gpuva.lock_dep_map ? \
+		       lock_is_held((obj)->gpuva.lock_dep_map) : \
+		       dma_resv_held((obj)->resv))
 #else
 #define drm_gem_gpuva_set_lock(obj, lock) do {} while (0)
 #define drm_gem_gpuva_assert_lock_held(obj) do {} while (0)
@@ -573,11 +575,12 @@ int drm_gem_evict(struct drm_gem_object *obj);
  *
  * Calling this function is only necessary for drivers intending to support the
  * &drm_driver_feature DRIVER_GEM_GPUVA.
+ *
+ * See also drm_gem_gpuva_set_lock().
  */
 static inline void drm_gem_gpuva_init(struct drm_gem_object *obj)
 {
 	INIT_LIST_HEAD(&obj->gpuva.list);
-	drm_gem_gpuva_set_lock(obj, &obj->resv->lock.base);
 }
 
 /**
-- 
2.41.0

On Thu,  3 Aug 2023 18:52:20 +0200
Danilo Krummrich <dakr@redhat.com> wrote:

> When no custom lock is set to protect a GEMs GPUVA list, lockdep checks
> should fall back to the GEM objects dma-resv lock. With the current
> implementation we're setting the lock_dep_map of the GEM objects 'resv'
> pointer (in case no custom lock_dep_map is set yet) on
> drm_gem_private_object_init().
> 
> However, the GEM objects 'resv' pointer might still change after
> drm_gem_private_object_init() is called, e.g. through
> ttm_bo_init_reserved(). This can result in the wrong lock being tracked.
> 
> To fix this, call dma_resv_held() directly from
> drm_gem_gpuva_assert_lock_held() and fall back to the GEMs lock_dep_map
> pointer only if an actual custom lock is set.
> 
> Fixes: e6303f323b1a ("drm: manager to keep track of GPUs VA mappings")
> Signed-off-by: Danilo Krummrich <dakr@redhat.com>

Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>

but I'm wondering if it wouldn't be a good thing to add a
drm_gem_set_resv() helper, so the core can control drm_gem_object::resv
re-assignments (block them if it's happening after the GEM has been
exposed to the outside world or update auxiliary data if it's happening
before that).

> ---
>  include/drm/drm_gem.h | 15 +++++++++------
>  1 file changed, 9 insertions(+), 6 deletions(-)
> 
> diff --git a/include/drm/drm_gem.h b/include/drm/drm_gem.h
> index c0b13c43b459..bc9f6aa2f3fe 100644
> --- a/include/drm/drm_gem.h
> +++ b/include/drm/drm_gem.h
> @@ -551,15 +551,17 @@ int drm_gem_evict(struct drm_gem_object *obj);
>   * @lock: the lock used to protect the gpuva list. The locking primitive
>   * must contain a dep_map field.
>   *
> - * Call this if you're not proctecting access to the gpuva list
> - * with the dma-resv lock, otherwise, drm_gem_gpuva_init() takes care
> - * of initializing lock_dep_map for you.
> + * Call this if you're not proctecting access to the gpuva list with the
> + * dma-resv lock, but with a custom lock.
>   */
>  #define drm_gem_gpuva_set_lock(obj, lock) \
> -	if (!(obj)->gpuva.lock_dep_map) \
> +	if (!WARN((obj)->gpuva.lock_dep_map, \
> +		  "GEM GPUVA lock should be set only once.")) \
>  		(obj)->gpuva.lock_dep_map = &(lock)->dep_map
>  #define drm_gem_gpuva_assert_lock_held(obj) \
> -	lockdep_assert(lock_is_held((obj)->gpuva.lock_dep_map))
> +	lockdep_assert((obj)->gpuva.lock_dep_map ? \
> +		       lock_is_held((obj)->gpuva.lock_dep_map) : \
> +		       dma_resv_held((obj)->resv))
>  #else
>  #define drm_gem_gpuva_set_lock(obj, lock) do {} while (0)
>  #define drm_gem_gpuva_assert_lock_held(obj) do {} while (0)
> @@ -573,11 +575,12 @@ int drm_gem_evict(struct drm_gem_object *obj);
>   *
>   * Calling this function is only necessary for drivers intending to support the
>   * &drm_driver_feature DRIVER_GEM_GPUVA.
> + *
> + * See also drm_gem_gpuva_set_lock().
>   */
>  static inline void drm_gem_gpuva_init(struct drm_gem_object *obj)
>  {
>  	INIT_LIST_HEAD(&obj->gpuva.list);
> -	drm_gem_gpuva_set_lock(obj, &obj->resv->lock.base);
>  }
>  
>  /**

On 8/8/23 09:21, Boris Brezillon wrote:
> On Thu,  3 Aug 2023 18:52:20 +0200
> Danilo Krummrich <dakr@redhat.com> wrote:
> 
>> When no custom lock is set to protect a GEMs GPUVA list, lockdep checks
>> should fall back to the GEM objects dma-resv lock. With the current
>> implementation we're setting the lock_dep_map of the GEM objects 'resv'
>> pointer (in case no custom lock_dep_map is set yet) on
>> drm_gem_private_object_init().
>>
>> However, the GEM objects 'resv' pointer might still change after
>> drm_gem_private_object_init() is called, e.g. through
>> ttm_bo_init_reserved(). This can result in the wrong lock being tracked.
>>
>> To fix this, call dma_resv_held() directly from
>> drm_gem_gpuva_assert_lock_held() and fall back to the GEMs lock_dep_map
>> pointer only if an actual custom lock is set.
>>
>> Fixes: e6303f323b1a ("drm: manager to keep track of GPUs VA mappings")
>> Signed-off-by: Danilo Krummrich <dakr@redhat.com>
> 
> Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
> 
> but I'm wondering if it wouldn't be a good thing to add a
> drm_gem_set_resv() helper, so the core can control drm_gem_object::resv
> re-assignments (block them if it's happening after the GEM has been
> exposed to the outside world or update auxiliary data if it's happening
> before that).

I agree, this might be a good idea. There are quite a few places where 
drm_gem_object::resv is set from external code.

> 
>> ---
>>   include/drm/drm_gem.h | 15 +++++++++------
>>   1 file changed, 9 insertions(+), 6 deletions(-)
>>
>> diff --git a/include/drm/drm_gem.h b/include/drm/drm_gem.h
>> index c0b13c43b459..bc9f6aa2f3fe 100644
>> --- a/include/drm/drm_gem.h
>> +++ b/include/drm/drm_gem.h
>> @@ -551,15 +551,17 @@ int drm_gem_evict(struct drm_gem_object *obj);
>>    * @lock: the lock used to protect the gpuva list. The locking primitive
>>    * must contain a dep_map field.
>>    *
>> - * Call this if you're not proctecting access to the gpuva list
>> - * with the dma-resv lock, otherwise, drm_gem_gpuva_init() takes care
>> - * of initializing lock_dep_map for you.
>> + * Call this if you're not proctecting access to the gpuva list with the
>> + * dma-resv lock, but with a custom lock.
>>    */
>>   #define drm_gem_gpuva_set_lock(obj, lock) \
>> -	if (!(obj)->gpuva.lock_dep_map) \
>> +	if (!WARN((obj)->gpuva.lock_dep_map, \
>> +		  "GEM GPUVA lock should be set only once.")) \
>>   		(obj)->gpuva.lock_dep_map = &(lock)->dep_map
>>   #define drm_gem_gpuva_assert_lock_held(obj) \
>> -	lockdep_assert(lock_is_held((obj)->gpuva.lock_dep_map))
>> +	lockdep_assert((obj)->gpuva.lock_dep_map ? \
>> +		       lock_is_held((obj)->gpuva.lock_dep_map) : \
>> +		       dma_resv_held((obj)->resv))
>>   #else
>>   #define drm_gem_gpuva_set_lock(obj, lock) do {} while (0)
>>   #define drm_gem_gpuva_assert_lock_held(obj) do {} while (0)
>> @@ -573,11 +575,12 @@ int drm_gem_evict(struct drm_gem_object *obj);
>>    *
>>    * Calling this function is only necessary for drivers intending to support the
>>    * &drm_driver_feature DRIVER_GEM_GPUVA.
>> + *
>> + * See also drm_gem_gpuva_set_lock().
>>    */
>>   static inline void drm_gem_gpuva_init(struct drm_gem_object *obj)
>>   {
>>   	INIT_LIST_HEAD(&obj->gpuva.list);
>> -	drm_gem_gpuva_set_lock(obj, &obj->resv->lock.base);
>>   }
>>   
>>   /**
>