Re: [RFC v2 03/13] dma-fence: Use a flag for 64-bit seqnos

[Tvrtko Ursulin <tvrtko.ursulin@igalia.com>]

On 12/05/2025 09:17, Christian König wrote:
> On 5/9/25 17:33, Tvrtko Ursulin wrote:
>> With the goal of reducing the need for drivers to touch (and dereference)
>> fence->ops, we move the 64-bit seqnos flag from struct dma_fence_ops to
>> the fence->flags.
>>
>> Drivers which were setting this flag are changed to use new
>> dma_fence_init64() instead of dma_fence_init().
>>
>> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
> 
> My idea was to copy the flag from the ops during init, but that should work as well.
> 
> Reviewed-by: Christian König <christian.koenig@amd.com>

Thanks!

One alternative to dma_fence_init64() I was thinking about is to perhaps 
have add dma_fence_init_flags(). Especially in the context of patch 4/13 
where it would then look cleaner for callers such as 
dma_fence_chain_init(). 4/13 aside, how would dma_fence_init_flags look 
to you? It is a little bit more verbose is one thing. And if we are not 
doing 4/13, verbosity coupled with a single benefit perhaps it is best 
to leave dma_fence_init64() as is?

Regards,

Tvrtko

>> ---
>>   drivers/dma-buf/dma-fence-chain.c                | 5 ++---
>>   drivers/dma-buf/dma-fence.c                      | 9 +++++++++
>>   drivers/gpu/drm/amd/amdgpu/amdgpu_vm_tlb_fence.c | 5 ++---
>>   include/linux/dma-fence.h                        | 6 +++++-
>>   4 files changed, 18 insertions(+), 7 deletions(-)
>>
>> diff --git a/drivers/dma-buf/dma-fence-chain.c b/drivers/dma-buf/dma-fence-chain.c
>> index 90424f23fd73..a8a90acf4f34 100644
>> --- a/drivers/dma-buf/dma-fence-chain.c
>> +++ b/drivers/dma-buf/dma-fence-chain.c
>> @@ -218,7 +218,6 @@ static void dma_fence_chain_set_deadline(struct dma_fence *fence,
>>   }
>>   
>>   const struct dma_fence_ops dma_fence_chain_ops = {
>> -	.use_64bit_seqno = true,
>>   	.get_driver_name = dma_fence_chain_get_driver_name,
>>   	.get_timeline_name = dma_fence_chain_get_timeline_name,
>>   	.enable_signaling = dma_fence_chain_enable_signaling,
>> @@ -262,8 +261,8 @@ void dma_fence_chain_init(struct dma_fence_chain *chain,
>>   			seqno = max(prev->seqno, seqno);
>>   	}
>>   
>> -	dma_fence_init(&chain->base, &dma_fence_chain_ops,
>> -		       &chain->lock, context, seqno);
>> +	dma_fence_init64(&chain->base, &dma_fence_chain_ops, &chain->lock,
>> +			 context, seqno);
>>   
>>   	/*
>>   	 * Chaining dma_fence_chain container together is only allowed through
>> diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c
>> index f0cdd3e99d36..33661658f684 100644
>> --- a/drivers/dma-buf/dma-fence.c
>> +++ b/drivers/dma-buf/dma-fence.c
>> @@ -1023,3 +1023,12 @@ dma_fence_init(struct dma_fence *fence, const struct dma_fence_ops *ops,
>>   	trace_dma_fence_init(fence);
>>   }
>>   EXPORT_SYMBOL(dma_fence_init);
>> +
>> +void
>> +dma_fence_init64(struct dma_fence *fence, const struct dma_fence_ops *ops,
>> +		 spinlock_t *lock, u64 context, u64 seqno)
>> +{
>> +	dma_fence_init(fence, ops, lock, context, seqno);
>> +	__set_bit(DMA_FENCE_FLAG_SEQNO64_BIT, &fence->flags);
>> +}
>> +EXPORT_SYMBOL(dma_fence_init64);
>> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_tlb_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_tlb_fence.c
>> index 51cddfa3f1e8..5d26797356a3 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_tlb_fence.c
>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_tlb_fence.c
>> @@ -71,7 +71,6 @@ static void amdgpu_tlb_fence_work(struct work_struct *work)
>>   }
>>   
>>   static const struct dma_fence_ops amdgpu_tlb_fence_ops = {
>> -	.use_64bit_seqno = true,
>>   	.get_driver_name = amdgpu_tlb_fence_get_driver_name,
>>   	.get_timeline_name = amdgpu_tlb_fence_get_timeline_name
>>   };
>> @@ -101,8 +100,8 @@ void amdgpu_vm_tlb_fence_create(struct amdgpu_device *adev, struct amdgpu_vm *vm
>>   	INIT_WORK(&f->work, amdgpu_tlb_fence_work);
>>   	spin_lock_init(&f->lock);
>>   
>> -	dma_fence_init(&f->base, &amdgpu_tlb_fence_ops, &f->lock,
>> -		       vm->tlb_fence_context, atomic64_read(&vm->tlb_seq));
>> +	dma_fence_init64(&f->base, &amdgpu_tlb_fence_ops, &f->lock,
>> +			 vm->tlb_fence_context, atomic64_read(&vm->tlb_seq));
>>   
>>   	/* TODO: We probably need a separate wq here */
>>   	dma_fence_get(&f->base);
>> diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h
>> index 48b5202c531d..ac6535716dbe 100644
>> --- a/include/linux/dma-fence.h
>> +++ b/include/linux/dma-fence.h
>> @@ -97,6 +97,7 @@ struct dma_fence {
>>   };
>>   
>>   enum dma_fence_flag_bits {
>> +	DMA_FENCE_FLAG_SEQNO64_BIT,
>>   	DMA_FENCE_FLAG_SIGNALED_BIT,
>>   	DMA_FENCE_FLAG_TIMESTAMP_BIT,
>>   	DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT,
>> @@ -262,6 +263,9 @@ struct dma_fence_ops {
>>   void dma_fence_init(struct dma_fence *fence, const struct dma_fence_ops *ops,
>>   		    spinlock_t *lock, u64 context, u64 seqno);
>>   
>> +void dma_fence_init64(struct dma_fence *fence, const struct dma_fence_ops *ops,
>> +		      spinlock_t *lock, u64 context, u64 seqno);
>> +
>>   void dma_fence_release(struct kref *kref);
>>   void dma_fence_free(struct dma_fence *fence);
>>   void dma_fence_describe(struct dma_fence *fence, struct seq_file *seq);
>> @@ -454,7 +458,7 @@ static inline bool __dma_fence_is_later(struct dma_fence *fence, u64 f1, u64 f2)
>>   	 * 32bit sequence numbers. Use a 64bit compare when the driver says to
>>   	 * do so.
>>   	 */
>> -	if (fence->ops->use_64bit_seqno)
>> +	if (test_bit(DMA_FENCE_FLAG_SEQNO64_BIT, &fence->flags))
>>   		return f1 > f2;
>>   
>>   	return (int)(lower_32_bits(f1) - lower_32_bits(f2)) > 0;
>