1 files changed, 57 insertions, 99 deletions

diff --git a/drivers/gpu/drm/panthor/panthor_mmu.c b/drivers/gpu/drm/panthor/panthor_mmu.c
index 6dec4354e378..d4839d282689 100644
--- a/drivers/gpu/drm/panthor/panthor_mmu.c
+++ b/drivers/gpu/drm/panthor/panthor_mmu.c
@@ -7,6 +7,7 @@
 #include <drm/drm_exec.h>
 #include <drm/drm_gpuvm.h>
 #include <drm/drm_managed.h>
+#include <drm/drm_print.h>
 #include <drm/gpu_scheduler.h>
 #include <drm/panthor_drm.h>
 
@@ -181,20 +182,6 @@ struct panthor_vm_op_ctx {
 		u64 range;
 	} va;
 
-	/**
-	 * @returned_vmas: List of panthor_vma objects returned after a VM operation.
-	 *
-	 * For unmap operations, this will contain all VMAs that were covered by the
-	 * specified VA range.
-	 *
-	 * For map operations, this will contain all VMAs that previously mapped to
-	 * the specified VA range.
-	 *
-	 * Those VMAs, and the resources they point to will be released as part of
-	 * the op_ctx cleanup operation.
-	 */
-	struct list_head returned_vmas;
-
 	/** @map: Fields specific to a map operation. */
 	struct {
 		/** @map.vm_bo: Buffer object to map. */
@@ -917,10 +904,9 @@ static int panthor_vm_unmap_pages(struct panthor_vm *vm, u64 iova, u64 size)
 {
 	struct panthor_device *ptdev = vm->ptdev;
 	struct io_pgtable_ops *ops = vm->pgtbl_ops;
+	u64 start_iova = iova;
 	u64 offset = 0;
 
-	drm_dbg(&ptdev->base, "unmap: as=%d, iova=%llx, len=%llx", vm->as.id, iova, size);
-
 	while (offset < size) {
 		size_t unmapped_sz = 0, pgcount;
 		size_t pgsize = get_pgsize(iova + offset, size - offset, &pgcount);
@@ -935,6 +921,12 @@ static int panthor_vm_unmap_pages(struct panthor_vm *vm, u64 iova, u64 size)
 			panthor_vm_flush_range(vm, iova, offset + unmapped_sz);
 			return  -EINVAL;
 		}
+
+		drm_dbg(&ptdev->base,
+			"unmap: as=%d, iova=0x%llx, sz=%llu, va=0x%llx, pgcnt=%zu, pgsz=%zu",
+			vm->as.id, start_iova, size, iova + offset,
+			unmapped_sz / pgsize, pgsize);
+
 		offset += unmapped_sz;
 	}
 
@@ -950,6 +942,7 @@ panthor_vm_map_pages(struct panthor_vm *vm, u64 iova, int prot,
 	struct scatterlist *sgl;
 	struct io_pgtable_ops *ops = vm->pgtbl_ops;
 	u64 start_iova = iova;
+	u64 start_size = size;
 	int ret;
 
 	if (!size)
@@ -969,15 +962,18 @@ panthor_vm_map_pages(struct panthor_vm *vm, u64 iova, int prot,
 		len = min_t(size_t, len, size);
 		size -= len;
 
-		drm_dbg(&ptdev->base, "map: as=%d, iova=%llx, paddr=%pad, len=%zx",
-			vm->as.id, iova, &paddr, len);
-
 		while (len) {
 			size_t pgcount, mapped = 0;
 			size_t pgsize = get_pgsize(iova | paddr, len, &pgcount);
 
 			ret = ops->map_pages(ops, iova, paddr, pgsize, pgcount, prot,
 					     GFP_KERNEL, &mapped);
+
+			drm_dbg(&ptdev->base,
+				"map: as=%d, iova=0x%llx, sz=%llu, va=0x%llx, pa=%pad, pgcnt=%zu, pgsz=%zu",
+				vm->as.id, start_iova, start_size, iova, &paddr,
+				mapped / pgsize, pgsize);
+
 			iova += mapped;
 			paddr += mapped;
 			len -= mapped;
@@ -1081,47 +1077,18 @@ void panthor_vm_free_va(struct panthor_vm *vm, struct drm_mm_node *va_node)
 	mutex_unlock(&vm->mm_lock);
 }
 
-static void panthor_vm_bo_put(struct drm_gpuvm_bo *vm_bo)
+static void panthor_vm_bo_free(struct drm_gpuvm_bo *vm_bo)
 {
 	struct panthor_gem_object *bo = to_panthor_bo(vm_bo->obj);
-	struct drm_gpuvm *vm = vm_bo->vm;
-	bool unpin;
 
-	/* We must retain the GEM before calling drm_gpuvm_bo_put(),
-	 * otherwise the mutex might be destroyed while we hold it.
-	 * Same goes for the VM, since we take the VM resv lock.
-	 */
-	drm_gem_object_get(&bo->base.base);
-	drm_gpuvm_get(vm);
-
-	/* We take the resv lock to protect against concurrent accesses to the
-	 * gpuvm evicted/extobj lists that are modified in
-	 * drm_gpuvm_bo_destroy(), which is called if drm_gpuvm_bo_put()
-	 * releases sthe last vm_bo reference.
-	 * We take the BO GPUVA list lock to protect the vm_bo removal from the
-	 * GEM vm_bo list.
-	 */
-	dma_resv_lock(drm_gpuvm_resv(vm), NULL);
-	mutex_lock(&bo->base.base.gpuva.lock);
-	unpin = drm_gpuvm_bo_put(vm_bo);
-	mutex_unlock(&bo->base.base.gpuva.lock);
-	dma_resv_unlock(drm_gpuvm_resv(vm));
-
-	/* If the vm_bo object was destroyed, release the pin reference that
-	 * was hold by this object.
-	 */
-	if (unpin && !drm_gem_is_imported(&bo->base.base))
+	if (!drm_gem_is_imported(&bo->base.base))
 		drm_gem_shmem_unpin(&bo->base);
-
-	drm_gpuvm_put(vm);
-	drm_gem_object_put(&bo->base.base);
+	kfree(vm_bo);
 }
 
 static void panthor_vm_cleanup_op_ctx(struct panthor_vm_op_ctx *op_ctx,
 				      struct panthor_vm *vm)
 {
-	struct panthor_vma *vma, *tmp_vma;
-
 	u32 remaining_pt_count = op_ctx->rsvd_page_tables.count -
 				 op_ctx->rsvd_page_tables.ptr;
 
@@ -1134,16 +1101,26 @@ static void panthor_vm_cleanup_op_ctx(struct panthor_vm_op_ctx *op_ctx,
 	kfree(op_ctx->rsvd_page_tables.pages);
 
 	if (op_ctx->map.vm_bo)
-		panthor_vm_bo_put(op_ctx->map.vm_bo);
+		drm_gpuvm_bo_put_deferred(op_ctx->map.vm_bo);
 
 	for (u32 i = 0; i < ARRAY_SIZE(op_ctx->preallocated_vmas); i++)
 		kfree(op_ctx->preallocated_vmas[i]);
 
-	list_for_each_entry_safe(vma, tmp_vma, &op_ctx->returned_vmas, node) {
-		list_del(&vma->node);
-		panthor_vm_bo_put(vma->base.vm_bo);
-		kfree(vma);
+	drm_gpuvm_bo_deferred_cleanup(&vm->base);
+}
+
+static void
+panthor_vm_op_ctx_return_vma(struct panthor_vm_op_ctx *op_ctx,
+			     struct panthor_vma *vma)
+{
+	for (u32 i = 0; i < ARRAY_SIZE(op_ctx->preallocated_vmas); i++) {
+		if (!op_ctx->preallocated_vmas[i]) {
+			op_ctx->preallocated_vmas[i] = vma;
+			return;
+		}
 	}
+
+	WARN_ON_ONCE(1);
 }
 
 static struct panthor_vma *
@@ -1175,10 +1152,14 @@ panthor_vm_op_ctx_prealloc_vmas(struct panthor_vm_op_ctx *op_ctx)
 		break;
 
 	case DRM_PANTHOR_VM_BIND_OP_TYPE_UNMAP:
-		/* Partial unmaps might trigger a remap with either a prev or a next VA,
-		 * but not both.
+		/* Two VMAs can be needed for an unmap, as an unmap can happen
+		 * in the middle of a drm_gpuva, requiring a remap with both
+		 * prev & next VA. Or an unmap can span more than one drm_gpuva
+		 * where the first and last ones are covered partially, requring
+		 * a remap for the first with a prev VA and remap for the last
+		 * with a next VA.
 		 */
-		vma_count = 1;
+		vma_count = 2;
 		break;
 
 	default:
@@ -1232,7 +1213,6 @@ static int panthor_vm_prepare_map_op_ctx(struct panthor_vm_op_ctx *op_ctx,
 		return -EINVAL;
 
 	memset(op_ctx, 0, sizeof(*op_ctx));
-	INIT_LIST_HEAD(&op_ctx->returned_vmas);
 	op_ctx->flags = flags;
 	op_ctx->va.range = size;
 	op_ctx->va.addr = va;
@@ -1243,7 +1223,9 @@ static int panthor_vm_prepare_map_op_ctx(struct panthor_vm_op_ctx *op_ctx,
 
 	if (!drm_gem_is_imported(&bo->base.base)) {
 		/* Pre-reserve the BO pages, so the map operation doesn't have to
-		 * allocate.
+		 * allocate. This pin is dropped in panthor_vm_bo_free(), so
+		 * once we have successfully called drm_gpuvm_bo_create(),
+		 * GPUVM will take care of dropping the pin for us.
 		 */
 		ret = drm_gem_shmem_pin(&bo->base);
 		if (ret)
@@ -1282,16 +1264,6 @@ static int panthor_vm_prepare_map_op_ctx(struct panthor_vm_op_ctx *op_ctx,
 	mutex_unlock(&bo->base.base.gpuva.lock);
 	dma_resv_unlock(panthor_vm_resv(vm));
 
-	/* If the a vm_bo for this <VM,BO> combination exists, it already
-	 * retains a pin ref, and we can release the one we took earlier.
-	 *
-	 * If our pre-allocated vm_bo is picked, it now retains the pin ref,
-	 * which will be released in panthor_vm_bo_put().
-	 */
-	if (preallocated_vm_bo != op_ctx->map.vm_bo &&
-	    !drm_gem_is_imported(&bo->base.base))
-		drm_gem_shmem_unpin(&bo->base);
-
 	op_ctx->map.bo_offset = offset;
 
 	/* L1, L2 and L3 page tables.
@@ -1339,7 +1311,6 @@ static int panthor_vm_prepare_unmap_op_ctx(struct panthor_vm_op_ctx *op_ctx,
 	int ret;
 
 	memset(op_ctx, 0, sizeof(*op_ctx));
-	INIT_LIST_HEAD(&op_ctx->returned_vmas);
 	op_ctx->va.range = size;
 	op_ctx->va.addr = va;
 	op_ctx->flags = DRM_PANTHOR_VM_BIND_OP_TYPE_UNMAP;
@@ -1387,7 +1358,6 @@ static void panthor_vm_prepare_sync_only_op_ctx(struct panthor_vm_op_ctx *op_ctx
 						struct panthor_vm *vm)
 {
 	memset(op_ctx, 0, sizeof(*op_ctx));
-	INIT_LIST_HEAD(&op_ctx->returned_vmas);
 	op_ctx->flags = DRM_PANTHOR_VM_BIND_OP_TYPE_SYNC_ONLY;
 }
 
@@ -2033,26 +2003,13 @@ static void panthor_vma_link(struct panthor_vm *vm,
 
 	mutex_lock(&bo->base.base.gpuva.lock);
 	drm_gpuva_link(&vma->base, vm_bo);
-	drm_WARN_ON(&vm->ptdev->base, drm_gpuvm_bo_put(vm_bo));
 	mutex_unlock(&bo->base.base.gpuva.lock);
 }
 
-static void panthor_vma_unlink(struct panthor_vm *vm,
-			       struct panthor_vma *vma)
+static void panthor_vma_unlink(struct panthor_vma *vma)
 {
-	struct panthor_gem_object *bo = to_panthor_bo(vma->base.gem.obj);
-	struct drm_gpuvm_bo *vm_bo = drm_gpuvm_bo_get(vma->base.vm_bo);
-
-	mutex_lock(&bo->base.base.gpuva.lock);
-	drm_gpuva_unlink(&vma->base);
-	mutex_unlock(&bo->base.base.gpuva.lock);
-
-	/* drm_gpuva_unlink() release the vm_bo, but we manually retained it
-	 * when entering this function, so we can implement deferred VMA
-	 * destruction. Re-assign it here.
-	 */
-	vma->base.vm_bo = vm_bo;
-	list_add_tail(&vma->node, &vm->op_ctx->returned_vmas);
+	drm_gpuva_unlink_defer(&vma->base);
+	kfree(vma);
 }
 
 static void panthor_vma_init(struct panthor_vma *vma, u32 flags)
@@ -2081,15 +2038,17 @@ static int panthor_gpuva_sm_step_map(struct drm_gpuva_op *op, void *priv)
 	ret = panthor_vm_map_pages(vm, op->map.va.addr, flags_to_prot(vma->flags),
 				   op_ctx->map.sgt, op->map.gem.offset,
 				   op->map.va.range);
-	if (ret)
+	if (ret) {
+		panthor_vm_op_ctx_return_vma(op_ctx, vma);
 		return ret;
+	}
 
-	/* Ref owned by the mapping now, clear the obj field so we don't release the
-	 * pinning/obj ref behind GPUVA's back.
-	 */
 	drm_gpuva_map(&vm->base, &vma->base, &op->map);
 	panthor_vma_link(vm, vma, op_ctx->map.vm_bo);
+
+	drm_gpuvm_bo_put_deferred(op_ctx->map.vm_bo);
 	op_ctx->map.vm_bo = NULL;
+
 	return 0;
 }
 
@@ -2128,16 +2087,14 @@ static int panthor_gpuva_sm_step_remap(struct drm_gpuva_op *op,
 		 * owned by the old mapping which will be released when this
 		 * mapping is destroyed, we need to grab a ref here.
 		 */
-		panthor_vma_link(vm, prev_vma,
-				 drm_gpuvm_bo_get(op->remap.unmap->va->vm_bo));
+		panthor_vma_link(vm, prev_vma, op->remap.unmap->va->vm_bo);
 	}
 
 	if (next_vma) {
-		panthor_vma_link(vm, next_vma,
-				 drm_gpuvm_bo_get(op->remap.unmap->va->vm_bo));
+		panthor_vma_link(vm, next_vma, op->remap.unmap->va->vm_bo);
 	}
 
-	panthor_vma_unlink(vm, unmap_vma);
+	panthor_vma_unlink(unmap_vma);
 	return 0;
 }
 
@@ -2154,12 +2111,13 @@ static int panthor_gpuva_sm_step_unmap(struct drm_gpuva_op *op,
 		return ret;
 
 	drm_gpuva_unmap(&op->unmap);
-	panthor_vma_unlink(vm, unmap_vma);
+	panthor_vma_unlink(unmap_vma);
 	return 0;
 }
 
 static const struct drm_gpuvm_ops panthor_gpuvm_ops = {
 	.vm_free = panthor_vm_free,
+	.vm_bo_free = panthor_vm_bo_free,
 	.sm_step_map = panthor_gpuva_sm_step_map,
 	.sm_step_remap = panthor_gpuva_sm_step_remap,
 	.sm_step_unmap = panthor_gpuva_sm_step_unmap,