dma-buf & drm/amdgpu: remove dma_resv workaround

Rework the internals of the dma_resv object to allow adding more than one
write fence and remember for each fence what purpose it had.

This allows removing the workaround from amdgpu which used a container for
this instead.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: amd-gfx@lists.freedesktop.org
Link: https://patchwork.freedesktop.org/patch/msgid/20220407085946.744568-4-christian.koenig@amd.com

drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h

@@ -34,7 +34,6 @@ struct amdgpu_fpriv;
 struct amdgpu_bo_list_entry {
 	struct ttm_validate_buffer	tv;
 	struct amdgpu_bo_va		*bo_va;
-	struct dma_fence_chain		*chain;
 	uint32_t			priority;
 	struct page			**user_pages;
 	bool				user_invalidated;

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

@@ -574,14 +574,6 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 		struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo);
 
 		e->bo_va = amdgpu_vm_bo_find(vm, bo);
-
-		if (bo->tbo.base.dma_buf && !amdgpu_bo_explicit_sync(bo)) {
-			e->chain = dma_fence_chain_alloc();
-			if (!e->chain) {
-				r = -ENOMEM;
-				goto error_validate;
-			}
-		}
 	}
 
 	/* Move fence waiting after getting reservation lock of
@@ -642,13 +634,8 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 	}
 
 error_validate:
-	if (r) {
-		amdgpu_bo_list_for_each_entry(e, p->bo_list) {
-			dma_fence_chain_free(e->chain);
-			e->chain = NULL;
-		}
+	if (r)
 		ttm_eu_backoff_reservation(&p->ticket, &p->validated);
-	}
 out:
 	return r;
 }
@@ -688,17 +675,9 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error,
 {
 	unsigned i;
 
-	if (error && backoff) {
-		struct amdgpu_bo_list_entry *e;
-
-		amdgpu_bo_list_for_each_entry(e, parser->bo_list) {
-			dma_fence_chain_free(e->chain);
-			e->chain = NULL;
-		}
-
+	if (error && backoff)
 		ttm_eu_backoff_reservation(&parser->ticket,
 					   &parser->validated);
-	}
 
 	for (i = 0; i < parser->num_post_deps; i++) {
 		drm_syncobj_put(parser->post_deps[i].syncobj);
@@ -1272,31 +1251,9 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 
 	amdgpu_vm_move_to_lru_tail(p->adev, &fpriv->vm);
 
-	amdgpu_bo_list_for_each_entry(e, p->bo_list) {
-		struct dma_resv *resv = e->tv.bo->base.resv;
-		struct dma_fence_chain *chain = e->chain;
-		struct dma_resv_iter cursor;
-		struct dma_fence *fence;
-
-		if (!chain)
-			continue;
-
-		/*
-		 * Temporary workaround dma_resv shortcommings by wrapping up
-		 * the submission in a dma_fence_chain and add it as exclusive
-		 * fence.
-		 *
-		 * TODO: Remove together with dma_resv rework.
-		 */
-		dma_resv_for_each_fence(&cursor, resv,
-					DMA_RESV_USAGE_WRITE,
-					fence) {
-			break;
-		}
-		dma_fence_chain_init(chain, fence, dma_fence_get(p->fence), 1);
-		rcu_assign_pointer(resv->fence_excl, &chain->base);
-		e->chain = NULL;
-	}
+	/* Make sure all BOs are remembered as writers */
+	amdgpu_bo_list_for_each_entry(e, p->bo_list)
+		e->tv.num_shared = 0;
 
 	ttm_eu_fence_buffer_objects(&p->ticket, &p->validated, p->fence);
 	mutex_unlock(&p->adev->notifier_lock);

include/linux/dma-resv.h

@@ -99,8 +99,8 @@ static inline enum dma_resv_usage dma_resv_usage_rw(bool write)
 /**
  * struct dma_resv - a reservation object manages fences for a buffer
  *
- * There are multiple uses for this, with sometimes slightly different rules in
- * how the fence slots are used.
+ * This is a container for dma_fence objects which needs to handle multiple use
+ * cases.
  *
  * One use is to synchronize cross-driver access to a struct dma_buf, either for
  * dynamic buffer management or just to handle implicit synchronization between
@@ -130,47 +130,22 @@ struct dma_resv {
 	 * @seq:
 	 *
 	 * Sequence count for managing RCU read-side synchronization, allows
-	 * read-only access to @fence_excl and @fence while ensuring we take a
-	 * consistent snapshot.
+	 * read-only access to @fences while ensuring we take a consistent
+	 * snapshot.
 	 */
 	seqcount_ww_mutex_t seq;
 
 	/**
-	 * @fence_excl:
+	 * @fences:
 	 *
-	 * The exclusive fence, if there is one currently.
+	 * Array of fences which where added to the dma_resv object
 	 *
-	 * To guarantee that no fences are lost, this new fence must signal
-	 * only after the previous exclusive fence has signalled. If
-	 * semantically only a new access is added without actually treating the
-	 * previous one as a dependency the exclusive fences can be strung
-	 * together using struct dma_fence_chain.
-	 *
-	 * Note that actual semantics of what an exclusive or shared fence mean
-	 * is defined by the user, for reservation objects shared across drivers
-	 * see &dma_buf.resv.
-	 */
-	struct dma_fence __rcu *fence_excl;
-
-	/**
-	 * @fence:
-	 *
-	 * List of current shared fences.
-	 *
-	 * There are no ordering constraints of shared fences against the
-	 * exclusive fence slot. If a waiter needs to wait for all access, it
-	 * has to wait for both sets of fences to signal.
-	 *
-	 * A new fence is added by calling dma_resv_add_shared_fence(). Since
-	 * this often needs to be done past the point of no return in command
+	 * A new fence is added by calling dma_resv_add_fence(). Since this
+	 * often needs to be done past the point of no return in command
 	 * submission it cannot fail, and therefore sufficient slots need to be
 	 * reserved by calling dma_resv_reserve_fences().
-	 *
-	 * Note that actual semantics of what an exclusive or shared fence mean
-	 * is defined by the user, for reservation objects shared across drivers
-	 * see &dma_buf.resv.
 	 */
-	struct dma_resv_list __rcu *fence;
+	struct dma_resv_list __rcu *fences;
 };
 
 /**
@@ -207,8 +182,8 @@ struct dma_resv_iter {
 	/** @fences: the shared fences; private, *MUST* not dereference  */
 	struct dma_resv_list *fences;
 
-	/** @shared_count: number of shared fences */
-	unsigned int shared_count;
+	/** @num_fences: number of fences */
+	unsigned int num_fences;
 
 	/** @is_restarted: true if this is the first returned fence */
 	bool is_restarted;