[PATCH 1/2] drm/imagination: Switch the GPUVM to immediate mode

[Gyeyoung Baek <gye976@gmail.com>]

Use DRM_GPUVM_IMMEDIATE_MODE so that each GEM's GPUVA list is protected
by its gpuva.lock instead of its dma_resv. This prepares for
asynchronous VM_BIND, whose run_job() will update the GPUVA lists
before signalling its fence. That section imposes three rules:

1. No dma_resv: another thread may hold it while waiting for the job's
   fence, directly or through a dependency.
   -> Protect the lists with gpuva.lock, and take it around
      drm_gpuva_link().

2. No allocation under a lock run_job() takes: reclaim may wait for a
   fence that depends on the job.
   -> Allocate the vm_bo before taking gpuva.lock:
      drm_gpuvm_bo_obtain_locked() becomes drm_gpuvm_bo_create() +
      drm_gpuvm_bo_obtain_prealloc().

3. No freeing of GEM objects: that takes their dma_resv, and under
   gpuva.lock would free the held lock too.
   -> Defer it: drm_gpuva_unlink() and drm_gpuvm_bo_put() become
      drm_gpuva_unlink_defer() and drm_gpuvm_bo_put_deferred(), and
      drm_gpuvm_bo_deferred_cleanup() frees once the locks are dropped.

This also fixes an unlocked GPUVA list update: when a map fails,
pvr_vm_bind_op_fini() drops the last vm_bo reference without holding
the object's dma_resv.

Failing VM_MAP allocations with fail-nth shows
it on a lockdep kernel (real allocation failures under memory pressure
take the same path):

  WARNING: drivers/gpu/drm/drm_gpuvm.c:1661 at drm_gpuvm_bo_put+0x2ec/0x660 [drm_gpuvm]
  Call trace:
   drm_gpuvm_bo_put
   pvr_vm_bind_op_fini
   pvr_vm_map
   pvr_ioctl_vm_map

Fixes: ff5f643de0bf ("drm/imagination: Add GEM and VM related code")
Signed-off-by: Gyeyoung Baek <gye976@gmail.com>
---
 drivers/gpu/drm/imagination/pvr_vm.c | 37 +++++++++++++++++++++++++++---------
 1 file changed, 28 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/imagination/pvr_vm.c b/drivers/gpu/drm/imagination/pvr_vm.c
index cbdd15ed74f..3921b765688 100644
--- a/drivers/gpu/drm/imagination/pvr_vm.c
+++ b/drivers/gpu/drm/imagination/pvr_vm.c
@@ -214,7 +214,7 @@ static int pvr_vm_bind_op_exec(struct pvr_vm_bind_op *bind_op)
 
 static void pvr_vm_bind_op_fini(struct pvr_vm_bind_op *bind_op)
 {
-	drm_gpuvm_bo_put(bind_op->gpuvm_bo);
+	drm_gpuvm_bo_put_deferred(bind_op->gpuvm_bo);
 
 	kfree(bind_op->new_va);
 	kfree(bind_op->prev_va);
@@ -255,11 +255,11 @@ pvr_vm_bind_op_map_init(struct pvr_vm_bind_op *bind_op,
 
 	bind_op->type = PVR_VM_BIND_TYPE_MAP;
 
-	dma_resv_lock(obj->resv, NULL);
-	bind_op->gpuvm_bo = drm_gpuvm_bo_obtain_locked(&vm_ctx->gpuvm_mgr, obj);
-	dma_resv_unlock(obj->resv);
-	if (IS_ERR(bind_op->gpuvm_bo))
-		return PTR_ERR(bind_op->gpuvm_bo);
+	bind_op->gpuvm_bo = drm_gpuvm_bo_create(&vm_ctx->gpuvm_mgr, obj);
+	if (!bind_op->gpuvm_bo)
+		return -ENOMEM;
+
+	bind_op->gpuvm_bo = drm_gpuvm_bo_obtain_prealloc(bind_op->gpuvm_bo);
 
 	bind_op->new_va = kzalloc_obj(*bind_op->new_va);
 	bind_op->prev_va = kzalloc_obj(*bind_op->prev_va);
@@ -366,7 +366,11 @@ pvr_vm_gpuva_map(struct drm_gpuva_op *op, void *op_ctx)
 		return err;
 
 	drm_gpuva_map(&ctx->vm_ctx->gpuvm_mgr, &ctx->new_va->base, &op->map);
+
+	mutex_lock(&op->map.gem.obj->gpuva.lock);
 	drm_gpuva_link(&ctx->new_va->base, ctx->gpuvm_bo);
+	mutex_unlock(&op->map.gem.obj->gpuva.lock);
+
 	ctx->new_va = NULL;
 
 	return 0;
@@ -396,7 +400,7 @@ pvr_vm_gpuva_unmap(struct drm_gpuva_op *op, void *op_ctx)
 		return err;
 
 	drm_gpuva_unmap(&op->unmap);
-	drm_gpuva_unlink(op->unmap.va);
+	drm_gpuva_unlink_defer(op->unmap.va);
 	kfree(to_pvr_vm_gpuva(op->unmap.va));
 
 	return 0;
@@ -418,6 +422,7 @@ pvr_vm_gpuva_unmap(struct drm_gpuva_op *op, void *op_ctx)
 static int
 pvr_vm_gpuva_remap(struct drm_gpuva_op *op, void *op_ctx)
 {
+	struct drm_gem_object *obj = op->remap.unmap->va->gem.obj;
 	/* The split parts belong to the object of the mapping being split. */
 	struct drm_gpuvm_bo *vm_bo = op->remap.unmap->va->vm_bo;
 	struct pvr_vm_bind_op *ctx = op_ctx;
@@ -435,16 +440,20 @@ pvr_vm_gpuva_remap(struct drm_gpuva_op *op, void *op_ctx)
 	drm_gpuva_remap(&ctx->prev_va->base, &ctx->next_va->base, &op->remap);
 
 	if (op->remap.prev) {
+		mutex_lock(&obj->gpuva.lock);
 		drm_gpuva_link(&ctx->prev_va->base, vm_bo);
+		mutex_unlock(&obj->gpuva.lock);
 		ctx->prev_va = NULL;
 	}
 
 	if (op->remap.next) {
+		mutex_lock(&obj->gpuva.lock);
 		drm_gpuva_link(&ctx->next_va->base, vm_bo);
+		mutex_unlock(&obj->gpuva.lock);
 		ctx->next_va = NULL;
 	}
 
-	drm_gpuva_unlink(op->remap.unmap->va);
+	drm_gpuva_unlink_defer(op->remap.unmap->va);
 	kfree(to_pvr_vm_gpuva(op->remap.unmap->va));
 
 	return 0;
@@ -588,7 +597,8 @@ pvr_vm_create_context(struct pvr_device *pvr_dev, bool is_userspace_context)
 	drm_gem_private_object_init(&pvr_dev->base, &vm_ctx->dummy_gem, 0);
 	drm_gpuvm_init(&vm_ctx->gpuvm_mgr,
 		       is_userspace_context ? "PowerVR-user-VM" : "PowerVR-FW-VM",
-		       0, &pvr_dev->base, &vm_ctx->dummy_gem,
+		       DRM_GPUVM_IMMEDIATE_MODE, &pvr_dev->base,
+		       &vm_ctx->dummy_gem,
 		       0, 1ULL << device_addr_bits, 0, 0, &pvr_vm_gpuva_ops);
 
 	mutex_init(&vm_ctx->lock);
@@ -622,6 +632,7 @@ pvr_vm_context_release(struct kref *ref_count)
 		pvr_fw_object_destroy(vm_ctx->fw_mem_ctx_obj);
 
 	pvr_vm_unmap_all(vm_ctx);
+	drm_gpuvm_bo_deferred_cleanup(&vm_ctx->gpuvm_mgr);
 
 	pvr_mmu_context_destroy(vm_ctx->mmu_ctx);
 	drm_gem_private_object_fini(&vm_ctx->dummy_gem);
@@ -758,7 +769,9 @@ pvr_vm_map(struct pvr_vm_context *vm_ctx, struct pvr_gem_object *pvr_obj,
 
 err_cleanup:
 	mutex_unlock(&vm_ctx->lock);
+
 	pvr_vm_bind_op_fini(&bind_op);
+	drm_gpuvm_bo_deferred_cleanup(&vm_ctx->gpuvm_mgr);
 
 	return err;
 }
@@ -840,6 +853,8 @@ pvr_vm_unmap_obj(struct pvr_vm_context *vm_ctx, struct pvr_gem_object *pvr_obj,
 	err = pvr_vm_unmap_obj_locked(vm_ctx, pvr_obj, device_addr, size);
 	mutex_unlock(&vm_ctx->lock);
 
+	drm_gpuvm_bo_deferred_cleanup(&vm_ctx->gpuvm_mgr);
+
 	return err;
 }
 
@@ -874,6 +889,8 @@ pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size)
 
 	mutex_unlock(&vm_ctx->lock);
 
+	drm_gpuvm_bo_deferred_cleanup(&vm_ctx->gpuvm_mgr);
+
 	return err;
 }
 
@@ -906,6 +923,8 @@ pvr_vm_unmap_all(struct pvr_vm_context *vm_ctx)
 	}
 
 	mutex_unlock(&vm_ctx->lock);
+
+	drm_gpuvm_bo_deferred_cleanup(&vm_ctx->gpuvm_mgr);
 }
 
 /* Static data areas are determined by firmware. */

-- 
2.43.0