dma-fence: Use a flag for 64-bit seqnos

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().

v2:
 * Streamlined init and added kerneldoc.
 * Rebase for amdgpu userq which landed since.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Reviewed-by: Christian König <christian.koenig@amd.com> # v1
Signed-off-by: Tvrtko Ursulin <tursulin@ursulin.net>
Link: https://lore.kernel.org/r/20250515095004.28318-3-tvrtko.ursulin@igalia.com

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,
+	dma_fence_init64(&chain->base, &dma_fence_chain_ops, &chain->lock,
-		       &chain->lock, context, seqno);
+			 context, seqno);
 
 	/*
 	 * Chaining dma_fence_chain container together is only allowed through

drivers/dma-buf/dma-fence.c

@@ -989,6 +989,25 @@ void dma_fence_describe(struct dma_fence *fence, struct seq_file *seq)
 }
 EXPORT_SYMBOL(dma_fence_describe);
 
+static void
+__dma_fence_init(struct dma_fence *fence, const struct dma_fence_ops *ops,
+	         spinlock_t *lock, u64 context, u64 seqno, unsigned long flags)
+{
+	BUG_ON(!lock);
+	BUG_ON(!ops || !ops->get_driver_name || !ops->get_timeline_name);
+
+	kref_init(&fence->refcount);
+	fence->ops = ops;
+	INIT_LIST_HEAD(&fence->cb_list);
+	fence->lock = lock;
+	fence->context = context;
+	fence->seqno = seqno;
+	fence->flags = flags;
+	fence->error = 0;
+
+	trace_dma_fence_init(fence);
+}
+
 /**
  * dma_fence_init - Initialize a custom fence.
  * @fence: the fence to initialize
@@ -1008,18 +1027,30 @@ void
 dma_fence_init(struct dma_fence *fence, const struct dma_fence_ops *ops,
 	       spinlock_t *lock, u64 context, u64 seqno)
 {
-	BUG_ON(!lock);
+	__dma_fence_init(fence, ops, lock, context, seqno, 0UL);
-	BUG_ON(!ops || !ops->get_driver_name || !ops->get_timeline_name);
-
-	kref_init(&fence->refcount);
-	fence->ops = ops;
-	INIT_LIST_HEAD(&fence->cb_list);
-	fence->lock = lock;
-	fence->context = context;
-	fence->seqno = seqno;
-	fence->flags = 0UL;
-	fence->error = 0;
-
-	trace_dma_fence_init(fence);
 }
 EXPORT_SYMBOL(dma_fence_init);
+
+/**
+ * dma_fence_init64 - Initialize a custom fence with 64-bit seqno support.
+ * @fence: the fence to initialize
+ * @ops: the dma_fence_ops for operations on this fence
+ * @lock: the irqsafe spinlock to use for locking this fence
+ * @context: the execution context this fence is run on
+ * @seqno: a linear increasing sequence number for this context
+ *
+ * Initializes an allocated fence, the caller doesn't have to keep its
+ * refcount after committing with this fence, but it will need to hold a
+ * refcount again if &dma_fence_ops.enable_signaling gets called.
+ *
+ * Context and seqno are used for easy comparison between fences, allowing
+ * to check which fence is later by simply using dma_fence_later().
+ */
+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,
+			 BIT(DMA_FENCE_FLAG_SEQNO64_BIT));
+}
+EXPORT_SYMBOL(dma_fence_init64);

drivers/gpu/drm/amd/amdgpu/amdgpu_eviction_fence.c

@@ -134,7 +134,6 @@ static bool amdgpu_eviction_fence_enable_signaling(struct dma_fence *f)
 }
 
 static const struct dma_fence_ops amdgpu_eviction_fence_ops = {
-	.use_64bit_seqno = true,
 	.get_driver_name = amdgpu_eviction_fence_get_driver_name,
 	.get_timeline_name = amdgpu_eviction_fence_get_timeline_name,
 	.enable_signaling = amdgpu_eviction_fence_enable_signaling,
@@ -160,9 +159,9 @@ amdgpu_eviction_fence_create(struct amdgpu_eviction_fence_mgr *evf_mgr)
 	ev_fence->evf_mgr = evf_mgr;
 	get_task_comm(ev_fence->timeline_name, current);
 	spin_lock_init(&ev_fence->lock);
-	dma_fence_init(&ev_fence->base, &amdgpu_eviction_fence_ops,
+	dma_fence_init64(&ev_fence->base, &amdgpu_eviction_fence_ops,
-		       &ev_fence->lock, evf_mgr->ev_fence_ctx,
+			 &ev_fence->lock, evf_mgr->ev_fence_ctx,
-		       atomic_inc_return(&evf_mgr->ev_fence_seq));
+			 atomic_inc_return(&evf_mgr->ev_fence_seq));
 	return ev_fence;
 }
 

drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c

@@ -239,8 +239,8 @@ static int amdgpu_userq_fence_create(struct amdgpu_usermode_queue *userq,
 	fence = &userq_fence->base;
 	userq_fence->fence_drv = fence_drv;
 
-	dma_fence_init(fence, &amdgpu_userq_fence_ops, &userq_fence->lock,
+	dma_fence_init64(fence, &amdgpu_userq_fence_ops, &userq_fence->lock,
-		       fence_drv->context, seq);
+			 fence_drv->context, seq);
 
 	amdgpu_userq_fence_driver_get(fence_drv);
 	dma_fence_get(fence);
@@ -334,7 +334,6 @@ static void amdgpu_userq_fence_release(struct dma_fence *f)
 }
 
 static const struct dma_fence_ops amdgpu_userq_fence_ops = {
-	.use_64bit_seqno = true,
 	.get_driver_name = amdgpu_userq_fence_get_driver_name,
 	.get_timeline_name = amdgpu_userq_fence_get_timeline_name,
 	.signaled = amdgpu_userq_fence_signaled,

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,
+	dma_fence_init64(&f->base, &amdgpu_tlb_fence_ops, &f->lock,
-		       vm->tlb_fence_context, atomic64_read(&vm->tlb_seq));
+			 vm->tlb_fence_context, atomic64_read(&vm->tlb_seq));
 
 	/* TODO: We probably need a separate wq here */
 	dma_fence_get(&f->base);

include/linux/dma-fence.h

@@ -98,6 +98,7 @@ 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,
@@ -125,14 +126,6 @@ struct dma_fence_cb {
  *
  */
 struct dma_fence_ops {
-	/**
-	 * @use_64bit_seqno:
-	 *
-	 * True if this dma_fence implementation uses 64bit seqno, false
-	 * otherwise.
-	 */
-	bool use_64bit_seqno;
-
 	/**
 	 * @get_driver_name:
 	 *
@@ -263,6 +256,9 @@ 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);
@@ -455,7 +451,7 @@ 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;