drm/i915/vm_bind: Handle persistent vmas in execbuf3

Handle persistent (VM_BIND) mappings during the request submission
in the execbuf3 path.

Signed-off-by: Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com>

1 files changed, 164 insertions, 0 deletions

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer_vm_bind.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer_vm_bind.c
index 132d4ab6f5cf..3c2a17480d7b 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer_vm_bind.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer_vm_bind.c
@@ -35,6 +35,7 @@
 #include "i915_trace.h"
 #include "i915_user_extensions.h"
 
+#define __EXEC3_HAS_PIN			BIT_ULL(30)
 #define __EXEC3_ENGINE_PINNED		BIT(29)
 #define __EXEC3_INTERNAL_FLAGS		(~0u << 29)
 
@@ -113,6 +114,19 @@ eb_find_vma(struct i915_address_space *vm, u64 addr)
 	return i915_gem_vm_bind_lookup_vma(vm, va);
 }
 
+static void eb_scoop_unbound_vmas(struct i915_address_space *vm)
+{
+	struct i915_vma *vma, *vn;
+
+	spin_lock(&vm->vm_rebind_lock);
+	list_for_each_entry_safe(vma, vn, &vm->vm_rebind_list, vm_rebind_link) {
+		list_del_init(&vma->vm_rebind_link);
+		if (!list_empty(&vma->vm_bind_link))
+			list_move_tail(&vma->vm_bind_link, &vm->vm_bind_list);
+	}
+	spin_unlock(&vm->vm_rebind_lock);
+}
+
 static int eb_lookup_vmas(struct i915_execbuffer *eb)
 {
 	unsigned int i, current_batch = 0;
@@ -127,12 +141,118 @@ static int eb_lookup_vmas(struct i915_execbuffer *eb)
 		++current_batch;
 	}
 
+	eb_scoop_unbound_vmas(eb->context->vm);
+
+	return 0;
+}
+
+static int eb_lock_vmas(struct i915_execbuffer *eb)
+{
+	struct i915_address_space *vm = eb->context->vm;
+	struct i915_vma *vma;
+	int err;
+
+	err = i915_gem_vm_priv_lock(eb->context->vm, &eb->ww);
+	if (err)
+		return err;
+
+	list_for_each_entry(vma, &vm->non_priv_vm_bind_list,
+			    non_priv_vm_bind_link) {
+		err = i915_gem_object_lock(vma->obj, &eb->ww);
+		if (err)
+			return err;
+	}
+
 	return 0;
 }
 
+static void eb_release_persistent_vmas(struct i915_execbuffer *eb, bool final)
+{
+	struct i915_address_space *vm = eb->context->vm;
+	struct i915_vma *vma, *vn;
+
+	assert_vm_bind_held(vm);
+
+	if (!(eb->args->flags & __EXEC3_HAS_PIN))
+		return;
+
+	assert_vm_priv_held(vm);
+
+	list_for_each_entry(vma, &vm->vm_bind_list, vm_bind_link)
+		__i915_vma_unpin(vma);
+
+	eb->args->flags &= ~__EXEC3_HAS_PIN;
+	if (!final)
+		return;
+
+	list_for_each_entry_safe(vma, vn, &vm->vm_bind_list, vm_bind_link)
+		if (i915_vma_is_bind_complete(vma))
+			list_move_tail(&vma->vm_bind_link, &vm->vm_bound_list);
+}
+
 static void eb_release_vmas(struct i915_execbuffer *eb, bool final)
 {
+	eb_release_persistent_vmas(eb, final);
+	eb_unpin_engine(eb);
+}
+
+static int eb_reserve_fence_for_persistent_vmas(struct i915_execbuffer *eb)
+{
+	struct i915_address_space *vm = eb->context->vm;
+	struct i915_vma *vma;
+	int ret;
+
+	ret = dma_resv_reserve_fences(vm->root_obj->base.resv, 1);
+	if (ret)
+		return ret;
+
+	list_for_each_entry(vma, &vm->non_priv_vm_bind_list,
+			    non_priv_vm_bind_link) {
+		ret = dma_resv_reserve_fences(vma->obj->base.resv, 1);
+		if (ret)
+			return ret;
+	}
 
+	return 0;
+}
+
+static int eb_validate_persistent_vmas(struct i915_execbuffer *eb)
+{
+	struct i915_address_space *vm = eb->context->vm;
+	struct i915_vma *vma, *last_pinned_vma = NULL;
+	int ret = 0;
+
+	assert_vm_bind_held(vm);
+	assert_vm_priv_held(vm);
+
+	ret = eb_reserve_fence_for_persistent_vmas(eb);
+	if (ret)
+		return ret;
+
+	if (list_empty(&vm->vm_bind_list))
+		return 0;
+
+	list_for_each_entry(vma, &vm->vm_bind_list, vm_bind_link) {
+		u64 pin_flags = vma->start | PIN_OFFSET_FIXED | PIN_USER;
+
+		ret = i915_vma_pin_ww(vma, &eb->ww, 0, 0, pin_flags);
+		if (ret)
+			break;
+
+		last_pinned_vma = vma;
+	}
+
+	if (ret && last_pinned_vma) {
+		list_for_each_entry(vma, &vm->vm_bind_list, vm_bind_link) {
+			__i915_vma_unpin(vma);
+			if (vma == last_pinned_vma)
+				break;
+		}
+	} else if (last_pinned_vma) {
+		eb->args->flags |= __EXEC3_HAS_PIN;
+	}
+
+	return ret;
 }
 
 static int eb_validate_vmas(struct i915_execbuffer *eb)
@@ -152,8 +272,17 @@ retry:
 	/* only throttle once, even if we didn't need to throttle */
 	throttle = false;
 
+	err = eb_lock_vmas(eb);
+	if (err)
+		goto err;
+
+	err = eb_validate_persistent_vmas(eb);
+	if (err)
+		goto err;
+
 err:
 	if (err == -EDEADLK) {
+		eb_release_vmas(eb, false);
 		err = i915_gem_ww_ctx_backoff(&eb->ww);
 		if (!err)
 			goto retry;
@@ -177,8 +306,43 @@ err:
 	BUILD_BUG_ON(!typecheck(int, _i)); \
 	for ((_i) = (_eb)->num_batches - 1; (_i) >= 0; --(_i))
 
+static void __eb_persistent_add_shared_fence(struct drm_i915_gem_object *obj,
+					     struct dma_fence *fence)
+{
+	dma_resv_add_fence(obj->base.resv, fence, DMA_RESV_USAGE_READ);
+	obj->write_domain = 0;
+	obj->read_domains |= I915_GEM_GPU_DOMAINS;
+	obj->mm.dirty = true;
+}
+
+static void eb_persistent_add_shared_fence(struct i915_execbuffer *eb)
+{
+	struct i915_address_space *vm = eb->context->vm;
+	struct dma_fence *fence;
+	struct i915_vma *vma;
+
+	fence = eb->composite_fence ? eb->composite_fence :
+		&eb->requests[0]->fence;
+
+	__eb_persistent_add_shared_fence(vm->root_obj, fence);
+	list_for_each_entry(vma, &vm->non_priv_vm_bind_list,
+			    non_priv_vm_bind_link)
+		__eb_persistent_add_shared_fence(vma->obj, fence);
+}
+
+static void eb_persistent_vmas_move_to_active(struct i915_execbuffer *eb)
+{
+	/* Add fence to BOs dma-resv fence list */
+	eb_persistent_add_shared_fence(eb);
+}
+
 static int eb_move_to_gpu(struct i915_execbuffer *eb)
 {
+	assert_vm_bind_held(eb->context->vm);
+	assert_vm_priv_held(eb->context->vm);
+
+	eb_persistent_vmas_move_to_active(eb);
+
 	/* Unconditionally flush any chipset caches (for streaming writes). */
 	intel_gt_chipset_flush(eb->gt);